No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Assessment of waste characteristics and their impact on GIS vehicle collection route optimization using ANN waste forecasts
Abstract
Combining an artificial neural network (ANN) waste prediction model with a geographic information system (GIS) waste collection route optimization, the paper shows how the compositional features of waste materials affect the optimized truck route time, distance, and air emissions. Using data from Austin, Texas, USA, a nonlinear autoregressive ANN model is used to predict the waste generation rate of the recycling and garbage streams for the year 2023 in four sub-areas of the city. This ANN model resulted in mean absolute percentage errors ranging from 10.92% to 16.51%. Modified compositions of the recycling and garbage streams are then used as inputs, along with the year 2023 generation rates, to create 6 modified and 3 non-modified scenarios that reflect possible future changes in waste composition. These waste stream scenarios are then used as input parameters to determine optimal waste collection routes with minimal travel distance in each of the four sub-areas using the GIS vehicle routing problem network analysis tool. Results of these 36 scenarios yield changes in travel distance of up to 19.9%, when compared to the non-modified composition. Further, dual compartment trucks were compared to single compartment trucks and found to save between 10.3 and 16.0% in travel distance and slightly reduce emissions but had a 15.7–19.8% increase in collection time. Results suggest temporal changes in waste composition and characteristics are important in GIS route optimization studies.
... Integrated GIS models have also optimized bin locations and collection routes, significantly reducing crew requirements and travel distances [57]. In another example, an Artificial Neural Network (ANN) was combined with GIS to forecast waste generation and optimize truck collection routes, highlighting the relationship between waste composition and travel distances for effective route planning [58]. ...
... work (ANN) was combined with GIS to forecast waste generation and optimize truck collection routes, highlighting the relationship between waste composition and travel distances for effective route planning [58]. ...
... These examples underscore the financial and infrastructural burden associated with the implementation of circular economy strategies and smart waste technologies. Moreover, while innovations such as dual-compartment waste collection trucks can reduce travel distances by 10-16%, they also increase collection time by up to 19.8% [58], demonstrating trade-offs between cost, efficiency, and sustainability. ...
Efficient waste management remains critical to achieving sustainable urban development, addressing challenges related to resource conservation, environmental preservation, and carbon emissions reduction. This review synthesizes advancements in waste management technologies, focusing on three transformative areas: optimization techniques, the integration of electric vehicles (EVs), and the adoption of smart technologies. Optimization methodologies, such as vehicle routing problems (VRPs) and dynamic scheduling, have demonstrated significant improvements in operational efficiency and emissions reduction. The integration of EVs has emerged as a sustainable alternative to traditional diesel fleets, reducing greenhouse gas emissions while addressing infrastructure and economic challenges. Additionally, the application of smart technologies, including Internet of Things (IoT), artificial intelligence (AI), and the Geographic Information System (GIS), has revolutionized waste monitoring and decision-making, enhancing the alignment of waste systems with circular economy principles. Despite these advancements, barriers such as high costs, technological complexities, and geographic disparities persist, necessitating scalable, inclusive solutions. This review highlights the need for interdisciplinary research, policy standardization, and global collaboration to overcome these challenges. The findings provide actionable insights for policymakers, municipalities, and businesses, enabling data-driven decision-making, optimized waste collection, and enhanced sustainability strategies in modern waste management systems.
... Medical Solid Waste (MSW) collection and transportation has become a major concern in large urban areas (Das & Bhattacharyya, 2015;Praveen et al., 2017;Vu et al., 2019). MSW should be collected directly from hospitals and medical centers, and transported to disposal sites as quickly as possible via safe and secure methods. ...
... Waste Collection VRP (WCVRP) is a particular VRP sub-category with specific operational and domain-related constraints that impose additional complexity (Dotoli & Epicoco, 2017). While several algorithms can address many complexities involved in standard VRPs (e.g., Akhtar et al., 2017;Bing et al., 2014;Eren & Tuzkaya, 2021;Hajibabai & Saha, 2019;Hannan et al., 2018;Hintsch & Irnich, 2018;Vu et al., 2019), WCVRP is different because it involves a fleet of vehicles dispatched from a depot to a set of collection points and disposal facilities. ...
... Other authors have used GIS tools to optimize sanitary waste management systems (Alagoz & Kocasoy, 2008;Shanmugasundaram et al., 2012). Vu et al. (2019) presented the optimization of the waste collection route using an ANN model and GIS, paying special attention to predicting the waste production rate, travel time, and distance traveled. They divided the study area into four sub-areas and found that travel distance decreased to 19.9%, influenced by changes in waste production rate and related characteristics. ...
Medical Solid Wastes (MSWs) are major hazardous materials containing harmful biological or chemical compounds that present public and environmental health risks. The collection and transportation of waste are usually informed by optimized work‐balanced routing based on comprehensive spatial data in urban traffic networks, called a Vehicle Routing Problem (VRP). This may be unsuitable for MSWs as their special category means they impose additional complexity. The present article develops a planar graph‐based cluster‐routing approach for the optimal collection of MSWs informed by a Geospatial Information System (GIS). The problem is first formulated as a mixed integer linear program in road network spatial data, in the context of Tehran city. The work has two key aims: (i) to minimize the total routing cost of MSW collection and transfer to waste landfills; (ii) to balance workload across waste collectors. There are three main contributions of the proposed approach: (i) to simplify the large search space area by converting the road network to a planar graph based on graph theory, spatial parameters, and topological rules; (ii) to use a modified K‐means algorithm for clustering; (iii) to consider average traffic impacts in the clustering stage and momentary traffic in the route planning stage. A planar graph extraction procedure is applied to capture the network sketch (i.e., a directed graph) from the traffic roadway network. An iterative cluster‐first‐route‐second heuristic is employed to solve the proposed routing problem. This heuristic customizes a K‐means algorithm to determine the optimal number and size of clusters (i.e., routes). A Traveling Salesman Problem (TSP) algorithm is applied to regulate the optimal sequence of visits to medical centers. The experimental results show improvements in balancing collectors' workload (i.e., ~4 min reduction in the standard deviation of average travel time) with reductions in travel time (i.e., an average ~1 h for the entire fleet and ~4 min per route). These findings confirm that the proposed methodology can be considered as an approach for optimizing waste collection routes.
... The researcher evaluated and proposed the potential of existing landfill sites and their area of effect for growth (Richter et al., 2019); this unique technique combines remote sensing and vector data. The literature on route analysis primarily focuses on optimizing waste collection and transportation using Vehicle Routing Problem (VRP) models (Vu et al., 2019;Zhang et al., 2015). Earlier studies often used capacitated VRPs to minimize travel distance but overlooked real-life constraints and regional variations in waste collection (Avellar et al., 2015;Vu et al., 2019). ...
... The literature on route analysis primarily focuses on optimizing waste collection and transportation using Vehicle Routing Problem (VRP) models (Vu et al., 2019;Zhang et al., 2015). Earlier studies often used capacitated VRPs to minimize travel distance but overlooked real-life constraints and regional variations in waste collection (Avellar et al., 2015;Vu et al., 2019). Integrating GIS for visual decision support and considering roll-on roll-off routing with large containers have been explored in some research (Lu et al., 2015). ...
Construction and demolition waste (C&DW) is increasing at an alarming rate globally. It is estimated that worldwide, C&DW occupies over 17,420,000 km² of land with an average depth of around 15.25 m, amounting to an astonishing 2.7 billion cubic meters of landfill space. The annual generation of C&D debris in India is up to 150 million tons. This study examines the use of geospatial technology to effectively manage C&DW disposal in the legal dumping yards of Chennai. Data were collected on C&DW in Chennai, which has 15 legal dumping sites and two recycling units in Perungudi and Kodungaiyur. Geospatial technology was applied to analyze optimal route planning, considering sources, and C&DW disposal locations, with two scenarios: the stationary container system and the hauled container system. The results suggest that the hauled container system is Chennai’s most suitable debris collection method, providing an optimal route with reduced environmental pollution. These findings are helpful for urban planners and environmental engineers, assisting in transforming old urban areas into new smart cities through effective planning and design.
... The model allows sequential decision making and evaluation of various strategies for different future scenarios with specific years, locations, technologies and capacities for the establishment of waste processing infrastructure. While in (Vu et al., 2019), not suggest a traditional stochastic approach, but rather generate scenario from a nonlinear autoregressive ANN model to predict the waste generation rate of the recycling and garbage streams, resulting in mean absolute percentage errors that ranged from 10.92% to 16.51%. What is used as inputs are the modified compositions of the recycling and trash streams, along with the year's generation rates, to create 6 modified and 3 unmodified scenarios that reflect possible future changes in waste composition. ...
... (Kůdela et al., 2020) Multi-stage model for waste processing infrastructure Sequential decision making for treatment plant locations and sizing with strategy evaluation. (Vu et al., 2019) Scenario generation based on waste generation rate predictions. ...
The accelerated growth of cities, population increase and economic development have leveraged waste generation globally. This trend is expected to continue, with a significant increase projected in the coming years. Therefore, efficient waste management has become a crucial concern for local, national and international authorities. Transportation plays a key role in waste collection and disposal, being directly related to traffic congestion, fuel consumption and environmental pollution. Despite the existing studies on household waste collection, there is a gap in the literature regarding routing for residential waste collection in medium-sized cities, especially in emerging and frontier developing countries. Therefore, this study seeks through the science tree metaphor and PRISMA methodology, to find studies focused on the vehicle routing problem in waste collection operations, considering aspects such as Modeling approaches and solution techniques, applied Vehicle Routing Problems variants, objective functions, decision variables and constraints, applications in real environments, applied algorithms, and studies considering uncertainty and real conditions. A methodological outline of Vehicle Routing Problems in waste collection operations is presented, where central research topics are identified such as processes developed with Geographic Information System and their integration with exact methods, time windows, multi-objective capacitated vehicle routing problems, the application of stochastic models consider the uncertainty in waste collection, which has allowed including future prediction and optimization as prediction models, based on neural networks, to foresee uncertain conditions of the operations. This article analyzes the evolution in the optimization of municipal solid waste collection routes since 1964, highlighting the transition from iterative models to advanced technologies and multi-objective approaches. The importance of tools such as 3D Geographic Information System and heuristic/metaheuristic algorithms in improving planning and efficiency, despite limitations in the face of uncertainty, is emphasized. The systematic review shows a trend towards sustainable and efficient solutions, indicating future directions for research in urban waste management.
... The presence of interactions among various elements of the waste management system makes it challenging to assess the environmental impacts of such decisions. By analysing the relationships between waste characteristics and GIS-based truck route planning, Vu et al. [11,12] observed that truck travel distances depend on collection frequency, truck capacity, compartment volume ratio, and waste density. The results suggest that increasing waste density and decreasing the collection frequency significantly reduce travel distances, with respective decreases of 18.2% and 41.9%. ...
... These data, combined with participating dwellings, allow collection time calculation and the needed collection labour (Equation (11)). With truck specifications (C f uel,t , tCO 2 f uel ), collection labour facilitates environmental and energy impact calculation (Equations (12) and (13)). Similarly, Equations (14)- (16) have been developed to quantify impacts caused by the waste material transport phase. ...
The effective management of urban waste represents a growing challenge in the face of demographic evolution and increased consumption. This study explores the impacts of municipal strategic decisions on household waste management behaviours and sustainability performance outcomes through agent-based modelling. Using data from Gatineau and Beaconsfield in Quebec, Canada, the model is calibrated and validated to represent diverse urban contexts. Our analysis demonstrates that reducing collection frequency leads to notable increases in participation rates, reaching 78.2 ± 5.1% for collections every two weeks and 96.5 ± 8.3% for collections every five weeks. While this reduction improves bin filling levels, it concurrently decreases the recovery of recyclable materials by 2.8% and 19.5%, significantly undermining the environmental benefits of the recycling program. These findings highlight a complex interplay between collection frequency, citizen participation behaviour, waste stream characteristics, and overall environmental performance. While reducing collection frequency initially appears beneficial, it leads to operational challenges and increased CO2 emissions due to reduced material recovery. The research emphasises the need for tailored holistic waste management strategies that optimise performance outcomes while minimising environmental impacts. By understanding these dynamics, municipalities can develop more effective waste management policies that promote sustainability.
... Work done and methodology used Lin et al., 2011 MSW collection done by using Ant colony optimization (ACO) algorithm to provide flexibility to local residents Lin and Kao, 2008 MSW collection done by using mixed-integer optimization model considering factors such as road network integrity, collection cost, compactness, and regional Optimization of MSW collection routes with travelling salesman problem (TSP) Vecchi et al., 2016 Mathematical modelling and Linear programming for optimizing MSW collection routes Laureri et al., 2016 A heuristic procedure was developed for the optimal planning of wet waste collection Khan and Samadder, 2016 Allocation of MSW collection bins and route optimisation using ArcGIS (Network Service area solver and Network Analyst) Lella et al., 2017 MSW collection and transportation optimization using vegetation land cover estimation (NDVI mapping) and ArcGIS-Network Analyst Hannan et al., 2018 MSW collection and route optimization using a modified particle swarm optimization (PSO) algorithm Vu et al., 2019 Combining of artificial neural network (ANN) waste prediction model with GIS route optimization for MSW collection Singhal and Goel, 2021a Developed an integrated solid waste management (ISWM) plan using Google ...
... In such cases, designing collection routes manually will be difficult and manually designed routes may lead to inadequate collection efficiency. For such case route optimization, mathematical or/and multicriteria decision modelling or Network analyst extension in Arc-GIS should be used (Das and Bhattacharyya, 2015;Khan and Samadder, 2016;Son and Louati, 2016;Vu et al., 2019). Even though Google earth is easy to use and contains large data set of historical imagery, however planimetric accuracy of the images in Google Earth can vary significantly depending on the region/country (Goudarzi and Landry, 2017;Pulighe et al., 2016). ...
Due to lack of monitoring and data availability, designing an efficient municipal solid waste (MSW) storage and collection system is a big challenge for many urban areas in developing nations. However, with the help of available remote sensing and geographic information system (RS and GIS) tools, the efficiency of the MSW collection system can be increased substantially. Google Earth and Google Maps are online freely available and easily accessible tools which can be utilized for improving the efficiency of waste management system. In the present study, a simple approach for developing a waste collection system is illustrated which requires a very less amount of data and easily accessible RS and GIS tools. By using basic population, waste composition, and per capita waste generation data, bin sizes were calculated for secondary waste collection with proper waste segregation. Then by using Google Earth Pro software and effective population density data, service areas for the bins and bin location plan were prepared. For sketching waste collection routes, Google Earth pro software was used by following the manual vehicle routing approach. For selecting an appropriate time for the secondary waste collection, historical traffic data of the road network was used which is freely available in Google Maps. The approach used in the present study can be effectively replicated for small to large cities to develop an integrated solid waste management system. For better collection efficiency, the present approach can be combined with linear programming or multicriteria decision modelling for collection route optimization.
... Most of these researchers have used ANN, GA, and LR in their optimization models for garbage collection frequency and efficient planning of collection routes. For instance, (Vu et al., 2019) integrated an ANN) with GIS for waste collection route optimization. This research demonstrates how different garbage types affect the optimal timing of routes, the distance covered, and air emissions. ...
Harnessing Artificial Intelligence (AI) for smart waste management presents a transformative approach to addressing the growing challenges of waste collection, transportation, and disposal, particularly in urban and underserved communities. The surge in the accumulation of solid waste and its implications for human health and the environment has attracted worldwide attention. This increased awareness emphasizes the significance of reusing, recycling, and incorporating AI in solid waste management. This manuscript presents a systematic review and scientometric study adhering to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) to evaluate the application of AI in solid waste management, focusing on its effectiveness in optimizing waste collection, sorting, and disposal processes. The review includes studies published between 2010 and 2023, sourced from PubMed, IEEE Xplore, Scopus, Web of Science, and Google Scholar databases. Only peer-reviewed articles published in English were considered. The findings indicate that AI models significantly enhance waste management efficiency, including route optimization, waste sorting, and energy recovery, although challenges such as data quality and model transparency persist. The risk of bias was assessed using standardized tools, revealing variability in study reliability and generalizability. The results were synthesized narratively, supported by quantitative data where available. While AI shows promise in enhancing operational efficiency, further research is needed to address limitations related to data quality and applicability across diverse contexts. Policymakers are encouraged to develop supportive frameworks to facilitate the adoption of AI in waste management.
... The integration of Geographic Information Systems (GIS) with machine learning has proven beneficial for optimizing waste collection routes. Studies by (Arefin et al., 2024) and (Vu et al., 2019) illustrate how GISbased approaches can enhance spatial analysis. The Internet of Things (IoT) has emerged as a transformative technology in waste management. ...
Municipal Solid Waste Management is an increasingly critical challenge in urban areas, intensified by rapid urbanization, population growth, and evolving consumption patterns. This study investigates the application of machine learning techniques to predict municipal solid waste generation in Sheger City, Koye Sub-city, Ethiopia, using data from 2009 to 2023. Three machine learning models, ARIMA, RF, and LSTM, were employed to forecast waste generation trends for the period 2024–2028, considering various socio-economic and demographic factors. Among the models, LSTM demonstrated the highest accuracy, with MSE of 1.62 × 10⁸ tonnes, MAE of 9,500 tonnes, and R² of 0.93. These results outperformed ARIMA (MSE = 3.84 × 10⁸ tonnes², MAE = 15,200 tonnes, R² = 0.85) and RF (MSE = 2.91 × 10⁸ tonnes², MAE = 12,800 tonnes, R² = 0.89). The forecasts predict an 8.5% increase in total waste generation, from 3,852,150 tonnes in 2023 to 4,177,500 tonnes by 2028. Notable growth is expected in high-volume waste streams, including food waste (13.5% increase) and plastic waste (8.9% increase). These findings highlight the urgent need for enhanced waste management strategies, including expanded recycling programs and policy interventions. This study provides a robust framework for leveraging machine learning models to guide waste management decisions, contributing to more sustainable urban waste management practices in rapidly growing cities.
... The advantage of this approach is that it employs different environmental data sources, GIS, and statistical datasets to train ANN model [54]. Such data-driven approach enables to better recognise complex landscape patterns for environmental mapping using spatial-temporal data and ANN algorithms [55] and is useful in environmental forecasting [56,57]. ...
Image processing using Machine Learning (ML) and Artificial Neural Network (ANN) methods was investigated by employing the algorithms of Geographic Resources Analysis Support System (GRASS) Geographic Information System GIS with embedded Scikit-Learn library of Python language. The data are obtained from the United States Geological Survey (USGS) and include the Landsat 8 Operational Land Imager/Thermal Infrared Sensor (OLI/TIRS) multispectral satellite images. The images were collectedon 2013 and 2023 to evaluate land cover categories in each of the year. The study area covers the region of Nile Delta and the Faiyum Oasis, Egypt. A series of modules for raster image processing was applied using scripting language of GRASS GIS to process the remote sensing data. The satellite images were classified into raster maps presenting the land cover types. These include ‘i.cluster’ and ‘i.maxlik’ for non-supervised classification used as training dataset of random pixel seeds, ‘r.random’, ‘r.learn.train’, ‘r.learn.predict’ and ‘r.category’ for ML part of image processing. The consequences of various ML parameters on the cartographic outputs are analysed, such as speed and accuracy, randomness of nodes, analytical determination of the output weights, and dependence distribution of pixels for each algorithm. Supervised learning models of GRASS GIS were tested and compared including the Gaussian Naive Bayes (GaussianNB), Multi-layer Perceptron classifier (MLPClassifier), Support Vector Machines (SVM) Classifier, and Random Forest Classifier (RF). Though each algorithms was developed to serve different objectives of ML applications in RS data processing, their technical implementation and practical purposes present valuable approaches to cartographic data processing and image analysis. The results shown that the most time-consuming algorithms was noted as SVM classification, while the fastest results were achieved by the GaussianNB approach to image processing and the best results are achieved by RF Classifier.
... Most of these studies concentrate on using ANN, GA, and LR to optimize waste collection frequency and route planning models (Liang and Gu, 2021;Selvakanmani et al., 2024). For instance, Vu et al. (2019) integrate a geographic information system (GIS) waste collection route optimization tool with an ANN waste prediction model. The study demonstrates how the optimal truck route time, distance, and air emissions are influenced by the compositional features of waste materials. ...
Rapid urbanization, economic expansion, and population growth have increased waste
generation in many nations worldwide. Research on municipal waste management (MWM) is moving towards new frontiers in efficiency and applicability due to the growing amount of data being collected in these systems and the convergence of various technological applications. Artificial intelligence (AI) techniques present novel and creative alternatives for MWM. Even though much research has been conducted in this field, relatively few review studies have assessed how advancements in AI techniques can contribute to the sustainable advancement of MWM systems. Furthermore, there are discrepancies and a dearth of knowledge regarding the operation of AI-based techniques in MWM. To close this gap, this study conducts a thorough review of the literature with an application of preferred reporting items for systematic reviews and meta-analyses-based methods, examining 229 peer-reviewed publications to explore the role of AI in different MWM areas, such as waste characteristics forecasting, waste bin level monitoring, process parameter prediction, vehicle routing, and MWM planning. The main AI techniques and models used in MWM optimization, as well as the application areas and stated performance metrics, are all thoroughly analyzed in this review. A conceptual framework is proposed to guide research and practice to take a holistic approach to MWM, along with areas of
future study that need to be explored. Researchers, policymakers, municipalities, governments, and other waste management organizations will benefit from this study to minimize costs, maximize efficiency, eliminate the need for manual labor, and change how MWM is approached.
Keywords: Artificial intelligence; Conceptual framework; Municipal waste; Optimization;
Performance metrics; Systematic literature review
... These optimized routes can reduce travel distances and vehicle counts, lowering labor expenses, fuel costs, operating time, and greenhouse gas emissions (Abdelli et al., 2016;Vu et al., 2018). This routing process is comparable to the Traveling Salesman Problem (TSP), a classic NP puzzle (Vu et al., 2019). The TSP solutions can be divided into two categories. ...
Accurate assessment of distribution patterns and dynamic insights into rural populations is pivotal for comprehending domestic waste generation, recycling, and transportation in rural territories. Given that the dispersion of rural inhabitants exhibits minimal variation and maintains stability, this research endeavors to establish a pragmatic model for rural domestic waste collection and routing, leveraging the capabilities of very high-resolution remote sensing combined with geographic information system (GIS) techniques. Specifically, the Dilated LinkNet model was employed to discern features such as buildings, roads, water bodies, farmlands, and forests from the high-resolution remote sensing imagery. A novel multiple K-means clustering approach was devised for building segmentation. Within these clusters, an assortment of spatial regulations and evaluations facilitated the judicious selection of environmentally-conscious waste collection sites (WCSs). The Pointer Network, augmented with reinforcement learning, executed a traveling salesman analysis on these chosen WCSs, yielding the optimal collection trajectory. Validated in Huangtu Town, a quintessential rural region in China, our model manifested superior recognition precision, recording IoU accuracies of 0.902, 0.926, 0.933, 0.891, and 0.849 for buildings, roads, water bodies, farmlands, and forests respectively. Notably, when compared to our field survey data, the optimized daily collection route in a rural context decreased from 256.40 km before optimization to 140.44 km, reflecting a substantial reduction of 45.23% in total distance. This study furnishes an effective model that relies solely on information from remote-sensing images for efficient rural waste collection and extends invaluable insights to planners and administrators in the realm of rural and township waste management.
... The ANN is extensively used and applied in many applications [24], including forecasting and prediction. This paper uses one hundred seventy datasets for training and validation and 52 for testing. ...
Garbage management is exceptionally critical and poses enormous environmental challenges. It has always been a vital issue in municipal corporations. However, municipal agencies have developed and used garbage management systems. Garbage forecasting still plays a crucial role in the management system and helps improve or create a garbage management system. This research examines the information from 212 cities to suggest a helpful regression model for garbage forecasting and control. To establish a connection between the variables, the descriptive study employs statistical techniques to learn about the composition of data collected from municipal corporations and conduct correlation analysis. Population and garbage depend highly on one another, as evidenced by their correlation coefficient of 0.922,144. The primary research is used to build an alternate hypothesis that shows the chosen variables are highly dependent on one another. The dataset is scaled and divided into a training and testing 80:20 ratio during the pre‐processing data phase. This research aims to do a regression analysis with daily garbage production, urban area, and population as independent variables. This research initiates a variety of regression models, including multiple linear regression (MLR), artificial neural network (ANN), decision tree regression (DTR), and random forest regression (RFR). The MLR model's R2 value of 0.85 indicates that it has the potential to accurately forecast daily garbage production based on just two independent variables and a single dependent variable. Random Forest Regression (RFR) with (MSE: 100,078.749 & MAE: 182.212) shows that it has the lowest MSE among all the models, which provides the most accurate predictions on average and the fit values of 8.85 and 316.23 obtained from the error distribution with a bin value 25. The estimated results from each model are compared to the test data values on line graphs and Taylor plots. The mean square error and the mean absolute error in the analysis and the Taylor plot show that the RFR model is best suited for predicting daily garbage production in a city. This research, therefore, provides a Random Forest model that is optimal for such challenges and is recommended for this class of problem.
... Commonly employed techniques encompass GA, ANN, and LR (Abdallah et al., 2020;Król et al., 2016). For instance, Vu et al. (2019) combined an ANN-based waste prediction model with a Geographic Information System (GIS)-grounded waste collection route optimization approach. This research delved into the influence of waste material composition on optimized factors such as truck route time, distance, and air emissions. ...
... The Harmony Search algorithm is used by an online system that supports e-waste collection for optimization of waste collection vehicles' routes [40]. The waste inputs came from a time series ANN nonlinear autoregressive model, and a waste collection model was developed utilizing a vehicle routing problem network analysis within a geographic information system (GIS) [41]. • Predictive maintenance: Artificial intelligence technologies grew in prominence over time by providing various computer solutions to the intelligent waste problem. ...
Artificial intelligence (AI) can help improve many areas of waste management and biogas generation. The world has reached a state where waste generation is increasing daily, while an effective waste management system is essential for the sustainable development of a country. AI could be of great use in optimizing the waste management scheme by technical differentiation of all sorts and recycling techniques. AI can contribute to the improvement of waste segmentation, recycling, and disposal. Thus, by assessing availability and composition, AI can easily contribute to the selection of the most suitable feedstock for biogas generation. This paper will discuss the optimization of gasifier design, an important part of biogas production, to enhance gasification efficiency for more efficient syngas production. Several gains accrue from AI applications, and among them is the selection of feedstocks and gasifiers optimal for more efficient and sustainable waste management and use in the production of biogas systems. This review paper identifies the potential application areas in either waste management practices or biogas production and puts forward ways in which AI can be used in these areas.
... In order to address this problem, computational studies have boarded the problem using different approaches. On the one hand, metaheuristic optimization techniques have been employed at municipal scale (Rada et al., 2013;Sumathi et al., 2008;Vu et al., 2019), On the other hand, mathematical optimization, based on mixed-integer linear programming (MILP), has been employed to design the supply chains (Santander et al., 2020) at a regional and national levels (Xu et al., 2017). By following this MILP approach, recent work on plastic upcycling has studied pyrolysis as a viable technology (Ma et al., 2023). ...
... The processed monthly disposal records were used to train the three models and tested the model performance in different testing years (2019, 2020, and 2021). An identical train/test split of 85:15 was used for all subsets due to its satisfactory performance in waste forecasting models (Kannangara et al. 2018;Vu et al. 2019b). Python 3.10.0 ...
In this study, three different univariate municipal solid waste (MSW) disposal rate forecast models (SARIMA, Holt-Winters, Prophet) were examined using different testing periods in four North American cities with different socioeconomic conditions. A review of the literature suggests that the selected models are able to handle seasonality in a time series; however, their ability to handle outliers is not well understood. The Prophet model generally outperformed the Holt-Winters model and the SARIMA model. The MAPE and R² of the Prophet model during pre-COVID-19 were 4.3–22.2% and 0.71–0.93, respectively. All three models showed satisfactory predictive results, especially during the pre-COVID-19 testing period. COVID-19 lockdowns and the associated regulatory measures appear to have affected MSW disposal behaviors, and all the univariate models failed to fully capture the abrupt changes in waste disposal behaviors. Modeling errors were largely attributed to data noise in seasonality and the unprecedented event of COVID-19 lockdowns. Overall, the modeling errors of the Prophet model were evenly distributed, with minimum modeling biases. The Prophet model also appeared to be versatile and successfully captured MSW disposal rates from 3000 to 39,000 tons/month. The study highlights the potential benefits of the use of univariate models in waste forecast.
... As for the logistics of resource and product distribution, artificial neural networks are coming into play. Works by [9] and [10] focus on optimizing vehicle routes to not only cut distances but also to decrease fuel consumption and emissions, all while maintaining timely deliveries. ...
... The growing trend of machine learning has influenced research in this area. Vu et al. [38] integrate a machine learning technique called Artificial Neural Network to predict the demand in collection points, which provides better input for the route planning of waste collection. ...
This research introduces the Multi-Depot Waste Collection Vehicle Routing Problem with Time Windows and Self-Delivery Option (MDWCVRPTW-SDO). The problem comes from the waste bank operation implemented in Yogyakarta City, Indonesia. A set of vehicles is dispatched from the waste banks to pick up waste from residents’ locations within the time windows specified by the residents. Residents may be compensated for delivering their waste to a waste bank by themselves. The objective of MDWCVRPTW-SDO is minimizing the sum of investment costs, routing costs, and total compensation paid to the residents. We model this problem as a mixed integer linear programming model and propose Simulated Annealing (SA) as an effective solution approach. Extensive computational experiments confirm that SA is effective to solve MDWCVRPTW-SDO. Moreover, the number of waste banks, compensation paid to residents, and the distribution of residents of each type are crucial for the success of the implementation.
... Kumar et al. (2018) also configured five neurons at the hidden layer of their ANN model after referring to a past study. Vu et al. (2019a) applied ten neurons in the hidden layer based on their experience. ...
Improper municipal solid waste (MSW) management contributes to greenhouse gas emissions, necessitating emissions reduction strategies such as waste reduction, recycling, and composting to move towards a more sustainable, low-carbon future. Machine learning models are applied for MSW-related trend prediction to provide insights on future waste generation or carbon emissions trends and assist the formulation of effective low-carbon policies. Yet, the existing machine learning models are diverse and scattered. This inconsistency poses challenges for researchers in the MSW domain who seek to identify and optimize the machine learning techniques and configurations for their applications. This systematic review focuses on MSW-related trend prediction using the most frequently applied machine learning model, artificial neural network (ANN), while addressing potential methodological improvements for reducing prediction uncertainty. Thirty-two papers published from 2013 to 2023 are included in this review, all applying ANN for MSW-related trend prediction. Observing a decrease in the size of data samples used in studies from daily to annual timescales, the summarized statistics suggest that well-performing ANN models can still be developed with approximately 33 annual data samples. This indicates promising opportunities for modeling macroscale greenhouse gas emissions in future works. Existing literature commonly used the grid search (manual) technique for hyperparameter (e.g., learning rate, number of neurons) optimization and should explore more time-efficient automated optimization techniques. Since there are no one-size-fits-all performance indicators, it is crucial to report the model's predictive performance based on more than one performance indicator and examine its uncertainty. The predictive performance of newly-developed integrated models should also be benchmarked to show performance improvement clearly and promote similar applications in future works. The review analyzed the shortcomings, best practices, and prospects of ANNs for MSW-related trend predictions, supporting the realization of practical applications of ANNs to enhance waste management practices and reduce carbon emissions.
... Machine learning applications in waste management have also gained prominence as municipalities need solutions for handling increasing volumes of waste. Machine learning algorithms can analyze large datasets, identify patterns and make predictions, leading to improvements in the optimization of collection routes and predictive analytics for waste generation (Vu et al., 2019). More recent applications include smart bins, informing when a bin is likely to reach its capacity, preventing overflow and collections of partially filled bins (Ghahramani et al., 2021). ...
Purpose
The purpose of this study is to formulate an algorithm designed to discern the optimal routes for efficient municipal solid waste (MSW) collection.
Design/methodology/approach
The research method is simulation. The proposed algorithm combines heuristics derived from the constructive genetic algorithm (CGA) and tabu search (TS). The algorithm is applied in a municipality located at Southern Brazil, with 40,000 inhabitants, circa.
Findings
The implementation achieved a remarkable 25.44% reduction in daily mileage of the vehicles, resulting in savings of 150.80 km/month and 1,809.60 km/year. Additionally, it reduced greenhouse gas emissions (including fossil CO 2 , CH 4 , N 2 O, total CO 2 e and biogenic CO 2 ) by an average of 26.15%. Moreover, it saved 39 min of daily working time.
Research limitations/implications
Further research should thoroughly analyze the feasibility of decision-making regarding planning, scheduling and scaling municipal services using digital technology.
Practical implications
The municipality now has a tool to improve public management, mainly related with municipal solid waste. The municipality reduced the cost of public management of municipal solid waste, redirecting funds to other priorities, such as public health and education.
Originality/value
The study integrates MSW collection service with an online platform based on Google MapsTM. The advantages of employing geographical information systems are agility, low cost, adaptation to changes and accuracy.
... The designed routes can be recalculated to provide corresponding solutions. In waste collection studies, for example, (Vu et al., 2019) utilized GIS to determine an optimal route for waste collection. (Rahman et al., 2008) employed a 3D version of GIS software to identify paths with the lowest fuel usage. ...
This study provides an in-depth exploration of the urban municipal solid waste (MSW) collection issue in the urban context, where there is a continuous rise in individual waste production levels and vulnerability to climate change, particularly in developing countries. The research focuses on a specialized vehicle routing model to optimize the solid waste transportation system within the city, aiding civil engineers and urban planners in strategically locating waste collection station positions for efficient waste collection routes. To enhance the model’s efficiency, a novel combined method is proposed, integrating with the Pelican Optimization Algorithm (POA). Experimental evaluations, conducted using real-world data, unequivocally demonstrate that the proposed combined method outperforms alternative approaches, including the current manual MSW collection process in the city. This research makes a significant contribution to the fields of waste management and urban sustainability, with the ultimate goal of mitigating the social, economic, and environmental consequences associated with urban solid waste collection.
... Sanjeevi and Shahabudeen [17] tested the applications of ArcGIS to find the optimal routes that would introduce cost-reduction opportunities in parts of Chennai, India. A few researchers [18,19] attempted to infuse GIS with other algorithms and models such as evolutionary algorithms, equation-based and agentbased models, to find optimised routing solutions. However, limited research on the subject is available in which such systems' full potential is realised. ...
p>In the realm of waste management, efficient route optimisation for municipal solid waste (MSW) collection is becoming increasingly crucial, particularly for developing nations with budgetary considerations. This study leverages the capabilities of the geographic information system (GIS) and integrates the Dijkstra algorithm to enhance route optimisation for MSW vehicles in Bahrain. Utilising comprehensive local vehicle routing data from Urbaser and applying GIS methodologies, three distinct areas in Bahrain were methodically analysed. The results revealed a notable 55% reduction in travel distance, a 17% decrease in time, and a yearly fuel cost saving of 6405 BHD (16,974 USD) in the optimal scenario. Given these findings, the potential applicability of this optimisation algorithm extends beyond Bahrain, suggesting significant benefits for regions with similar challenges. To further refine this approach, the integration of real-time traffic data into the routing algorithm is recommended. Other additions to the optimization process could include additional parameters such as safety.</p
... In terms of resource and product distribution, AI also proves beneficial. For instance [58,43], utilize ANNs to address routing problems, optimizing distribution vehicle routes to minimize distances, reduce gas emissions, and ensure on-time product delivery based on real-time geographical context information. ...
The fashion industry often falls short of sustainability goals, but contemporary technological advancements offer a wide range of tools to address this issue. Artificial Intelligence (AI) has emerged as a particularly promising ally in promoting sustainability in fashion. This literature review explores how AI can contribute to the fashion industry’s sustainability, highlighting its potential benefits and limitations. Following PRISMA guidelines, we conducted a review of scientific documents, focusing on the period from 2010 to 2022. After a meticulous selection process, we analyzed 37 scholarly articles to distill their key insights and contributions. Our findings demonstrate that AI has diverse applications in different aspects of the fashion industry, enhancing sustainability efforts in supply chain management, creative design, sales and promotion, waste control, and data analysis. While AI offers significant potential, it is important to acknowledge limitations, such as the volume of data required and associated implementation costs. The reviewed literature aligns with the multifaceted nature of sustainability, emphasizing responsible resource management, accessible services, and efficient customer satisfaction, both now and in the future. In conclusion, despite some reservations, AI stands as a crucial partner in guiding the fashion industry toward a more sustainable future.
... AI is capable of processing and analysing large amounts of both structured and unstructured data (e.g., images, videos, and audio) in high dimensions. This characteristic could largely improve automatic waste recognition and classification; greatly assist smart waste collection location, route planning, and time scheduling; and tremendously increase the quality of intelligent prediction of the amount of waste (Abbasi et al., 2014;Jull et al., 2018;Vu et al., 2019). ...
... Monitor generating waste, report the performance, and collaborate with recycling facilities. Modeling (Nguyen-Trong et al., 2017;Rashid et al., 2020;Tushar et al., 2018;Vu et al., 2019) Simulation Discrete Event Simulation (DES) optimizes the waste collection, transportation, sorting, recycling, and disposal process. The environmental and economic model Life Cycle Assessment (LCA) assesses environmental impacts, and the costeffectiveness of waste management is justified by economic models' indicators (NPV, benefit-cost ratio, payback period). ...
... En esta misma línea se tiene el trabajo de[11], el cual aborda el tema de optimización de la red de transporte público en términos de reducir el tiempo de viaje y proporcionar acceso a áreas que actualmente no tienen suficiente acceso a la instalación de servicio. Este trabajo utilizó el Sistema de Información Geográfica (GIS), la Optimización del Enjambre de Partículas (PSO) y el Algoritmo Genético (GA) para modelar la ubicación de las paradas de autobús en la ciudad de Amman en Jordania para encontrar el tiempo de viaje óptimo y la capacidad de servicio de las paradas, reduciendo el tiempo de viaje tanto en horas pico, como fuera de ellas.El trabajo de[14] combina un modelo de predicción de desechos de una red neuronal artificial (ANN) con un sistema de información geográfica (GIS) orientado a la optimización de la ruta (GIS). Los resultados muestran ahorros importantes en tiempos y recorridos para los 36 escenarios analizados en Austin, Texas, EE. ...
Objetivo: Presentar el desarrollo de Rutia, un ecosistema de soluciones tecnológicas que incluyen elementos de inteligencia artificial, y analítica de datos para administrar rutas en el transporte de pasajeros en modalidad empresarial, turística y de transporte escolar además de los contratos y otras operaciones involucradas. Metodología: Se desarrolló la solución tecnológica a través de tres (3) fases Diseño y ajuste de la plataforma Rutia, Desarrollo y validación de nuevas funcionalidades y Despliegue de la estrategia comercial. Este trabajo presenta los resultados de su validación en ambiente real de la solución con un grupo de cinco (5) early adopters, lo que permitió la retroalimentación y validación de las funcionalidades de la plataforma. Resultados: La solución permite la optimización e Integración con GPS, aplicativos Móviles, digitalización de información y reportes de interés para el sector. Conclusiones: En términos generales la plataforma cumple con las expectativas de los usuarios e impacta de manera positiva en la productividad de los vehículos (aumento promedio del 21%), lo que se refleja en la disminución de tiempos de ejecución de ruta (12% en promedio), disminución de costos de ruta (12% en promedio) e incremento del volumen de la operación y satisfacción de usuarios.
... Idwan et al. [21] use genetic algorithm operators such as selection, crossover, and mutation to compute the optimal route for the sector's dumpsters. Vu et al. [22] integrated nonlinear autoregressive neural networks with GIS route optimization to investigate the effect of waste composition and weight on the optimized vehicle routes and emissions. Nowakowski P. [23] presents an online e-waste collection system that employs the Harmony Search algorithm for waste collection vehicle route optimization. ...
Due to the dramatic increase in the volume of e-waste and its complex composition, containing hazardous components, improper e-waste management poses significant risks to the environment, human health, and socio-economic sustainability. The application of intellectual technologies has given new opportunities for more effective e-waste management. This research aims at providing a comprehensive landscape of the body of research on smart e-waste management in China through a systematic literature review accompanied by content analysis. On this basis, the seminal research themes of the advanced digital technologies used in e-waste management literature were unfolded and discussed. The most recent developments of smart e-waste collection and sorting initiatives in China, which have been implemented and scaled up through local businesses and entrepreneurship programs as alternatives to informal approaches, were presented. It turns out that the results highlight the potential of smart technologies in e-waste management through (i) delivering the most recent academic research on smart e-waste recycling, (ii) showcasing cutting-edge smart e-waste recycling solutions, primarily from business and emerging technology firms, (iii) enhancing academic debate and bridging the gap between industry practitioners and the research community, (iv) identifying the main challenges and provide countermeasures for future smart e-waste management.
... Supply chain design studies have remarked the influence of waste heterogeneity (Burgess et al., 2021;Rutkowski and Rutkowski, 2017) and dispersion in low-density population areas on the cost of collecting specific plastic wastes. (Lombrano, 2009;Wong, 2010) In order to address this problem, computational studies have integrated geographical information systems and metaheuristic optimization, (Natesan and Sarkar, 2008;Rada et al., 2013;Vu et al., 2019) offering a solution at a municipal scale. Mathematical optimization, based on mixed-integer linear programming (MILP), is another alternative to design the supply chain (Santander et al., 2020) at a regional and national levels (Xu et al., 2017) and select the optimal treatment processes for municipal solid wastes. ...
... Considering the city's population and urbanization, more than about 200 tons of C&D waste is expected to be generated per day in the city. Construction and demolition waste are being diverted away from landfills in favour of sorting, recycling, and reusing due to increased stress on raw materials and a shortage of landfill space as a result of increasing rates of urbanisation (Vu et al., 2019). The SCC is yet to prepare a plan for managing the construction waste generated in the city. ...
Planning and implementing an integrated, effective solid waste management system is one of the biggest challenges in large cities. In this study, all the wards under the Shivamogga City Corporation (SCC) were surveyed to collect data on the number of households, commercial establishments and bulk waste generators to deter-mine the average waste generation rate in each ward. To determine the total waste generation in the city, aver-age quantity of waste generated by each generator was multiplied with the estimated number of waste generators. To find the average household waste generation, waste sampled from 400 households and 100commercial establishments was recorded. A waste characterisation study was also conducted over a period of 3 days at the transfer station. GIS techniques were used to prepare the various maps to understand the population growth, road network, ward boundaries etc. The study showed that the total quantity of waste generated in the Shivamogga city can be estimated as 210 tons per day (TPD), including 34 TPD of silt waste from drainage. Through the sampling studies conducted on field, it has been estimated that households and commercial establishments are the major waste generators in the city, with households generate about 55% of waste generated in the city and commercial establishments generate about 11% of the waste adding up to 66% of the total waste generated. This paper also provides recommendations on building adaptable solutions for the existing problems in Shivamogga.
Implementing sustainable solid waste management strategies depends on accurately predicting municipal solid waste (MSW). This study forecasts Chittagong City's waste production using the well-known Multilayer Perceptron (MLP), Support Vector Machine (SVM), and Gaussian Algorithm (GA). The model performance is evaluated based on Mean Absolute Percentage Error (MAPE), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE). Among these, the MLP algorithm demonstrates the highest accuracy in predicting future MSW generation. Waste compositions such as food, fabric, plastic, paper, and wood are also forecasted. Results indicate that by 2030, Chittagong will generate approximately 2,780 tons per day (TPD) of MSW, requiring 247.5 m ² of landfill space and emitting 51,183.57 tons of greenhouse gases (GHG) under the current waste management practices. This forecast supports decision-makers in modifying and updating waste management systems to achieve sustainability goals, highlighting the practical benefits of accurate predictions in resource optimization, environmental impact mitigation, and long-term planning.
Background
Medical waste should be collected, classified, and transported to the treatment plant within 48 h. If it is not disposed of in time, it will cause cross-infection, increasing the risk of disease transmission and environmental pollution. How to reasonably plan transportation routes to ensure that the medical waste can be transported to the treatment plant in time is very important.
Objective
There are usually two modes of transportation, the fastest speed and shortest path, how to reasonably plan the transportation scheme so that medical waste can be transported to the treatment plant for disposal in the specified time is the main purpose of this article.
Methods
The multi-agent modeling method is adopted. AnyLogic simulation software is used to model the transportation routes of 118 Grade III hospitals and 2 treatment plants in Beijing under the two transportation modes of fastest speed and shortest path.
Results
Based on the traffic index in Beijing, the speed range of 20 km/h–32 km/h is set up and divided into 4 parts and 24 levels with 0.5 km/h as the unit, and the 24 levels of medical waste transportation data set is formed. The key speed nodes of 21 km/h, 24 km/h and 29.5 km/h are identified.
Conclusions
The medical waste transportation model and transport data set formed in this paper have enriched the theory and data basis of medical waste transportation management. The key speed nodes of transportation model selection have important practical significance for the transportation management decision of medical waste in big cities.
Solid Waste Management (SWM) poses a major global challenge with significant environmental implications. The integration of Artificial Intelligence (AI) and Information and Communication Technology (ICT) has emerged as a promising solution to revolutionize waste management practices. This systematic literature review, which examines the application of AI and ICT in SWM over the past five years (2018-2023) and analyzes 152 research papers, explores their integration at various stages.In the production phase, AI-driven predictive models have outperformed traditional methods, improving waste forecasting accuracy and facilitating recycling initiatives. In waste collection, AI and ICT enable real-time route optimization, dynamic scheduling, and sensor-based monitoring, enhancing service delivery while reducing operational costs. Furthermore, AI-powered technologies have revolutionized waste sorting, precisely identifying and segregating recyclables from mixed waste streams, thereby increasing recycling rates and alleviating the burden on landfills. The article also identifies the constraints and challenges associated with these technologies and discusses potential strategies to address them. The main objective of this review is to provide guidance to SWM researchers interested in utilizing these technologies within their field. Additionally, it aims to enrich the ongoing conversation about sustainable waste management by offering insights into current practices and future trends.
Various economic, social, and cultural factors have contributed to the proliferation of illegal dumps, causing urban image degradation, population health impacts, and soil, air, and water contamination. Scientists developed remote sensing techniques to identify these red spots and thus contribute to their mitigation and control. They recently used these techniques to detect large areas of illegal waste dumping instead of using expensive field monitoring. Artificial intelligence algorithms have been used to process satellite images due to the availability of satellite images and the increase in the processing capacity of computer systems. This work presents the results of a satellite remote-sensing procedure to detect illegal dumps in one hydrographic subbasin in Oaxaca, Mexico, through a supervised land cover classification using a Random Forest classifier. Two hundred and fifty-six control polygons were used to train the classifier. The classification criteria were the twelve bands of the Sentinel 2A satellite images with a spatial resolution of 10x10 meters, the spectral indices NDVI, MNDWI, SAVI, NDBI, BSI, and the surface slope. Google Earth Engine platform was used to process satellite images. There were 288,100 hectares classified in this way: 65.4% classified as vegetation, 31.5% like bare soil, 2.7% was urban soil and the rest was classified as water or garbage. A confusion matrix calculated the accuracy of the model in 0.9517. The model was not able to accurately distinguish between urban soil, bare soil and garbage due to the similarity of their spectral fingerprints. NDVI and SAVI were the most important spectral indices for detecting litter, and those might contribute to building a spectral fingerprint of litter in the future. Poorly classified areas were discarded through photointerpretation work and post-processing. Finally, thirty-two probable illegal dumps were identified, twelve of which were confirmed on the territory.
Waste management poses a pressing global challenge, necessitating innovative solutions for resource optimization and sustainability. Traditional practices often prove insufficient in addressing the escalating volume of waste and its environmental impact. However, the advent of Artificial Intelligence (AI) technologies offers promising avenues for tackling the complexities of waste management systems. This review provides a comprehensive examination of AI’s role in waste management, encompassing collection, sorting, recycling, and monitoring. It delineates the potential benefits and challenges associated with each application while emphasizing the imperative for improved data quality, privacy measures, cost-effectiveness, and ethical considerations. Furthermore, future prospects for AI integration with the Internet of Things (IoT), advancements in machine learning, and the importance of collaborative frameworks and policy initiatives were discussed. In conclusion, while AI holds significant promise for enhancing waste management practices, addressing challenges such as data quality, privacy concerns, and cost implications is paramount. Through concerted efforts and ongoing research endeavors, the transformative potential of AI can be fully harnessed to drive sustainable and efficient waste management practices.
The study explores the intricacies of Municipal Solid Waste (MSW) collection in the urban context where its high per capita waste generation and susceptibility to the adverse impacts of climate change, particularly in developing countries. This research focuses on a specialized vehicle routing model to optimize the solid waste transportation system within the city. To enhance the model's efficiency, a novel combined method is proposed, integrating the Pelican Optimization Algorithm (POA). Experimental evaluations, conducted using real data, unequivocally demonstrate that the proposed combined method outperforms alternative approaches, including the current manual MSW collection protocol in the city. This research makes a significant contribution to the waste management and urban sustainability field, with the ultimate goal of mitigating the social, economic, and environmental consequences associated with urban waste collection.
The recent advancements made in the realms of Artificial Intelligence (AI) and Artificial Intelligence of Things (AIoT) have unveiled transformative prospects and opportunities to enhance and optimize the environmental performance and efficiency of smart cities. These strides have, in turn, impacted smart eco-cities, catalyzing ongoing improvements and driving solutions to address complex environmental challenges. This aligns with the visionary concept of smarter eco-cities, an emerging paradigm of urbanism characterized by the seamless integration of advanced technologies and environmental strategies. However, there remains a significant gap in thoroughly understanding this new paradigm and the intricate spectrum of its multifaceted underlying dimensions. To bridge this gap, this study provides a comprehensive systematic review of the burgeoning landscape of smarter eco-cities and their leading-edge AI and AIoT solutions for environmental sustainability. To ensure thoroughness, the study employs a unified evidence synthesis framework integrating aggregative, configurative, and narrative synthesis approaches. At the core of this study lie these subsequent research inquiries: What are the foundational underpinnings of emerging smarter eco-cities, and how do they intricately interrelate, particularly urbanism paradigms, environmental solutions, and data-driven technologies? What are the key drivers and enablers propelling the materialization of smarter eco-cities? What are the primary AI and AIoT solutions that can be harnessed in the development of smarter eco-cities? In what ways do AI and AIoT technologies contribute to fostering environmental sustainability practices, and what potential benefits and opportunities do they offer for smarter eco-cities? What challenges and barriers arise in the implementation of AI and AIoT solutions for the development of smarter eco-cities? The findings significantly deepen and broaden our understanding of both the significant potential of AI and AIoT technologies to enhance sustainable urban development practices, as well as the formidable nature of the challenges they pose. Beyond theoretical enrichment, these findings offer invaluable insights and new perspectives poised to empower policymakers, practitioners, and researchers to advance the integration of eco-urbanism and AI- and AIoT-driven urbanism. Through an insightful exploration of the contemporary urban landscape and the identification of successfully applied AI and AIoT solutions, stakeholders gain the necessary groundwork for making well-informed decisions, implementing effective strategies, and designing policies that prioritize environmental well-being.
This review article provides a comprehensive analysis of the optimization techniques used in a wide range of engineering applications. The comparison of various approaches such as Response surface methodology (RSM), Genetic algorithm (GA) and Artificial neural network (ANN) towards optimization problems is widely elaborated. The factors that affect the optimization using various techniques are addressed along with the safety precautions to be followed in a sequential manner to achieve a better optimization model. Furthermore, the coupling of two distinct algorithms (RSM-GA, ANN-GA) are explained and this hybrid approach provides a better localizing of the optimal point with a higher accuracy.
TDS is modeled for an aquifer near an unlined landfill in Canada. Canadian Drinking Water Guidelines and other indices are used to evaluate TDS concentrations in 27 monitoring wells surrounding the landfill. This study aims to predict TDS concentrations using three different modeling approaches: dual-step multiple linear regression (MLR), hybrid principal component regression (PCR), and backpropagation neural networks (BPNN). An analysis of the bias and precision of each models follows, using performance evaluation metrics and statistical indices. TDS is one of the most important parameters in assessing suitability of water for irrigation, and for overall groundwater quality assessment. Good agreement was observed between the MLR1 model and field data, although multicollinearity issues exist. Percentage errors of hybrid PCR were comparable to the dual-step MLR method. Percentage error for hybrid PCR was found to be inversely proportional to TDS concentrations, which was not observed for dual-step MLR. Larger errors were obtained from the BPNN models, and higher percentage errors were observed in monitoring wells with lower TDS concentrations. All models in this study adequately describe the data in testing stage (R² > 0.86). Generally, the dual-step MLR and hybrid PCR models fared better (R²avg = 0.981 and 0.974, respectively), while BPNN models performed worse (R²avg = 0.904). For this dataset, both regression and machine learning models are more suited to predict mid-range data compared to extreme values. Advanced regression methods (hybrid PCR and dual-step MLR) are more advantageous compared to BPNN.
One of the major challenges in big cities is planning and implementation of an optimized, integrated solid waste management system. This optimization is crucial if environmental problems are to be prevented and the expenses to be reduced. A solid waste management system consists of many stages including collection, transfer and disposal. In this research, an integrated model was proposed and used to optimize two functional elements of municipal solid waste management (storage and collection systems) in the Ahmadabad neighbourhood located in the City of Mashhad – Iran. The integrated model was performed by modelling and solving the location allocation problem and capacitated vehicle routing problem (CVRP) through Geographic Information Systems (GIS). The results showed that the current collection system is not efficient owing to its incompatibility with the existing urban structure and population distribution. Application of the proposed model could significantly improve the storage and collection system. Based on the results of minimizing facilities analyses, scenarios with 100, 150 and 180 m walking distance were considered to find optimal bin locations for Alamdasht, C-metri and Koohsangi. The total number of daily collection tours was reduced to seven as compared to the eight tours carried out in the current system (12.50% reduction). In addition, the total number of required crews was minimized and reduced by 41.70% (24 crews in the current collection system vs 14 in the system provided by the model). The total collection vehicle routing was also optimized such that the total travelled distances during night and day working shifts was cut back by 53%.
Waste collection and transport can generate up to 70% of the total costs of the system. Separated collection of recyclables implies additional costs for which the sale of recycled waste often does not compensate, but there is increased pressure to reach the long-term recycling objectives set by law. The proper estimation and monitoring of waste collection costs are essential to define the most cost-effective waste collection system. The aim of this study is to propose and implement a management tool to determine waste collection costs for different waste collection schemes. Based on input data, such as waste quantity and composition, the number of waste bins, the location of collection points, the type of collection vehicle, crew, collection route, etc., the developed tool can calculate the time and costs of waste collection (per vehicle, collection point or tonne of collected waste). This tool uses Excel spreadsheets and it was tested on a district in the central area of the city of Kragujevac to calculate the costs of waste collection for two scenarios: Collecting all waste as mixed waste, and collecting separately recyclables and residual waste. The developed tool can be useful for municipal solid waste management companies, since it allows benchmarking and variance analysis.
The collection of source separated kerbside municipal FW (SSFW) is being incentivised in Australia, however such a collection is likely to increase the fuel and time a collection truck fleet requires. Therefore, waste managers need to determine whether the incentives outweigh the cost. With literature scarcely describing the magnitude of increase, and local parameters playing a crucial role in accurately modelling kerbside collection; this paper develops a new general mathematical model that predicts the energy and time requirements of a collection regime whilst incorporating the unique variables of different jurisdictions. The model, Municipal solid waste collect (MSW-Collect), is validated and shown to be more accurate at predicting fuel consumption and trucks required than other common collection models. When predicting changes incurred for five different SSFW collection scenarios, results show that SSFW scenarios require an increase in fuel ranging from 1.38 – 57.59%. There is also a need for additional trucks across most SSFW scenarios tested. All SSFW scenarios are ranked and analysed in regards to fuel consumption; sensitivity analysis is conducted to test key assumptions.
Collection of municipal solid waste is one of the most important elements of municipal waste management and requires maximum fund allocated for waste management. The cost of collection and transportation can be reduced in comparison with the present scenario if the solid waste collection bins are located at suitable places so that the collection routes become minimum. This study presents a suitable solid waste collection bin allocation method at appropriate places with uniform distance and easily accessible location so that the collection vehicle routes become minimum for the city Dhanbad, India. The network analyst tool set available in ArcGIS was used to find the optimised route for solid waste collection considering all the required parameters for solid waste collection efficiently. These parameters include the positions of solid waste collection bins, the road network, the population density, waste collection schedules, truck capacities and their characteristics. The present study also demonstrates the significant cost reductions that can be obtained compared with the current practices in the study area. The vehicle routing problem solver tool of ArcGIS was used to identify the cost-effective scenario for waste collection, to estimate its running costs and to simulate its application considering both travel time and travel distance simultaneously.
This work proposes an optimisation of municipal solid waste collection in terms of collection cost and polluting emissions (carbon oxides, carbon dioxides, nitrogen oxides and particulate matter). This method is based on a simultaneous optimisation of the vehicles routing (distance and time travelled) and the routing system for household wastes collection based on the existing network of containers, the capacity of vehicles and the quantities generated in every collecting point. The process of vehicle routing optimisation involves a geographical information system. This optimisation has enabled a reduction of travelled distances, collection time, fuel consumption and polluting emissions. Pertinent parameters affecting the fuel consumption have been utilised, such as the state of the road, the vehicles speed in the different paths, the vehicles load and collection frequencies. Several scenarios have been proposed. The results show the importance of the construction of a waste transfer station that can reduce the cost of household waste collection and emissions of waste transfer pollutants. Among the proposed five scenarios, we have noticed that the fourth scenario (by constructing a waste transfer centre) was the most performing. So, the routes of optimised travelled distance of the new circuits have been reduced by 71.81%. The fuel consumption has been reduced by 72.05% and the total cost of the collection has been reduced by 46.8%. For the polluting emissions, the reduction has been by 60.2% for carbon oxides, by 67.9% for carbon dioxides, by 74.2% for nitrogen oxides and by 65% for particulate matter.
Predicting the mass of solid waste generation plays an important role in integrated solid waste management plans. In this study, the performance of two predictive models, Artificial Neural Network (ANN) and Multiple Linear Regression (MLR) was verified to predict mean Seasonal Municipal Solid Waste Generation (SMSWG) rate. The accuracy of the proposed models is illustrated through a case study of 20 cities located in Fars Province, Iran. Four performance measures, MAE, MAPE, RMSE and R were used to evaluate the performance of these models. The MLR, as a conventional model, showed poor prediction performance. On the other hand, the results indicated that the ANN model, as a non-linear model, has a higher predictive accuracy when it comes to prediction of the mean SMSWG rate. As a result, in order to develop a more cost-effective strategy for waste management in the future, the ANN model could be used to predict the mean SMSWG rate.
Unlabelled:
The objectives of this study were to quantify real-world activity, fuel use, and emissions for heavy duty diesel roll-off refuse trucks; evaluate the contribution of duty cycles and emissions controls to variability in cycle average fuel use and emission rates; quantify the effect of vehicle weight on fuel use and emission rates; and compare empirical cycle average emission rates with the U.S. Environmental Protection Agency's MOVES emission factor model predictions. Measurements were made at 1 Hz on six trucks of model years 2005 to 2012, using onboard systems. The trucks traveled 870 miles, had an average speed of 16 mph, and collected 165 tons of trash. The average fuel economy was 4.4 mpg, which is approximately twice previously reported values for residential trash collection trucks. On average, 50% of time is spent idling and about 58% of emissions occur in urban areas. Newer trucks with selective catalytic reduction and diesel particulate filter had NOx and PM cycle average emission rates that were 80% lower and 95% lower, respectively, compared to older trucks without. On average, the combined can and trash weight was about 55% of chassis weight. The marginal effect of vehicle weight on fuel use and emissions is highest at low loads and decreases as load increases. Among 36 cycle average rates (6 trucks×6 cycles), MOVES-predicted values and estimates based on real-world data have similar relative trends. MOVES-predicted CO2 emissions are similar to those of the real world, while NOx and PM emissions are, on average, 43% lower and 300% higher, respectively. The real-world data presented here can be used to estimate benefits of replacing old trucks with new trucks. Further, the data can be used to improve emission inventories and model predictions.
Implications:
In-use measurements of the real-world activity, fuel use, and emissions of heavy-duty diesel roll-off refuse trucks can be used to improve the accuracy of predictive models, such as MOVES, and emissions inventories. Further, the activity data from this study can be used to generate more representative duty cycles for more accurate chassis dynamometer testing. Comparisons of old and new model year diesel trucks are useful in analyzing the effect of fleet turnover. The analysis of effect of haul weight on fuel use can be used by fleet managers to optimize operations to reduce fuel cost.
Municipal Solid Waste Management (MSWM) is one of the major environmental challenges in developing countries. Many efforts to reduce and recover the wastes have been made, but still land disposal of solid wastes is the most popular one. Finding an environmentally sound landfill site is a challenging task. This paper addresses a mini review on various aspects of MSWM (suitable landfill site selection, route optimization and public acceptance) using the Geographical Information System (GIS) coupled with other tools. The salient features of each of the integrated tools with GIS are discussed in this paper. It is also addressed how GIS can help in optimizing routes for collection of solid wastes from transfer stations to disposal sites to reduce the overall cost of solid waste management. A detailed approach on performing a public acceptance study of a proposed landfill site is presented in this study. The study will help municipal authorities to identify the most effective method of MSWM.
Over the years, the management of municipal solid waste (MSW) has been improved to some extent through installation of various schemes, development of new treatment technologies and implementation of economic instruments. Despite such progress, solid waste problems still impose an increasing pressure on cities and remain one of the major challenges in urban environmental management. Although approximating of waste generation in its management is important, the prediction of its production is a difficult job due to the effect of various factors on it. Artificial intelligence is an exciting and relatively new application of computers. It provides new opportunities for harnessing the scarce and often scattered pieces of valuable knowledge and experience in solid waste management which at present is in the possession of the privileged few. While conventional algorithmic programming replaced much of the sophisticated and repetitive analytical work of the solid waste practitioner, artificial intelligence is poised to take over the no-less important tasks of the ill-structured and lessdeterministic parts of the planning, design and management processes. In this research with application of feed forward artificial neural network, we proposed an appropriate model to predict weight of waste generation in Saqqez city of Iran. For this purpose, we used time series of generated waste of Saqqez which have been arranged weekly, from 2004 to 2007. After performing of the mentioned model, determination 2 coefficient (R) and mean absolute relative error (MARE) in neural network for test have been achieved to be equal to 0.648 and 2.17% respectively.
The optimization of municipal waste collection can reduce management costs and negative impacts on the environment. This article analyzes municipal waste collection in Churriana de la Vega (Granada, Spain), and describes a way to improve waste collection service, based on the information provided by Geographic Information Systems. The results of our study showed that the town had an excessive number of containers for organic matter and rest-waste fraction. This made waste collection less efficient and raised costs related to the purchase of containers, collection time, personnel costs, collection route length, and vehicle maintenance. In the case of recyclable fraction collection, our results showed that waste collection could be improved by increasing the number of containers and optimizing their location. The solutions proposed could improve the percentage of selective waste collection and raise environmental
awareness although this action should be accompanied by public awareness campaigns.
Successful planning and operation of a solid waste management system depends on municipal solid waste (MSW) generation process knowledge and on accurate predictions of solid waste quantities produced. Conventional analysis and prediction models are based on demographic and socioeconomic factors. However, this kind of analysis is related to mean generation data. Dynamic MSW generation analysis can be done using time series data of solid waste generated quantities. In this paper some tools for time series analysis and forecasting are proposed to study MSW generation. A prediction technique based on non-linear dynamics is proposed, comparing its performance with a seasonal AutoRegressive and Moving Average (sARIMA) methodology, dealing with short and medium term forecasting. Finally, a practical implementation consisting of the study of MSW time series of three cities in Spain and Greece is presented.
Use of diesel in collection trucks is presumably the most important environmental burden from waste collection because of the emission of exhaust gases from the combustion process. The environmental impact depends not only on the amount of diesel used, but also the on the cleanness of the exhaust gas that is regulated by emission standards. We measured the diesel consumption for 14 different collection schemes in two municipalities in Denmark, yielding a total of 254 measurements. Collection was defined as driving and loading of waste from the first to the final stop on the collection route. All other distances covered were defined as transport of waste, which was modelled in generic transport simulation models. The diesel consumption per tonne of waste in the specified collection schemes turned out to be related to the type of housing and to the amount of waste collected per stop. The observations showed a considerable variation between different collection schemes, ranging from 1.4- 10.1 L diesel tonne(- 1) of waste. Assessment of the potential environmental impact by a life-cycle-assessment method showed a substantial decrease over the last decade because of implementation of European emissions standard for diesel trucks. The paper also discusses the importance of energy used for collection and transport in relation to the potential energy savings from waste treatment. In many cases, the net savings exceed significantly the use of diesel.
Efficient and effective solid waste management requires sufficient ability to predict the operational capacity of a system correctly. Waste prediction models have been widely studied and these models are always being challenged to perform more accurately. Unlike waste prediction models for mixed wastes, variables for yard waste are time sensitive and the effects of lag must be explicitly considered. This study is the first to specifically look at lag times relating to variables that attempt to predict municipal yard waste generation using machine learning approaches. Weekly averaged climatic and socio-economic variables are screened through correlation analysis and the significant variables are then used to develop yard waste models. These models then utilize artificial neural networks (ANN) where the variables are time lagged for a different number of weeks. This helps to realize a reduction in the error of the predicted weekly yard waste generation. Optimal lag times for each model varied from 1 to 11 weeks. The best model used both the ambient air temperature and population variables, in an ANN model with 3 layers, 11 neurons in the hidden layer, and an optimal lag time of 1 week. A mean absolute percentage error of 18.72% was obtained during the testing stage. One model saw a 55.4% decrease in the mean squared error at training, showing the value of lag time on the accuracy of weekly yard waste prediction models.
Geographic information systems are a valuable tool for waste collection and optimization, but they have been underutilized in helping to understand the complex interrelationships that exist within a dual phase solid waste collection system. A GIS-based dual phase model integrating the handcart pre-collection phase and truck collection phase for a study area located in Hai Phong, Vietnam was proposed, and a resulting total system cost was estimated. Temporary collection points were first identified using both the maximize coverage and minimize facility location-allocation tools from a list of candidate temporary collection points and constraints. Two vehicle routing problems were then separately modeled for handcart and truck routes. A total of 30 scenarios were considered in order to investigate the interrelationships between the model parameters, with respect to the total operation costs and maintenance system costs. The scenario with 11 temporary collection points and a maximum handcart collection distance of 500 m gave the lowest overall cost in the study area. The results suggest a single temporary collection point in the study is able to serve about 2,590 people in an area of 0.11 km2. Compared to the status quo condition, a 13.76% reduction in truck travel distances is attainable using the proposed model. It is found that the number and distribution of temporary collection points greatly affected the cost effectiveness in both pre-collection and collection phases.
In 2014, Canadians produced 961 kg per capita of non-hazardous waste, and spent about CAD$85 on waste management operating expenditure. Using aggregate data from Statistics Canada, multiple linear regression models were developed to examine diversion rates with respect to percentage of expenditure on various parameters related to waste management in Nova Scotia, Québec, Ontario, and nationally (in Canada). Budget allocation varies significantly in Nova Scotia with respect to time. On average, only 31% of the Nova Scotia’s budget was spent on collection and transportation, compared to the national average of 46%. Tipping fees were only significant in the national regression model, likely because some prairie provinces are using tipping fees to increase waste diversion. The Québec model was the least statistically significant. Negative regression coefficients were identified for the operation of recycling facilities in the Nova Scotia and Ontario models, however, they were less statistically significant, suggesting a more complex relationship. A lagged relationship between increases in budget allocation for operation of organics and recycling facilities and diversion rates was found in Québec, with a lag period of about 5–8 years. Overall, the Nova Scotia model had a much higher modelling adequacy, interesting considering its highest diversion rate in Canada.
The main objective of this study was to develop models for accurate prediction of municipal solid waste (MSW) generation and diversion based on demographic and socio-economic variables, with planned application of generating Canada-wide MSW inventories. Models were generated by mapping residential MSW quantities with socio-economic and demographic parameters of 220 municipalities in the province of Ontario, Canada. Two machine learning algorithms, namely decision trees and neural networks, were applied to build the models. Socio-economic variables were derived from Canadian Census data at regional and municipal levels. A data pre-processing and integration framework was developed in Matlab® computing software to generate datasets with sufficient data quantity and quality for modeling. Results showed that machine learning algorithms can be successfully used to generate waste models with good prediction performance. Neural network models had the best performance, describing 72% of variation in the data. The approach proposed in this study demonstrates the feasibility of creating tools that helps in regional waste planning by means of sourcing, pre-processing, integrating and modeling of publically available data from various sources.
One of the most widely used standard procedures for model evaluation in classification and regression is K-fold cross-validation (CV). However, when it comes to time series forecasting, because of the inherent serial correlation and potential non-stationarity of the data, its application is not straightforward and often replaced by practitioners in favour of an out-of-sample (OOS) evaluation. It is shown that for purely autoregressive models, the use of standard K-fold CV is possible provided the models considered have uncorrelated errors. Such a setup occurs, for example, when the models nest a more appropriate model. This is very common when Machine Learning methods are used for prediction, and where CV can control for overfitting the data. Theoretical insights supporting these arguments are presented, along with a simulation study and a real-world example. It is shown empirically that K-fold CV performs favourably compared to both OOS evaluation and other time-series-specific techniques such as non-dependent cross-validation.
Non-hazardous waste disposal and diversion trends in Ontario from 1996 to 2010 were identified using parametric and non-parametric statistical methods, and the temporal variability of its waste diversion practices were examined. Ontario’s diversion was sensitive to waste diversion policy and residential diversion programs. Total waste diversion increased by 85% in 14 years. Results suggested that waste minimization may be more effective than recycling on Ontario diversion rates. Programs targeting non-residential sectors are recommended, specifically for smaller businesses with limited waste management budgets. Linear regression and Mann-Kendall tests detected significant increasing trends for residential waste diversion. In contrast, non-residential diversion had a decreasing trend using linear regression. A significant upward trend (S = +10) was found for Ontario’s total waste diversion using Mann-Kendall tests. Highly significant upward trends were observed for plastic and organic recycling. Mann-Kendall tests were found more appropriate for waste trend analysis in the present study.
Abstract The amount of municipal solid waste (MSW) has been increasing steadily over the last decade by reason of population rising and waste generation rate. In most of the urban areas, disposal sites are usually located outside of the urban areas due to the scarcity of land. There is no fixed route map for transportation. The current waste collection and transportation are already overloaded arising from the lack of facilities and insufficient resources. In this paper, a model for optimizing municipal solid waste collection will be proposed. Firstly, the optimized plan is developed in a static context, and then it is integrated into a dynamic context using multi-agent based modelling and simulation. A case study related to Hagiang City, Vietnam, is presented to show the efficiency of the proposed model. From the optimized results, it has been found that the cost of the MSW collection is reduced by 11.3%.
Solid waste collection contributes to the cost, emissions, and fossil fuel required to manage municipal solid waste. Mechanistic models to estimate these parameters are necessary to perform integrated assessments of solid waste management alternatives using a life-cycle approach; however, models are only as good as their parameterization. This study presents operational waste collection data that can be used in life-cycle models for areas with similar collection systems, and provides illustrative results from a collection process model using operational data. Fuel use and times associated with various aspects of waste collection were obtained for vehicles collecting mixed residential (residual) waste, recyclables, and yard waste from single-family residences in selected municipalities. The total average fuel economy for similarly-sized diesel collection vehicles was 0.6-1.4 km/L (1.4–3.3 mpg (miles per gallon)) for residual waste and 0.8–1 km/L (1.9–2.4 mpg) for recyclables. For residual waste and recyclables collection stops, the average time to collect at each residence using automated collection was 11–12 s and 13–17 s, respectively. The average time between stops was 11–12 s and 10–13 for residuals and recyclables, respectively. A single yard waste route was observed, and all collection times were longer than those measured for either recycling or residual waste. Unload or tip times were obtained or measured at a landfill, transfer station, and material recovery facility (MRF). Average time to unload was 7–9 min at a MRF, 14–22 min at a landfill, and 11 min at a transfer station. Commercial and multi-family collection vehicles tend to have longer stops and spend more time between stops than single-family collection, and a larger portion of fuel is used while driving relative to single-family collection. Roll-off vehicles, which collect more waste per stop, spend longer at each stop and drive longer distances between stops than front-loader vehicles. Diesel roll-offs averaged 2.4 km/L (5.7 mpg) and front-loaders averaged 1.4 km/L (3.3 mpg).
Municipal solid waste (MSW) management is a major concern to local governments to protect human health, the environment and to preserve natural resources. The design and operation of an effective MSW management system requires accurate estimation of future waste generation quantities. The main objective of this study was to develop a model for accurate forecasting of MSW generation that helps waste related organizations to better design and operate effective MSW management systems. Four intelligent system algorithms including support vector machine (SVM), adaptive neuro-fuzzy inference system (ANFIS), artificial neural network (ANN) and k-nearest neighbours (kNN) were tested for their ability to predict monthly waste generation in the Logan City Council region in Queensland, Australia. Results showed artificial intelligence models have good prediction performance and could be successfully applied to establish municipal solid waste forecasting models. Using machine learning algorithms can reliably predict monthly MSW generation by training with waste generation time series. In addition, results suggest that ANFIS system produced the most accurate forecasts of the peaks while kNN was successful in predicting the monthly averages of waste quantities. Based on the results, the total annual MSW generated in Logan City will reach 9.4 × 107 kg by 2020 while the peak monthly waste will reach 9.37 × 106 kg.
Inefficient collection and scheduling procedures negatively affect residential curbside collection (RCC) efficiency, greenhouse gas (GHG) emissions, and cost. As Florida aims to achieve a 75% recycling goal by 2020, municipalities have switched to single-stream recycling to improve recycling efficiency. Waste diversion and increased collection cost have forced some municipalities to reduce garbage collection frequency. The goal of this study was to explore the trade-offs between environmental and economic factors of RCC systems in Florida by evaluating the RCC system design of 25 different Central Florida communities. These communities were grouped into four sets based on their RCC garbage, yard waste, and recyclables collection design, i.e., frequency of collection and use of dual-stream (DS) or single-stream (SS) recyclables collection system. For the 25 communities studied, it was observed that RCC programs that used SS recyclables collection system recycled approximately 15–35%, by weight of the waste steam, compared to 5–20% for programs that used DS. The GHG emissions associated with collection programs were estimated to be between 36 and 51 kg CO2eq per metric ton of total household waste (garbage and recyclables), depending on the garbage collection frequency, recyclables collection system (DS or SS), and recyclables compaction. When recyclables offsets were considered, the GHG emissions associated with programs using SS were estimated between −760 and −560, compared to between −270 and −210 kg CO2eq per metric ton of total waste for DS programs. These data suggest that RCC system design can significantly impact recyclables generation rate and efficiency, and consequently determine environmental and economic impacts of collection systems. Recycling participation rate was found to have a significant impact on the environmental and financial performance of RCC programs. Collection emissions were insignificant compared to the benefits of recycling. SS collection of recyclables provided cost benefits compared to DS, mainly due to faster collection time.
Worldwide, about US$410 billion is spent every year to manage four billion tonnes of municipal solid wastes (MSW). Transport cost alone constitutes more than 50% of the total expenditure on solid waste management (SWM) in major cities of the developed world and the collection and transport cost is about 85% in the developing world. There is a need to improve the ability of the city administrators to manage the municipal solid wastes with least cost. Since 2000, new technologies such as geographical information system (GIS) and related optimization software have been used to optimize the haul route distances. The city limits of Chennai were extended from 175 to 426 km(2) in 2011, leading to sub-optimum levels in solid waste transportation of 4840 tonnes per day. After developing a spatial database for the whole of Chennai with 200 wards, the route optimization procedures have been run for the transport of solid wastes from 13 wards (generating nodes) to one transfer station (intermediary before landfill), using ArcGIS. The optimization process reduced the distances travelled by 9.93%. The annual total cost incurred for this segment alone is Indian Rupees (INR) 226.1 million. Savings in terms of time taken for both the current and shortest paths have also been computed, considering traffic conditions. The overall savings are thus very meaningful and call for optimization of the haul routes for the entire Chennai.
The prediction of municipal solid waste generation ( MSWG ) plays an important role in a solid waste management system. However, achieving the anticipated prediction accuracy with regard to the nonhomogeneous nature of waste and effect of various and out of control factors on MSWG is quite challenging. In this article, support vector machine ( SVM ), one of the artificial intelligence techniques, and hybrid of wavelet transform (WT) and support vector machine ( WT ‐ SVM ) are used to predict weekly time series of MSWG in Tehran and Mashhad cites during the period of January 2006–December 2011. To improve the performance of SVM model, considering the influence of noise and the disadvantages of traditional noise eliminating technologies, the wavelet denoising method is applied to reduce or eliminate the noise in MSWG time series.
Since Data‐driven models such as SVM involve potential of uncertainty that is difficult to quantify, uncertainty determination is one of important gaps observed in SVM results analysis. Therefore, M onte C arlo method was used to analyze uncertainty of the model results.
Results showed both models could precisely predict MSWG in Tehran and Mashhad cites. However, the preprocessing of input variables by WT led to develop a more accurate model for prediction of weekly MSWG in both cities. The uncertainty analysis also verified that the WT ‐ SVM model had more robustness than SVM and had a lower sensitivity to change of input variables. © 2013 American Institute of Chemical Engineers Environ Prog, 33: 220–228, 2014
This research is an in-depth environmental analysis of potential alternative fuel technologies for waste collection vehicles. Life-cycle emissions, cost, fuel and energy consumption were evaluated for a wide range of fossil and bio-fuel technologies. Emission factors were calculated for a typical waste collection driving cycle as well as constant speed. In brief, natural gas waste collection vehicles (compressed and liquid) fueled with North-American natural gas had 6-10% higher well-to-wheel (WTW) greenhouse gas (GHG) emissions relative to diesel-fueled vehicles; however the pump-to-wheel (PTW) GHG emissions of natural gas waste collection vehicles averaged 6% less than diesel-fueled vehicles. Landfill gas had about 80% lower WTW GHG emissions relative to diesel. Biodiesel waste collection vehicles had between 12% and 75% lower WTW GHG emissions relative to diesel depending on the fuel source and the blend. In 2011, natural gas waste collection vehicles had the lowest fuel cost per collection vehicle kilometer travel. Finally, the actual driving cycle of waste collection vehicles consists of repetitive stops and starts during waste collection; this generates more emissions than constant speed driving.
This work proposes an innovative methodology for the reduction of the operation costs and pollutant emissions involved in the waste collection and transportation. Its innovative feature lies in combining vehicle route optimization with that of waste collection scheduling. The latter uses historical data of the filling rate of each container individually to establish the daily circuits of collection points to be visited, which is more realistic than the usual assumption of a single average fill-up rate common to all the system containers. Moreover, this allows for the ahead planning of the collection scheduling, which permits a better system management. The optimization process of the routes to be travelled makes recourse to Geographical Information Systems (GISs) and uses interchangeably two optimization criteria: total spent time and travelled distance. Furthermore, rather than using average values, the relevant parameters influencing fuel consumption and pollutant emissions, such as vehicle speed in different roads and loading weight, are taken into consideration. The established methodology is applied to the glass-waste collection and transportation system of Amarsul S.A., in Barreiro. Moreover, to isolate the influence of the dynamic load on fuel consumption and pollutant emissions a sensitivity analysis of the vehicle loading process is performed. For that, two hypothetical scenarios are tested: one with the collected volume increasing exponentially along the collection path; the other assuming that the collected volume decreases exponentially along the same path. The results evidence unquestionable beneficial impacts of the optimization on both the operation costs (labor and vehicles maintenance and fuel consumption) and pollutant emissions, regardless the optimization criterion used. Nonetheless, such impact is particularly relevant when optimizing for time yielding substantial improvements to the existing system: potential reductions of 62% for the total spent time, 43% for the fuel consumption and 40% for the emitted pollutants. This results in total cost savings of 57%, labor being the greatest contributor, representing over €11,000 per year for the two vehicles collecting glass-waste. Moreover, it is shown herein that the dynamic loading process of the collection vehicle impacts on both the fuel consumption and on pollutant emissions.
In Bosnia and Herzegovina only 50% of the municipalities have a well-organized service for (mixed) waste collection and disposal. Illegal dumping is very common, in particular in rural areas, which are not regularly served by any service of collection. This situation leads to serious risks for public health and has dangerous environmental impacts. In Zavidovići the municipality is trying to meet high standards in the delivery of services of waste collection, but is constrained by scarce financial and technical resources. Different scenarios for the implementation of a system of separate collection in Zavidovići were elaborated in order to provide a useful tool for decision making by comparing costs and environmental & economic benefits of each scenario. Six scenarios were considered, based on different recovery rates for plastic, paper & cardboard, and metals. Benefits resulting from the implementation of each of the proposed scenarios are compared in terms of savings of landfill volume and costs. The study concludes that the adoption of a system of separate collection could generate positive impacts on all the stakeholders involved in the solid waste management sector in Zavidovići and could contribute to the compliance of European standards in many Central and Eastern European countries as established by a number of national environmental protection strategies.
This article takes a detailed look at an uncertainty factor in waste management LCA that has not been widely discussed previously, namely the uncertainty in waste composition. Waste composition is influenced by many factors; it can vary from year to year, seasonally, and with location, for example. The data publicly available at a municipal level can be highly aggregated and sometimes incomplete, and performing composition analysis is technically challenging. Uncertainty is therefore always present in waste composition. This article performs uncertainty analysis on a systematically modified waste composition using a constructed waste management system. In addition the environmental impacts of several waste management strategies are compared when applied to five different cities. We thus discuss the effect of uncertainty in both accounting LCA and comparative LCA. We found the waste composition to be important for the total environmental impact of the system, especially for the global warming, nutrient enrichment and human toxicity via water impact categories.
On-road vehicle tests of nine heavy-duty diesel trucks were conducted using SEMTECH-D, an emissions measuring instrument provided by Sensors, Inc. The total length of roads for the tests was 186 km. Data were obtained for 37,255 effective driving cycles, including 17,216 on arterial roads, 15,444 on residential roads, and 4595 on highways. The impacts of speed and acceleration on fuel consumption and emissions were analyzed. Results show that trucks spend an average of 16.5% of the time in idling mode, 25.5% in acceleration mode, 27.9% in deceleration mode, and only 30.0% at cruise speed. The average emission factors of CO, total hydrocarbons (THC), and NOx for the selected vehicles are (4.96±2.90), (1.88±1.03) and (6.54±1.90) g km−1, respectively. The vehicle emission rates vary significantly with factors like speed and acceleration. The test results reflect the actual traffic situation and the current emission status of diesel trucks in Shanghai. The measurements show that low-speed conditions with frequent acceleration and deceleration, particularly in congestion conditions, are the main factors that aggravate vehicle emissions and cause high emissions of CO and THC. Alleviating congestion would significantly improve vehicle fuel economy and reduce CO and THC emissions.
The collection of waste is a highly visible and important municipal service that involves large expenditures. Waste collection problems are, however, one of the most difficult operational problems to solve. This paper describes the optimization of vehicle routes and schedules for collecting municipal solid waste in Eastern Finland. The solutions are generated by a recently developed guided variable neighborhood thresholding metaheuristic that is adapted to solve real-life waste collection problems. Several implementation approaches to speed up the method and cut down the memory usage are discussed. A case study on the waste collection in two regions of Eastern Finland demonstrates that significant cost reductions can be obtained compared with the current practice.
The twentieth century saw a dramatic increase in the production of urban solid waste, reflecting unprecedented global levels of economic activity. Despite some efforts to reduce and recover the waste, disposal in landfills is still the most usual destination. However, landfill has become more difficult to implement because of its increasing cost, community opposition to landfill siting, and more restrictive environmental regulations regarding the siting and operation of landfills. Moreover, disposal in landfill is the waste destination method with the largest demand for land, while land is a resource whose availability has been decreasing in urban systems. Shortage of land for landfills is a problem frequently cited in the literature as a physical constraint. Nonetheless, the shortage of land for waste disposal has not been fully studied and, in particular, quantified. This paper presents a method to quantify the relationship between the demand and supply of suitable land for waste disposal over time using a geographic information system and modelling techniques. Based on projections of population growth, urban sprawl and waste generation the method can allow policy and decision-makers to measure the dimension of the problem of shortage of land into the future. The procedure can provide information to guide the design and schedule of programs to reduce and recover waste, and can potentially lead to a better use of the land resource. Porto Alegre City, Brazil was used as the case study to illustrate and analyse the approach. By testing different waste management scenarios, the results indicated that the demand for land for waste disposal overcomes the supply of suitable land for this use in the study area before the year 2050.
Forecasting of generation of municipal solid waste (MSW) in developing countries is often a challenging task due to the lack of data and selection of suitable forecasting method. This article aimed to select and evaluate several methods for MSW forecasting in a medium-scaled Eastern European city (Kaunas, Lithuania) with rapidly developing economics, with respect to affluence-related and seasonal impacts. The MSW generation was forecast with respect to the economic activity of the city (regression modelling) and using time series analysis. The modelling based on social-economic indicators (regression implemented in LCA-IWM model) showed particular sensitivity (deviation from actual data in the range from 2.2 to 20.6%) to external factors, such as the synergetic effects of affluence parameters or changes in MSW collection system. For the time series analysis, the combination of autoregressive integrated moving average (ARIMA) and seasonal exponential smoothing (SES) techniques were found to be the most accurate (mean absolute percentage error equalled to 6.5). Time series analysis method was very valuable for forecasting the weekly variation of waste generation data (r (2) > 0.87), but the forecast yearly increase should be verified against the data obtained by regression modelling. The methods and findings of this study may assist the experts, decision-makers and scientists performing forecasts of MSW generation, especially in developing countries.
Fuel consumption during seven different daily activities of a garbage co-collection truck and a normal packer truck was estimated from the trucks' global positioning system (GPS) data and fuel consumption records. The co-collection and the normal garbage packer consumed approximately 1.8 L and 1.26 L of diesel per km, respectively, while travelling within the collection areas. Using these fuel rates and the GPS data, the results show that both types of trucks consumed more than 60% of daily total fuel while actually collecting waste on the route. The average daily fuel consumption was 2-4 times higher on rural routes compared to urban areas. Fuel consumption varied significantly depending on the housing density along the collection route. In addition, approximately 5-6 times as much fuel was required to collect a kilogram of waste on a rural route compared to an urban route. Potential methods of reducing fuel consumption were examined. Consistent use of optimal collection routes could potentially save an average of 7.5 L of fuel per truck per day. Reducing the loading time per stop was also studied, but the results suggest that this method does not have significant potential to reduce fuel consumption.
Idle emissions data from 19 medium heavy-duty diesel and gasoline trucks are presented in this paper. Emissions from these trucks were characterized using full-flow exhaust dilution as part of the Coordinating Research Council (CRC) Project E-55/59. Idle emissions data were not available from dedicated measurements, but were extracted from the continuous emissions data on the low-speed transient mode of the medium heavy-duty truck (MHDTLO) cycle. The four gasoline trucks produced very low oxides of nitrogen (NOx) and negligible particulate matter (PM) during idle. However, carbon monoxide (CO) and hydrocarbons (HCs) from these four trucks were approximately 285 and 153 g/hr on average, respectively. The gasoline trucks consumed substantially more fuel at an hourly rate (0.84 gal/hr) than their diesel counterparts (0.44 gal/hr) during idling. The diesel trucks, on the other hand, emitted higher NOx (79 g/hr) and comparatively higher PM (4.1 g/hr), on average, than the gasoline trucks (3.8 g/hr of NOx and 0.9 g/hr of PM, on average). Idle NOx emissions from diesel trucks were high for post-1992 model year engines, but no trends were observed for fuel consumption. Idle emissions and fuel consumption from the medium heavy-duty diesel trucks (MHDDTs) were marginally lower than those from the heavy heavy-duty diesel trucks (HHDDTs), previously reported in the literature.
Heavy-duty diesel vehicle idling consumes fuel and reduces atmospheric quality, but its restriction cannot simply be proscribed, because cab heat or air-conditioning provides essential driver comfort. A comprehensive tailpipe emissions database to describe idling impacts is not yet available. This paper presents a substantial data set that incorporates results from the West Virginia University transient engine test cell, the E-55/59 Study and the Gasoline/Diesel PM Split Study. It covered 75 heavy-duty diesel engines and trucks, which were divided into two groups: vehicles with mechanical fuel injection (MFI) and vehicles with electronic fuel injection (EFI). Idle emissions of CO, hydrocarbon (HC), oxides of nitrogen (NOx), particulate matter (PM), and carbon dioxide (CO2) have been reported. Idle CO2 emissions allowed the projection of fuel consumption during idling. Test-to-test variations were observed for repeat idle tests on the same vehicle because of measurement variation, accessory loads, and ambient conditions. Vehicles fitted with EFI, on average, emitted approximately 20 g/hr of CO, 6 g/hr of HC, 86 g/hr of NOx, 1 g/hr of PM, and 4636 g/hr of CO2 during idle. MFI equipped vehicles emitted approximately 35 g/hr of CO, 23 g/hr of HC, 48 g/hr of NOx, 4 g/hr of PM, and 4484 g/hr of CO2, on average, during idle. Vehicles with EFI emitted less idle CO, HC, and PM, which could be attributed to the efficient combustion and superior fuel atomization in EFI systems. Idle NOx, however, increased with EFI, which corresponds with the advancing of timing to improve idle combustion. Fuel injection management did not have any effect on CO2 and, hence, fuel consumption. Use of air conditioning without increasing engine speed increased idle CO2, NOx, PM, HC, and fuel consumption by 25% on average. When the engine speed was elevated from 600 to 1100 revolutions per minute, CO2 and NOx emissions and fuel consumption increased by >150%, whereas PM and HC emissions increased by approximately 100% and 70%, respectively. Six Detroit Diesel Corp. (DDC) Series 60 engines in engine test cell were found to emit less CO, NOx, and PM emissions and consumed fuel at only 75% of the level found in the chassis dynamometer data. This is because fan and compressor loads were absent in the engine test cell.
There is little experience in Portugal with the separate collection of the biodegradable fraction of municipal solid waste (MSW). Therefore, it is relevant to evaluate how this process could economically affect the actual practices of MSW collection in small municipalities. This article simulates the costs of collection by means of a fixed container system and a transfer station, using values from a municipality with a population of 28,000 inhabitants. The main goal of this exercise is to compare the economic effects of three alternative scenarios: (i) the traditional, unsorted collection; (ii) the separate collection of whole biowaste; and (iii) the separate collection of biowaste generated in the major urban communities, while setting aside the other biowaste for home composting. The input data are from 2001, and include waste quantities, travel times, work crew composition, crew time shifts, vehicles, and containers. Calculations of the proposed mathematical method were carried out using the Microsoft Excel software. This study concludes that the global cost for separate collection of biowaste (alternative ii) need not necessarily be higher than the corresponding cost of the traditional, unsorted method of collection (alternative i). Furthermore, the global cost for collection with separated biowaste and home composting (alternative iii) could also be lower than the corresponding cost of the traditional, unsorted method of collection.
Waste Collection & Diversion Report (daily)
- Austin City Of