No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Assessing intra and interannual variability of water quality in the Sundarban mangrove dominated estuarine ecosystem using remote sensing and hybrid machine learning models
... Elevated concentrations of TDS and TSS near industrial zones and urbanized areas suggest considerable contributions from industrial effluents and urban runoff. This observation is consistent with previous research that has documented the adverse effects of industrial activities and urban development on water quality [10,46,47]. Rapid urbanization and industrial activities, including untreated sewage disposal, significantly deteriorate water quality, leading to increased turbidity [48]. ...
... Furthermore, the persistent higher turbidity levels observed near riverine and coastal regions reinforce [50] the impact of anthropogenic discharge, particularly through increased sedimentation and particulate matter load [51,52]. The salinity levels recorded in this study are comparable to those reported in mangrove ecosystems in the Mekong Delta (2-32 PPT) and the Ganges-Brahmaputra Estuary (5-28 PPT) [47,53]. However, turbidity and TSS levels in the Sundarbans show distinct seasonality and variability, with peak TSS values (up to 210 mg/L) exceeding those commonly reported in similar estuarine ecosystems, such as the Amazon Delta (50-150 mg/L) [54]. ...
... By integrating GEE and ML, the research processed extensive satellite imagery datasets, demonstrating the efficacy of these technologies in estimating water quality parameters such as TDS, TSS, turbidity, pH, SSS, and LST. This finding is consistent with prior studies that have successfully employed remote sensing and machine learning for environmental assessment [47,62,71]. ...
This study presents a semi-automated approach for assessing water quality in the Sundarbans, a critical and vulnerable ecosystem, using machine learning (ML) models integrated with field and remotely-sensed data. Key water quality parameters—Sea Surface Temperature (SST), Total Suspended Solids (TSS), Turbidity, Salinity, and pH—were predicted through ML algorithms and interpolated using the Empirical Bayesian Kriging (EBK) model in ArcGIS Pro. The predictive framework leverages Google Earth Engine (GEE) and AutoML, utilizing deep learning libraries to create dynamic, adaptive models that enhance prediction accuracy. Comparative analyses showed that ML-based models effectively captured spatial and temporal variations, aligning closely with field measurements. This integration provides a more efficient alternative to traditional methods, which are resource-intensive and less practical for large-scale, remote areas.
Our findings demonstrate that this semi-automated technique is a valuable tool for continuous water quality monitoring, particularly in ecologically sensitive areas with limited accessibility. The approach also offers significant applications for climate resilience and policy-making, as it enables timely identification of deteriorating water quality trends that may impact biodiversity and ecosystem health. However, the study acknowledges limitations, including the variability in data availability and the inherent uncertainties in ML predictions for dynamic water systems. Overall, this research contributes to the advancement of water quality monitoring techniques, supporting sustainable environmental management practices and the resilience of the Sundarbans against emerging climate challenges.
... Over the past decade, average peak temperatures have reached 35 °C. The summer season (or pre-monsoon season) is from about the middle of March to the middle of June, while the winter season (or post-monsoon season) is from mid-November to mid-February (Mondal et al., 2024a). The monsoon season -also called the southwest monsoon -usually begins in June and lasts until early October. ...
... ANN is a standard model that uses the brain's innate capacity for reading (Mondal et al., 2024a;Karmakar et al., 2024). It uses backward feedback to change the weights and impulses of each neuron in order to reduce the discrepancy between factual dimension and vaticination (Song et al., 2012). ...
... The different spectral variables that comprise the input subcaste are identified by a strong association between the Chl-a focus and the initial spectral bands, band mates, and spectral outgrowth. These four defunct layers provide a good mix between the complexity of Chl-a recoup and the speed with which software can calculate them (Mondal et al., 2024a;Karmakar et al., 2024). According to the input point dimension, the quantity of neurons equals the quantity of spectral input variables. ...
... More than 7 million people live in the coastal delta of Sundarbans and fishing, small-scale farming and tourism are their main sources of income. With the assistance of a massive amount of freshwater being discharged by the Ganges-Brahmaputra-Meghna river system into the region, the intertidal mangrove ecosystem is flourishing in this brackish aquatic environment (Mondal et al., 2023a). Rivers also bring in significant amounts of suspended sediment, nutrients, and other toxic contaminants and chemicals; some of them are trapped in the estuary by the intricate prop root systems of the mangroves as well as the complex circulation and mixing processes within the estuary. ...
... The study briefly overviews Sundarbans coastal habitat's nutrient makeup has evolved across time and space. The ML based Support Vector Machine (SVM) algorithm is used for assessing the spatio-temporal variations over a 20-year (2002-2021) duration (Mondal et al., 2023a). The Artificial Intelligence (AI) based models simplify complex datasets, make specific tasks easier to accomplish, and processes large datasets. ...
... It reduces artefacts and biases caused by residual glint, stray light, atmospheric correction errors, and white or spectrally-linear bias errors in Rrs. To achieve a seamless transition, the implemented algorithm adapt significantly and transformation between CI and OCx now happens at 0.15 CI 0.2 mg m − 3 (Mondal et al., 2023a). ...
This study documents a novel method for tracking spatio-temporal variability of productivity-related elements, including particulate organic carbon (POC), particular inorganic carbon (PIC), chlorophyll-a (Chl-a), dissolved nitrate, total phosphate, and dissolved phosphate, in the Sundarbans coastal aquatic system over a period of twenty years (2002–2021). Machine learning (ML) algorithms were employed to compute all the parameters from optical remote sensing data. Input data were obtained from the MODIS multispectral imageries bands satellite data sets and data extraction and analysis were performed using SVM regression models. Moving average study of POC and Chl-a concentration along the coastal zone revealed shallow deltaic coagulation, eutrophication, microbial decomposition, and lysis-caused variation and deterioration. However, high ambient temperatures and organic waste decomposition increase dissolved phosphate in inland mangrove creeks before the monsoon. Elevated nutrient levels lead to a reduction in Chl-a and particulate organic carbon is highly correlated with Chl-a to the extent of 0.79 Especially in summer time nutrient loading from agriculture and urban runoff cause harmful algal blooms that destroy aquatic life and degrade ecosystem functions. Even though collecting samples from the field on a seasonal basis for monitoring water quality and aquatic productivity is the ideal approach, it is time-consuming and also uneconomical, given the remoteness of the expansive mangrove forest. This study demonstrates efficacy of cost-effective methods like utilizing satellite data and adopting ML techniques for continuous monitoring of Sundarbans deltaic coast for its water quality and aquatic health.
... Groundwater level [124,125], streamflow [126], surface water [127,128], water storage [129], sediment concentration [130], algal blooms [131], Secchi disk depth [132], sediment discharge [133], water quality , turbidity [159][160][161][162][163][164], evapotranspiration [165,166], flash flood water depth [167], inundation status [168], ocean surface CO2 [169] 50 ...
... Wildfire management Wildfire prediction [32, , wildfire monitoring [25,33,, wildfire recovery [216,217] 52 [75], soil erodibility [76][77][78][79], soil matric potential [80], soil mercury [81], soil moisture , soil nutrients [109][110][111], soil total nitrogen [112], soil respiration [113], soil stiffness [114], soil texture [115][116][117], soil types [118], soil organic matter [119][120][121][122], soil water content and evapotranspiration [123] 93 Hydrology and water resources Groundwater level [124,125], streamflow [126], surface water [127,128], water storage [129], sediment concentration [130], algal blooms [131], Secchi disk depth [132], sediment discharge [133], water quality , turbidity [159][160][161][162][163][164], evapotranspiration [165,166], flash flood water depth [167], inundation status [168], ocean surface CO 2 [169] 50 ...
The application of machine learning (ML) and remote sensing (RS) in soil and water conservation has become a powerful tool. As analytical tools continue to advance, the variety of ML algorithms and RS sources has expanded, providing opportunities for more sophisticated analyses. At the same time, researchers are required to select appropriate technologies based on the research objectives, topic, and scope of the study area. In this paper, we present a comprehensive review of the application of ML algorithms and RS that has been implemented to advance research in soil and water conservation. The key contribution of this review paper is that it provides an overview of current research areas within soil and water conservation and their effectiveness in improving prediction accuracy and resource management in categorized subfields, including soil properties, hydrology and water resources, and wildfire management. We also highlight challenges and future directions based on limitations of ML and RS applications in soil and water conservation. This review aims to serve as a reference for researchers and decision-makers by offering insights into the effectiveness of ML and RS applications in the fields of soil and water conservation.
... Creation of scientifically sound sustainable development plans may benefit from an analysis of changes in habitat quality over time and space for a particular area of interest, as well as an understanding of the key variables, driving processes, and patterns of their spatial distribution. For maintaining ecological equilibrium and protecting biodiversity, this study approach is crucial Mondal et al., 2024;Wu et al., 2015). ...
... The study investigates environmental quality and health of mangrove forests of western Sundarbans delta using InVEST and ANN models. Study also evaluates the contribution of various stressors, particularly anthropogenic impacts, on the degradation of the mangrove vegetation in this lowlying protected habitat Mondal et al., 2024). The quality of the Sundarban mangrove environment has significantly changed, according to the study's analysis. ...
The startling rate of biodiversity loss, particularly in ecologically delicate coastal environments, is a major environmental concern facing the globe today. As sustainable exploitation of natural resources, including timber and other forest products from tropical rainforests and mangrove habitats, is crucial this research will examine the factors and processes that degrade mangrove habitats -in terms of their health and resilience -and suggest ways to reduce human impact. The study evaluates the evolution of Sundarbans—the largest contiguous mangrove forest in the world—coastal habitat quality from 2017 to 2022 using the InVEST and machine learning-based ANN model. The mangrove habitat sustained heavy destruction, including structural damage from the landfall of cyclone Amphan in May 2020. Spatial auto-correlation method and Geotagging were employed for location-dependent habitat quality analysis. Study demonstrates that habitat quality and degradation vary significantly across the Sundarbans mangrove forest provinces, particularly for habitat quality spatial distribution and their degradation. Important determinants for habitat quality are per capita water usage, night-time light index (proxy for population density), forest area, and prevalence of fragmented and degrading forest area. All factor pairings are bifactor or non-linear enhanced, showing that impact of two variables combined is more powerful than one alone in determining ecosystem quality and degeneration. In particular, forest land coverage and per capita water consumption have strong correlations with the habitat quality in the region. Geographical disparity of habitat quality and its probable causes suggests an urgent need for system-wide approach in implementing conservation and restoration measures for preserving Sundarbans mangroves, which spread across the international boundary between India and Bangladesh.
... Although these methods provide insights into temporal variations, they are time consuming and labor-intensive (Guo et al., 2021). Satellite technology enable large-scale, periodic monitoring of Chl-a by establishing a relationship between Chl-a concentration and remote sensing reflectance (Rrs) (Palmer, et al., 2015;Liu et al., 2021;Mondal et al., 2024). Over the past few decades, numerous algorithms have been developed to estimate Chla concentration. ...
... Satellite-based monitoring techniques are costeffective and provide comprehensive information on water quality conditions across extensive spatial and temporal scales (Tian et al., 2024). Consequently, remote sensing technology has long been an effective approach for estimating Chl-a concentrations in both coastal and inland waters (Bar et al., 2023;Mondal et al., 2024b). ...
The development of remote sensing algorithms has traditionally relied on satellite spectra or simulated equivalents derived from in-situ spectra to monitor inland water quality. However, such equivalent spectra often result in significant errors when retrieving chlorophyll-a (Chl-a) concentrations due to discrepancies between in-situ and satellite-derived spectra. In this research, the authors innovatively adjusted the red-light component of in-situ spectra for application in two inland waters, Dongzhang Reservoir and Jie Zhukou Reservoir. Sentinel-2 multispectral images (MSI), standard equivalent spectra (ES), and modified equivalent spectra (MES) were utilized as input data to assess models' effectiveness in terms of accuracy, robustness, and generalizability. The research applied Chl-a retrieval models including deep neural networks (DNN), extreme gradient boosting (XGB), and conventional statistical approaches with various spectral indices, such as the red-NIR method, the three-band method, and the normalized difference chlorophyll index (NDCI). The results revealed that the MES-based model achieved best results in Chl-a retrieval (RMSE = 2.04 mg/m3) comparable to MSI-based model (RMSE = 2.07 mg/m3) and ES-based model (RMSE = 7.71 mg/m3). Moreover, MES-based model behaved robustness and precision within selected water bodies and temporal periods. Notably, the integration of the red-NIR method with DNN was particularly effective in retrieving Chl-a with higher accuracy, robustness, and generalizability. Enhancement method to the equivalent spectra methodology provided by the research have reduced retrieval errors in retrieving Chl-a, and providing a valuable reference for future model development in this domain.
... Although this strategy allows for a large spatial resolution and the monitoring of big water bodies, it might not be as accurate due to factors such as cloud coverage, atmospheric conditions, or surface reflection. Also, remote sensing data typically need to process the sensed spectral information by way of complex algorithms in order that water quality parameters can be derived secondarily, making it susceptible to output errors and decreasing accuracies [11,12]. Figure 1 shows the benefits of water quality with remote sensing. ...
Water quality is a pivotal factor for maintaining human and ecological health. Traditional water quality assessments often depend on ground sampling and lab tests, which are costly, slow, and constrained by geographic limitations. The emergence of remote sensing technologies now allows for extensive and timely monitoring of water quality across vast regions. This study introduces an innovative approach that utilizes remote sensing data alongside a hybrid Generative Adversarial Network-Long Short-Term Memory (GAN-LSTM) model to transform the monitoring of water quality, focusing on pollution and sanitation management. We employed a comprehensive dataset from Kaggle, which includes 3276 data points and 10 essential water quality indicators, integrated with historical remote sensing data. The GAN model is designed to produce realistic synthetic datasets, which are then used by the LSTM model to predict water quality trends with high accuracy. The methodology achieved notable results, with an accuracy of 98%, precision of 97%, recall of 99%, and an F1-score of 98%. This approach leverages cutting-edge modeling techniques and extensive datasets to significantly improve the monitoring and management of water quality.
... There has been a growing interest in using machine-learning models to assess water quality, especially, in the recent years (Mondal et al., 2024). These models have the potential to detect changes quickly and effectively in water quality conditions (Huan and Liu, 2024). ...
The Water Quality Index (WQI) is a primary metric used to evaluate and categorize surface water quality which plays a crucial role in the management of fresh water resources. Machine Learning (ML) modeling offers potential insights into water quality index prediction. This study employed advanced ML models to get potential insights into the prediction of water quality index for the Aik-Stream, an industrially polluted natural water resource in Pakistan with 19 input water quality variables aligning them with surrounding land use and anthropogenic activities. Six machine learning algorithms, i.e. Adaptive Boosting (AdaBoost), K-Nearest Neighbors (K-NN), Gradient Boosting (GB), Random Forests (RF), Support Vector Regression (SVR), and Bayesian Regression (BR) were employed as benchmark models to predict the Water Quality Index (WQI) values of the polluted stream to achieve our objectives. For model calibration, 80% of the dataset was reserved for training, while 20% was set aside for testing. In our comparative analyses of predictive models for water quality index, the Gradient Boost (GB) model stood out the fittest for its precision, utilizing a combination of just seven parameters (chemical oxygen demand, total organic carbon, oil & grease, Ammonia- nitrogen, arsenic, nickel and zinc), surpassing other models by achieving better results in both training (R2 = 0.88, RMSE = 7.24) and testing (R2 = 0.85, RMSE = 8.67). Analyzing feature importance showed that all the selected variables, except for NO3 N, TDS and temperature had an impact on the accuracy of the models predictions. It is concluded that the application of machine learning to assess water quality in polluted environments enhances accuracy and facilitates real-time tracking, enabling proactive risk mitigations.
The Sundarbans coastal delta, spread across the international boundary between Bangladesh and India, is a globally recognized priority for conserving biodiversity. This region is particularly vulnerable to frequent flooding and the degradation of its fragile wetland environment, with an average elevation of just 2 m above sea level. The extent of this potential loss can be predicted with acceptable confidence since the average sea level is expected to increase 2 m globally by 2100, compared to the baseline period (2022). We investigated the possible impacts of three sea-level rise (SLR) scenarios on the Sundarbans using field and remote measurements, simulation modelling, and geographic information systems. Hindcast’s modelling efforts using the Sea Level Affecting Marshes Model (SLAMM) and machine learning (ML) algorithms accurate predictions of reported area declines during the 1990–2022 period. The input characteristics applied were the National Wetland Inventory (NWI) classifications, the slope of each cell, and the Digital Elevation Map (DEM). Next, using ML approaches, NWI categories were developed. We examined the effects of varying sea levels at 0.49 m in 2022, 0.79 m in 2050, 1.52 m in 2075, and 2 m in 2100, considering different wetland types, marsh accretion, wave erosion, and changes in surface elevation. According to estimates, the mangrove wetland area will decrease by ~ 46 km² between 2022 and 2050 under the 1.5-m and 1-m SLR scenarios. The decline in mangrove area by 2100 is estimated to be 81 km², 111 km², and 583 km² under the 1-m, 1.5-m, and 2-m SLR scenarios, respectively. Our results suggest that in a 1-m inundation scenario, approximately 325.36 km² of land may be submerged, whereas, for a 2-m inundation, this area increases substantially to 874.49 km², more than 2.5 times the area impacted by the 1-m scenario. Both scenarios resulted in significant land loss in the Sundarbans. Severe adverse effects from erosion and floods are expected in the coastal zone, including decreased capacity to sequester carbon gases. This study will help coastal management organizations estimate the impacts of SLR and pinpoint places that need significant mitigating efforts.
This study aims to explore the impact of fly ash (FA) on two types of free-floating aquatic plants, Eichhornia crassipes and Pistia stratiotes, growing in two different locations. The stress caused by FA has led to a significant biochemical alteration in several leaf properties, including ascorbic acid, relative water, and chlorophyll, as well as anatomical changes in leaf, petiole, and stolon in the growing plants at highly contaminated sites (HCS) relative to the low contaminated site (LCS). According to the study, HCS plants lose total chlorophyll overall, have shallower ascorbic acid levels, and have higher RWC than LCS plants. These findings imply that both species are highly resilient to pollution. The assessment of the shape and size of the epidermis, cortex, palisade cells, air space, bundle sheath, xylem cavity, phloem cells, vascular bundle, parenchyma, pith of the leaves, petioles, and stolon in the HCS is shorter than the LCS. The APTI values of E. crassipes (8.407%) and P. stratiotes (9.681%) are higher in HCS than the values of E. crassipes (7.729%) and P. stratiotes (9.077%) in LCS. These results suggest that both species exhibit greater APTI values in plants from HCS, indicating their tolerance to pollution. We target six water bodies in HCS and LCS to assess the FA-containing water quality. We calculated the water quality using WA-WQI and CCME-WQI. The higher WA-WQI scores indicate higher water pollution levels. The value of WA-WQI is higher in HCS sites included in the KTPP colony (93.94), Amalhanda (91.43), and Barunan Ghoshpara (89.07) than in LCS sites such as in Kashinathpur (88.59), but the CCME-WQI scores are 64.33, 76.09 and 75.71 respectively. The investigation highlights that both species are exceptionally suitable as stress-tolerant plants for fly ash and possess the potential to serve as an option for the restoration of water bodies impacted by fly ash. This study will enhance our comprehension of the potential advantages of these plants, particularly in the phytoremediation of polluted aquatic ecosystems.
To address the limitations of existing water quality prediction models in handling non-stationary data and capturing multi-scale features, this study proposes a hybrid model integrating Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN), Variational Mode Decomposition (VMD), Long Short-Term Memory Network (LSTM), and Frequency-Enhanced Channel Attention (FECA). The model aims to improve prediction accuracy and robustness for complex water quality dynamics, which is critical for environmental protection and sustainable water resource management. First, CEEMDAN and Sample Entropy (SE) were used to decompose raw water quality data into interpretable components and filter noise. Then, a VMD-enhanced LSTM architecture embedded with FECA was developed to adaptively prioritize frequency-specific features, thereby improving the model’s ability to handle nonlinear patterns. Results show that the model is successful in predicting all six water quality indicators: NH₃-N (ammonia nitrogen), DO (dissolved oxygen), pH, TN (total nitrogen), TP (total phosphorus), and CODMn (chemical oxygen demand, permanganate method). The model achieved Nash-Sutcliffe Efficiency (NSE) values ranging from 0.88 to 0.99. Using dissolved oxygen (DO) as an example, the model reduced the Mean Absolute Percentage Error (MAPE) by 0.12% and increased the coefficient of determination (R2) by 0.20% compared to baseline methods. This work provides a robust framework for real-time water quality monitoring and supports decision making in pollution control and ecosystem management.
It is time consuming and expensive to monitor extensive areas of coastal waters with sufficient frequency using in situ (ship based) methods. Satellite remote sensing is much more cost effective. Satellites can detect Optically Active Constituents (OACs) in water. Therefore, it is crucial to know the concentrations of OACs in the study area in order to develop and validate remote sensing methods suitable for assessing water quality in this region. The Pars Special Economic Energy Zone (PSEEZ), a major hub of natural gas extraction in the Persian Gulf, has undergone rapid industrial expansion since 1998, intensifying environmental pressures and necessitating high-resolution, frequent water quality assessments. However, a structured, long-term monitoring framework is absent despite the significance of this region. In order to develop satellite-based remote sensing methods for this region we carried out measurements of different OACs (chlorophyll-a, coloured dissolved organic matter (CDOM) and turbidity) and tested Landsat 8, Sentinel-2, and Sentinel-3 performance in retrieving the OACs. We tested the k-Nearest Neighbors machine learning algorithm. The selection of distance metrics demonstrated a significant influence on the accuracy of retrieving OACs. In turbidity retrieval, the Euclidean Distance (ED) enhanced the regression slope to 0.90 (a 55.17 % improvement over Fuzzy Mahalanobis Distance (FD)) and reduced the RMSLE to 0.51, corresponding to an approximate 160 % enhancement in precision. For CDOM, RMSLE values for ED and FD were 0.39 and 0.48, respectively, indicating an 18.75 % improvement favoring ED. Furthermore, bias analysis revealed deviations of 1-6 % compared to reference data, with the lowest values observed for Mahalanobis Distance (MD) with MSI and FD with OLCI. In chlorophyll-a retrieval, the choice of distance metric directly impacted the accuracy of the OLCI sensor, inducing bidirectional bias, comprising both overestimation and underestimation, which varied depending on the selected metric. These results underscore the critical importance of optimizing distance metric selection to enhance prediction accuracy and mitigate systematic errors in remote sensing applications. Furthermore, the results revealed that the implementation of this algorithm exhibited substantially superior performance compared to other evaluated algorithms within the study area, achieving significantly higher accuracy metrics. Thereby establishing k-NN as the optimal framework for satellite-based water quality monitoring in environmentally sensitive regions like PSEEZ.
Accurate estimation of coastal and inland water quality parameters is important for managing water resources and meeting the demand of sustainable development goals. The water quality monitoring based on discrete water sample analysis is limited to specific locations and becomes less effective to offer a synoptic view of the water quality variability at different spatial and temporal scales. The optical remote sensing techniques have proved their ability to provide a comprehensive and synoptic view of water quality parameters. In conjugation with other products, the optical remote sensing data products can be utilized for the effective management of water bodies while addressing the socioeconomic issues faced by local governments and states. In recent years, multiple machine-learning (ML) models have been reported on the estimation of water quality using remote sensing data, but their performance is limited when extended to diverse water types within coastal and inland water environments. In this study, we present an ensemble machine-learning model for estimating the primary water quality parameters in coastal and inland waters, such as Chlorophyll-a (Chl-a) concentration, colored dissolved organic matter (a CDOM (440)), and Turbidity. It utilizes the in-situ measurements to train and optimize the ensemble machine-learning models for the spectral measurements data (400-700 nm) provided by MODIS-Aqua, Sentinel-2 Multi Spectral Instrument (MSI), and PlanetScope (Planet). To develop the prediction models, these in-situ measurements data were split into two parts: a training dataset (70 %) and a testing dataset (30 %). The ensemble machine-learning models were validated using the 5-fold cross-validation method. These models were trained and tested against distinct datasets encompassing a broad range of variations in water quality parameters collected from open ocean, coastal and inland waters. The validation results demonstrated a superior performance of the present ensemble ML models compared to other ML models (Chl-a: R 2 = 0.96, RMSE = 4.93, MAE = 2.89; a CDOM (440): R 2 = 0.93, RMSE = 0.057, MAE = 0.025; Turbidity: R 2 = 0.95, RMSE = 4.52, MAE = 1.009). To realize the importance of this study, the ensemble ML models were applied to MODIS-Aqua monthly composite measurements from 2003 to 2022 and captured pronounced seasonal variations in water quality parameters (WQP) and Water Quality Index (WQI). For instance, in the Gulf of Khambhat, turbidity decreased at an annual average rate of~0.08 NTU and Chl-a increased at an annual average rate of~0.004 mg m − 3 for the past 20 years. Furthermore, we investigated the occurrences of Noctiluca scintillans (here after N. scintillans) bloom between 2019 and 2021 near the fin fish cage culture sites in Mandapam, on the southeast coast of Tamil Nadu, within the Gulf of Mannar, India which serves as a documentation of the Harmful Algal Bloom (HAB) incidents. The performance of ensemble model is further demonstrated using Planet images from inland turbid waters of the Muthupet lagoon (Brackish water) and Adyar river (Urban River) and MSI image from Chilika lagoon. The proposed ensemble ML models proved as an effective method for accurately estimating the WQP and WQI products and capturing their spatial and temporal variations in regional and global waters, which forms an important tool for sustainable development and management of coastal and inland water environments.
Despite having more than 200 environmental laws and policies in Bangladesh, the overall ecological situation is almost beyond control. Relying on both primary and secondary sources of data, particularly the legal texts, this study delves into analysing the legal frameworks of Bangladesh pertaining to wildlife and biodiversity conservation in the Sundarbans mangrove forest (SMF). This study finds that the lack of implementation of stringent provisions is one of the key reasons for the failure to successfully conserve biological diversity in the SMF. The other reason that heavily accelerates environmental crimes in Bangladesh is the less severe punishment compared to other crimes. This study result reveals that the Animal Welfare Act 2019 imposes a mere BDT 10,000 (USD 116) for harming any animal. This study also finds that the Environment Court Act 2010 strives to expand environmental governance in every district, but the absolute authority of the Department of Environment (DoE) and its limited resources hinder such lavish expansion. Although the government has revised many outdated laws and policies and enacted new laws such as Bangladesh Environment Conservation Act 1995 (2023), Forest Act 2023, and Forest Conservation Act 2023, evidence indicates that most of the provisions were not successfully implemented due to overlaps with other laws and loopholes within the laws. In addition, complex bureaucratic systems significantly hamper the administration system in forest management. Furthermore, the Director General (DG) of the DoE’s sole authority often sparked concerns regarding the transparency and accountability of this department. Therefore, this paper examines the domestic legal system of Bangladesh for conserving biodiversity in the SMF.
The application of machine learning (ML) and remote sensing (RS) in soil and water conserva-tion has become a powerful tool. As analytical tools continue to advance, the variety of ML al-gorithms and RS sources has expanded, providing opportunities for more sophisticated analyses. At the same time, researchers are required to select appropriate technologies based on research objectives, topic, and scope of the study area. In this paper, we present a comprehensive review on the application of ML algorithms and RS that has been implemented to advance research in soil and water conservation. The key contribution of this review paper is that it provides an overview of current research areas within soil and water conservation and their effectiveness in improving prediction accuracy and resource management in categorized subfields, including biomass-vegetation, soil properties, hydrology and water resources, and wildfire management. We also highlight challenges and future directions based on limitations of ML and RS applica-tions in soil and water conservation. This review aims to serve as a reference for researchers and decision-makers by offering insights into the effectiveness of ML and RS applications in the field of soil and water conservation.
Zooplankton plays crucial roles in the food web by transferring energy from primary producers to higher trophic
levels. The Indian Sundarbans, being a large mangrove-estuarine ecosystem, harbors rich aquatic diversity but
endures several threats from anthropogenic activities. The present review comprehensively summarizes the
status of zooplankton in the Indian Sundarbans. This review discusses the distribution of zooplankton across
rivers and tidal creeks/canals, the influences of water parameters, possible threats, and conservation proposals
through potential long-term monitoring. Calanoid copepods (~32.02 %) are predominant in the Indian Sundarbans, followed by Choreotrichida (~17.8 %), Cyclopoida (~8.67 %), Decapoda (~7.55 %), and Harpacticoida
(~5.66 %). As per previous studies, calanoid Pseudodiaptomus serricaudatus is predominant in rivers, followed by
Paracalanus parvus, Bestiolina similis, Acartia plumosa, and Acartiella tortaniformis. Salinity is the key water
parameter influencing the assemblage and distribution of zooplankton in the Indian Sundarbans. Zooplankton in
this region face several threats, such as pollution, natural disasters, and the development of river dykes, which
may raise serious concerns about their survival. This review recommends conservation and long-term monitoring
programs, including mass culture, database development, and the use of advanced techniques to support conservation policies for zooplankton communities. Special emphasis is given to habitat conservation and the
implementation of river conservation programs like “Namami Gange” initiated by the Government of India.
Additionally, this review outlines a baseline draft on zooplankton monitoring in the Indian Sundarbans,
addressing sampling frequency, sampling locations, and possible funding opportunities for the smooth running of
this program.
In water-scarce arid areas, the water cycle is affected by urban development and natural river changes, and urbanization has a profound impact on the hydrological system of the basin. Through an ecohydrological observation system established in the Shiyang River basin in the inland arid zone, we studied the impact of urbanization on the water cycle of the basin using isotope methods. The results showed that urbanization significantly changed the water cycle process in the basin and accelerated the rainfall-runoff process due to the increase in urban land area, and the mean residence time (MRT) of river water showed a fluctuating downward trend from upstream to downstream and was shortest in the urban area in the middle reaches, and the MRT was mainly controlled by the landscape characteristics of the basin. In addition, our study showed that river water and groundwater isotope data were progressively enriched from upstream to downstream due to the construction of metropolitan landscape dams, which exacerbated evaporative losses of river water and also strengthened the hydraulic connection between groundwater and river water around the city. Our findings have important implications for local water resource management and urban planning and provide important insights into the hydrologic dynamics of urban areas.
The study explores the spatio-temporal variation of water quality parameters in the Hooghly estuary, which is considered an ecologically-stressed shallow estuary and a major distributary for the Ganges River. The estimated parameters are chlorophyll-a, total suspended matter (TSM), and chromophoric dissolved organic matter (CDOM). The Sentinel-3 OLCI remote sensing imageries were analyzed for the duration of October 2018 to February 2019. We observed that the water quality of the Hooghly estuaries is comparatively low-oxygenated, mesotrophic, and phosphate-limited. Ongoing channel dredging for maintaining shipping channel depth keeps the TSM in the estuary at an elevated level, with the highest amount of TSM observed during March of 2019 (41.59g m⁻³) at station A, upstream point. Since the pre-monsoon season, TSM data shows a decreasing trend towards the mouth of the estuary. Chl-a concentration is higher during pre-monsoon than monsoon and post-monsoon periods, with the highest value observed in April at 1.09 mg m⁻³ in station D during the pre-monsoon period. The CDOM concentration was high in the middle section (January–February) and gradually decreased towards the estuary’s head and mouth. The highest CDOM was found in February at locations C and D during the pre-monsoon period. Every station shows a significant correlation among CDOM, TSM, and Chl-a measured parameters. Based on our satellite data analysis, it is recommended that SNAP C2RCC be regionally used for TSM, Chl-a, and CDOM for water quality product retrieval and in various algorithms for the Hooghly estuary monitoring.
The purpose of this study was to evaluate the spatiotemporal distribution of physicochemical parameters along Mumbai coastal water. Water samples were taken using an experimental fishing cum research vessel in order to monitor and evaluate ecosystem stress. Sea Surface Temperature, Sea Surface Salinity, pH, Chlorophyll-a, DO, BOD, Alkalinity, and Primary Productivity are all measured on a monthly basis. The range of the sea surface temperature was 26.5-29.5°C. Sea surface salinity ranged from 32 to 36, and pH was in the 7.9 to 8.3 range. The ranged of the Dissolved oxygen concentration was 2-2.9 mg/l. The alkalinity levels were 118–125 mg/l. BOD was between 3.8 and 5.4 mg/l. Primary productivity concentrations ranged from 0.77 to 0.85 mg C/m3/d. To estimate the accuracy with in-situ field measured parameters with remotely sensed parameter comparison of Sea Surface Temperature, Sea Surface Salinity, Chlorophyll-a, and Primary Productivity was carried out. All of the parameters had acceptable levels of accuracy (SST: r2≥0.79, ≤0.713 [°C], SSS: r2≥ 0.90, ≤ 0.517 [‰], Chl-a: r2≥ 0.83, ≤ 1.925 [mg/m3]) and further adjustments could be made for satellite-based primary productivity (r2≥ 0.64, ≤ 241.30 [mg. C/m2/d]) for use in the future.
Remote Sensing for water quality assessment is a newly emerging field. Although numerous studies have been conducted to evaluate the correlation between the Digital Number (DN) of bands and water quality parameters (WQP), further studies are required to make this methodology a robust low-cost technique for water quality assessment. With a brief case study of spatio-temporal analysis of WQPs of the Sundarban estuary, the current work explores the possibility of multispectral remote sensing for large-scale water quality monitoring. The study is about establishing empirical relationships between DN values (single, multiple or combination of many bands) with a limited number of in-situ measurements of WQPs such as Chlorophyll algae, Turbidity, pH, Salinity and Euphotic Depth. The study also assesses seasonal variation of WQPs for the period 2013-2014. Stepwise regressions have been performed to select the best predictors of each WQPs; afterwards, simple or multiple regression has been performed according to the result of stepwise regression. Temporal variation has been assessed for summer and winter using those predicted maps. The predictors of Chlorophyll-a, Euphotic Depth, pH, Salinity, Turbidity are B4/B5; B4/B6; B5/B7; B5/B7; B6/B7 for summer and B3/B5; B2/B3, B4; B1, B3/B6; (B2/B5); (B2/B5) for the winter. Three best model estimates are pH and chlorophyll-a of both the seasons with RMSEs of 0.202865, 0.059793, 0.477288568, and 0.224603275905043 respectively. Higher chlorophyll-a, pH and turbidity found in Hooghly estuary in both seasons, at Matla, Thakuran, Raimangal and Harinbhanga higher salinity found in both season and higher euphotic depth found in summer.
Ileana Callejas discusses how remote sensing can be used to monitor water quality in coastal regions,including tracking sewage plumes, algal blooms and oil spills.
Coastal water quality management is a public health concern, as water of poor quality can potentially harbor dangerous pathogens. In this study, we employ routine monitoring data of EscherichiaColi and enterococci across 15 beaches in the city of Rijeka, Croatia, to build machine learning models for predicting E.Coli and enterococci based on environmental features. Cross-validation analysis showed that the Catboost algorithm performed best with R2 values of 0.71 and 0.69 for predicting E.Coli and enterococci, respectively, compared to other evaluated algorithms. SHapley Additive exPlanations technique showed that salinity is the most important feature for forecasting both E.Coli and enterococci levels. Furthermore, for low water quality sites, the spatial predictive models achieved R2 values of 0.85 and 0.83, while the temporal models achieved R2 values of 0.74 and 0.67. The temporal model achieved moderate R2 values of 0.44 and 0.46 at a site with high water quality.
With the rapid increase in the volume of data on the aquatic environment, machine learning has become an important tool for data analysis, classification, and prediction. Unlike traditional models used in water-related research, data-driven models based on machine learning can efficiently solve more complex nonlinear problems. In water environment research, models and conclusions derived from machine learning have been applied to the construction, monitoring, simulation, evaluation, and optimization of various water treatment and management systems. Additionally, machine learning can provide solutions for water pollution control, water quality improvement, and watershed ecosystem security management. In this review, we describe the cases in which machine learning algorithms have been applied to evaluate the water quality in different water environments, such as surface water, groundwater, drinking water, sewage, and seawater. Furthermore, we propose possible future applications of machine learning approaches to water environments.
Water pollution has become one of the most serious issues threatening water environments, water as a resource and human health. The most urgent and effective measures rely on dynamic and accurate water quality monitoring on a large scale. Due to their temporal and spatial advantages, remote sensing technologies have been widely used to retrieve water quality data. With the development of hyper-spectral sensors, unmanned aerial vehicles (UAV) and artificial intelligence, there has been significant advancement in remotely sensed water quality retrieval owing to various data availabilities and retrieval methodologies. This article presents the application of remote sensing for water quality retrieval, and mainly discusses the research progress in terms of data sources and retrieval modes. In particular, we summarize some retrieval algorithms for several specific water quality variables, including total suspended matter (TSM), chlorophyll-a (Chl–a), colored dissolved organic matter (CDOM), chemical oxygen demand (COD), total nitrogen (TN) and total phosphorus (TP). We also discuss the significant challenges to atmospheric correction, remotely sensed data resolution, and retrieval model applicability in the domains of spatial, temporal and water complexity. Finally, we propose possible solutions to these challenges. The review can provide detailed references for future development and research in water quality retrieval.
Characterizing and forecasting coastal water quality and spatiotemporal evolution should be significant to coastal ecosystem management. However, high-quality modeling coastal water quality and their spatiotemporal evolutions is rather challenging due to complex dynamic mechanisms especially in a spatially and temporally heterogenous semi-enclosed bay. To this end, this study develops a framework incorporating machine learning (ML) algorithms and the Environmental Kuznets Curves (EKC) analysis to model, analyze and forecast the spatiotemporal variations of water quality indicators for different subzones and seasons in the semi-enclosed Tolo Harbour of Hong Kong. The application results indicate that the developed ML-based framework with an accuracy range of 0.672 ∼ 0.998 is well-suited in forecasting and understanding the coastal water evolution in a semi-enclosed harbour compared to conventional approach. Furthermore, the spatiotemporal characteristics of coastal water quality evolution in this semi-enclosed bay are analyzed and discussed for coastal hydro-environmental management. Moreover, the EKC analysis is also performed for determining the evolutions of essential water quality variables under 95% confidence interval of Hong Kong PCGDP projection and then implemented in the developed ML-based model for future prediction.
The Swarnamukhi river estuary (SRE), and the surrounding sea in Nellore, southeast coast of India, is one of the least studied marine environments, notably for physicochemical characteristics. Seawater samples were collected from five stations every month from 2014 to 2017 to assess physicochemical characteristics. The open sea (OS) station was significantly different from the inner stations, according to non-metric multidimensional scaling and cluster analysis. The variability was shown by strong factor loadings of atmospheric temperature (0.87), water temperature (0.84), biochemical oxygen demand (0.77), ammonia (0.85), and total nitrogen (0.78). Furthermore, one-way ANOVA and box-whisker plots facilitated simplifying and corroborating multivariate results that showed high concentration in the inner stations. Based on the N/P and Si/N ratios, nitrate and silicate were the key limiting factors in this study. The findings are critical for establishing reference conditions for comparison studies with other comparable ecosystems in the tropical region for better environmental conservation and management.
The quality of water has a direct influence on both human health and the environment. Water is utilized for a variety of purposes, including drinking, agriculture, and industrial use. The water quality index (WQI) is a critical indication for proper water management. The purpose of this work was to use machine learning techniques such as RF, NN, MLR, SVM, and BTM to categorize a dataset of water quality in various places across India. Water quality is dictated by features such as dissolved oxygen (DO), total coliform (TC), biological oxygen demand (BOD), Nitrate, pH, and electric conductivity (EC). These features are handled in five steps: data pre-processing using min-max normalization and missing data management using RF, feature correlation, applied machine learning classification, and model's feature importance. The highest accuracy Kappa, Accuracy Lower, and Accuracy Upper findings in this research are 99.83, 99.17, 99.07, and 99.99, respectively. The finding showed that Nitrate, PH, conductivity, DO, TC, and BOD are the key qualities that contribute to the orderly classification of water quality, with Variable Importance values of 74.78, 36.805, 81.494, 105.770, 105.166, and 130.173, respectively.
The Indian Sundarbans, together with Bangladesh, comprise the largest mangrove forest
in the world. Reclamation of the mangroves in this region ceased in the 1930s. However, they are
still subject to adverse environmental influences, such as sediment starvation due to migration of the
main river channels in the Ganges–Brahmaputra delta over the last few centuries, cyclone landfall,
wave action from the Bay of Bengal—changing hydrology due to upstream water diversion—and the
pervasive effects of relative sea-level rise. This study builds on earlier work to assess changes from
2000 to 2020 in mangrove extent, genus composition, and mangrove ‘health’ indicators, using various
vegetation indices derived from Landsat and MODIS satellite imagery by performing maximum
likelihood supervised classification. We show that about 110 km2 of mangroves disappeared within the reserve forest due to erosion, and 81 km2 were gained within the inhabited part of Sundarbans Biosphere Reserve (SBR) through plantation and regeneration. The gains are all outside the contiguous mangroves. However, they partially compensate for the losses of the contiguous mangroves
in terms of carbon. Genus composition, analyzed by amalgamating data from published literature and ground-truthing surveys, shows change towards more salt-tolerant genus accompanied by a reduction in the prevalence of freshwater-loving Heiritiera, Nypa, and Sonneratia assemblages. Health indicators, such as the enhanced vegetation index (EVI) and normalized differential vegetation index (NDVI), show a monotonic trend of deterioration over the last two decades, which is more pronounced in the sea-facing parts of the mangrove forests. An increase in salinity, a temperature rise, and rainfall reduction in the pre-monsoon and the post-monsoon periods appear to have led to such degradation. Collectively, these results show a decline in mangrove area and health, which poses an existential threat to the Indian Sundarbans in the long term, especially under scenarios of climate change and sea-level rise. Given its unique values, the policy process should acknowledge and address these threats
Groundwater quality appraisal is one of the most crucial tasks to ensure safe drinking water sources. Concurrently, a water quality index (WQI) requires some water quality parameters. Conventionally, WQI computation consumes time and is often found with various errors during subindex calculation. To this end, 8 artificial intelligence algorithms, e.g., multilinear regression (MLR), random forest (RF), M5P tree (M5P), random subspace (RSS), additive regression (AR), artificial neural network (ANN), support vector regression (SVR), and locally weighted linear regression (LWLR), were employed to generate WQI prediction in Illizi region, southeast Algeria. Using the best subset regression, 12 different input combinations were developed and the strategy of work was based on two scenarios. The first scenario aims to reduce the time consumption in WQI computation, where all parameters were used as inputs. The second scenario intends to show the water quality variation in the critical cases when the necessary analyses are unavailable, whereas all inputs were reduced based on sensitivity analysis. The models were appraised using several statistical metrics including correlation coefficient (R), mean absolute error (MAE), root mean square error (RMSE), relative absolute error (RAE), and root relative square error (RRSE). The results reveal that TDS and TH are the key drivers influencing WQI in the study area. The comparison of performance evaluation metric shows that the MLR model has the higher accuracy compared to other models in the first scenario in terms of 1, 1.4572*10-08, 2.1418*10-08, 1.2573*10-10%, and 3.1708*10-08% for R, MAE, RMSE, RAE, and RRSE, respectively. The second scenario was executed with less error rate by using the RF model with 0.9984, 1.9942, 3.2488, 4.693, and 5.9642 for R, MAE, RMSE, RAE, and RRSE, respectively. The outcomes of this paper would be of interest to water planners in terms of WQI for improving sustainable management plans of groundwater resources.
To assess the magnitude of water quality decline in the Turag River of Bangladesh, this study examined the seasonal variation of physicochemical parameters of water, identified potential pollution sources, and clustered the monitoring months with similar characteristics. Water samples were collected in four distinct seasons to evaluate temperature, pH, dissolved oxygen (DO) concentration, five-day biochemical oxygen demand (BOD5), chemical oxygen demand (COD), electrical conductivity (EC), chloride ion (Cl−) concentration, total alkalinity (TA), turbidity, total dissolved solids (TDS) concentration, total suspended solids (TSS) concentration, and total hardness (TH) using standard methods. The analytical results revealed that 40% of water quality indices were within the permissible limits suggested by different agencies, with the exception of EC, Cl− concentration, TA, turbidity, DO concentration, BOD5, and COD in all seasons. Statistical analyses indicated that 52% of the contrasts were significantly different at a 95% confidence interval. The factor analysis presented the best fit among the parameters, with four factors explaining 94.29% of the total variance. TDS, BOD5, COD, EC, turbidity, DO, and Cl− were mainly responsible for pollution loading and were caused by the significant amount of industrial discharge and toxicological compounds. The cluster analysis showed the seasonal change in surface water quality, which is usually an indicator of pollution from rainfall or other sources. However, the values of different physicochemical properties varied with seasons, and the highest values of pollutants were recorded in the winter. With the change in seasonal temperature and increase in rainfall, the seasonal Turag River water followed a self-refining trend as follows: rainy season > pre-winter > summer > winter.
Today, there are undesired changes in the physical, chemical, and biological characteristics of water which impose a tremendous threat on aquatic species. Knowing the details of physical and chemical parameters and their behaviors such as temperature, salinity, density, dissolved oxygen, pH, electrical conductivity, turbidity, and chlorophyll-a for survivability of the aquatic ecosystem is essential. This paper discusses these parameters through a time series analysis of observation for the year 2007. The spatial and temporal variations of water chemical and physical parameters are investigated in nine stations in the northern part of the Persian Gulf. While many investigations have been carried out on the Persian Gulf, the innovation of this research is focusing on the northern part which is not or little discussed in the previous, historical studies, and barely data are available for this region. Analyses of the data in the study area show that the water is well mixed during the year due to the shallowness and tidal effects. Water is alkaline and tends to have a stable pH and relatively high salinity and temperature. pH is an important factor in determining the amount of toxic dissolved heavy metals in water. Turbidity and chlorophyll-a are low at the surface and increased toward the water bed as depth increases. The results of this paper are of the interest of the academic, business, and industrial communities and from a management point of view help the policymakers and environment managers to propose effective–strategic decisions that both help coastal communities and save aquatic life.
The water quality index (WQI) model is a popular tool for evaluating surface water quality. It uses aggregation techniques that allow conversion of extensive water quality data into a single value or index. Globally, the WQI model has been applied to evaluate water quality (surface water and groundwater) based on local water quality criteria. Since its development in the 1960s, it has become a popular tool due to its generalised structure and ease-of-use. Commonly, WQI models involve four consecutive stages; these are (1) selection of the water quality parameters, (2) generation of sub-indices for each parameter (3) calculation of the parameter weighting values, and (4) aggregation of sub-indices to compute the overall water quality index. Several researchers have utilized a range of applications of WQI models to evaluate the water quality of rivers, lakes, reservoirs, and estuaries. Some problems of the WQI model are that they are usually developed based on site-specific guidelines for a particular region, and are therefore not generic. Moreover, they produce uncertainty in the conversion of large amounts of water quality data into a single index.
This paper presents a comparative discussion of the most commonly used WQI models, including the different model structures, components, and applications. Particular focus is placed on parameterization of the models, the techniques used to determine the sub-indices, parameter weighting values, index aggregation functions and the sources of uncertainty. Issues affecting model accuracy are also discussed.
Garlic and winter wheat are major economic and grain crops in China, and their boundaries have increased substantially in recent decades. Updated and accurate garlic and winter wheat maps are critical for assessing their impacts on society and the environment. Remote sensing imagery can be used to monitor spatial and temporal changes in croplands such as winter wheat and maize. However, to our knowledge, few studies are focusing on garlic area mapping. Here, we proposed a method for coupling active and passive satellite imagery for the identification of both garlic and winter wheat in Northern China. First, we used passive satellite imagery (Sentinel-2 and Landsat-8 images) to extract winter crops (garlic and winter wheat) with high accuracy. Second, we applied active satellite imagery (Sentinel-1 images) to distinguish garlic from winter wheat. Third, we generated a map of the garlic and winter wheat by coupling the above two classification results. For the evaluation of classification, the overall accuracy was 95.97%, with a kappa coefficient of 0.94 by eighteen validation quadrats (3 km by 3 km). The user's and producer's accuracies of garlic are 95.83% and 95.85%, respectively; and for the winter wheat, these two accuracies are 97.20% and 97.45%, respectively. This study provides a practical exploration of targeted crop identification in mixed planting areas using multisource remote sensing data.
Application of remote sensing makes the assessment and monitoring of mangroves both time and cost-effective. In this study, the capacity of AVIRIS-NG data in discriminating different mangrove species of Lothian Island of Indian Sundarbans has been evaluated and compared with hyperspectral (Hyperion) and multispectral dataset (Landsat 8 OLI and Sentinel-2). Spectral signatures of mangrove species were retrieved, and spectral libraries were created. With the corrected images and spectral libraries, mangroves were classified using appropriate classification techniques. For multispectral datasets (Landsat 8 OLI and Sentinel-2) and hyperspectral coarser-resolution Hyperion datasets, K-means classification followed by knowledge-based classification was adopted. For fine resolution hyperspectral AVIRIS-NG data-set, classification was accomplished using Support Vector Machine (SVM). The overall accuracy for the classification is significantly high in case of AVIRIS-NG data (87.61%) compared to the Landsat 8 OLI (76.42%), Sentinel-2 (79.81%), and Hyperion data (81.98%). The results showed that AVIRIS-NG hyper-spectral dataset has the potential to classify not only the genus level but also species-level with satisfactory accuracy in a complex mangrove forest. Ó 2020 National Authority for Remote Sensing and Space Sciences. Production and hosting by Elsevier B. V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
Water Quality Index (WQI) is the most common determinant of the quality of the stream-flow. According to the Department of Environment (DOE, Malaysia), WQI is chiefly affected by six factors, which are, chemical oxygen demand (COD), biochemical oxygen demand (BOD), dissolved oxygen (DO), suspended solids (SS), -potential for hydrogen (pH), and ammoniacal nitrogen (AN). In fact, understanding the inter-relationships between these variables and WQI can improve predicting the WQI for better water resources management. The aim of this study is to create an input approach using ANNs (Artificial Neural Networks) to compute the WQI from input parameters instead of using the indices of the parameters when one of the parameters is absent. The data are collected from the nine water quality monitoring stations at the Klang River basin, Malaysia. In addition, comprehensive sensitivity analysis has been carried out to identify the most influential input parameters. The model is based on the frequency distribution of the significant factors showed exceptional ability to replicate the WQI and attained very high correlation (98.78%). Furthermore, the sensitivity analysis showed that the most influential parameter that affects WQI is DO, while pH is the least one. Additionally, the performance of models shows that the missing DO values caused deterioration in the accuracy.
This paper investigates the impacts of changing land use–land cover on the land surface temperature (LST) and normalized differential vegetation index (NDVI) distribution in the Indian part of the Sundarbans Biosphere Reserve by utilizing remote sensing and geographical information system. Landsat Thematic Mapper (TM), Enhanced Thematic Mapper (ETM+) and Operational Land Imager images of the year 2000, 2010 and 2017, respectively, were used to assess the essential indicators for regional environmental health employing appropriate calibrations and corrections. It was observed that there has been a marked reduction in the areas of plantation, mangrove swamp, mangrove forests and agricultural land since 2000. In contrast, an increase in sand beach, waterlogged areas, mudflat, river, and agriculture area was observed. The mean NDVI values for mangrove forests and plantation have decreased from 0.441 to 0.229 and 0.266 to 0.195, respectively, while river, aquaculture, agricultural and open scrubs classes had higher values. The rate of increase in surface LST was highest over settlements, followed by sand beaches, mudflats, aquaculture, mangrove forest, river, plantations, waterlogged areas and agricultural field. LST showed a negative correlation with NDVI values probably due to the high rate of evapo-transpiration activities of the mangrove vegetations. All these above facts distinctly substantiates that there is an increase in open patches/non-vegetated cover and that the ecosystem is under constant stress.
In a smart home linked to a smart grid (SG), demand-side management (DSM) has the potential to reduce electricity costs and carbon/chlorofluorocarbon emissions, which are associated with electricity used in today’s modern society. To meet continuously increasing electrical energy demands requested from downstream sectors in an SG, energy management systems (EMS), developed with paradigms of artificial intelligence (AI) across Internet of things (IoT) and conducted in fields of interest, monitor, manage, and analyze industrial, commercial, and residential electrical appliances efficiently in response to demand response (DR) signals as DSM. Usually, a DSM service provided by utilities for consumers in an SG is based on cloud-centered data science analytics. However, such cloud-centered data science analytics service involved for DSM is mostly far away from on-site IoT end devices, such as DR switches/power meters/smart meters, which is usually unacceptable for latency-sensitive user-centric IoT applications in DSM. This implies that, for instance, IoT end devices deployed on-site for latency-sensitive user-centric IoT applications in DSM should be aware of immediately analytical, interpretable, and real-time actionable data insights processed on and identified by IoT end devices at IoT sources. Therefore, this work designs and implements a smart edge analytics-empowered power meter prototype considering advanced AI in DSM for smart homes. The prototype in this work works in a cloud analytics-assisted electrical EMS architecture, which is designed and implemented as edge analytics in the architecture described and developed toward a next-generation smart sensing infrastructure for smart homes. Two different types of AI deployed on-site on the prototype are conducted for DSM and compared in this work. The experimentation reported in this work shows the architecture described with the prototype in this work is feasible and workable.
The present study has applied artificial neural network (ANN) and multiple linear regression (MLR) techniques to predict the fitness of groundwater quality for drinking from Shivganga River basin, located on the eastern slopes of the Western Ghat region of India. In view of this, thirty-four (34) representative groundwater samples have been collected and analyzed for major cations and anions during pre-and post-monsoon seasons of 2015. The physicochemical parameters such as pH, EC, TDS, TH, Ca, Mg, Na, K, Cl, HCO 3 , SO 4 , NO 3 and PO 4 were considered for computing water quality index (WQI). Analytical results confirmed that all the parameters are within acceptable range; however, EC, TDS, TH, Ca and Mg are exceeding the desirable limit of the WHO drinking standards. The groundwater suitability for drinking was ascertained by WQI method. The WQI value ranges from 25.75 to 129.07 and from 37.54 to 91.38 in pre-and post-monsoon seasons, respectively. Only one sample (DW5) shows 129.07 WQI value indicating poor quality for drinking due to input of domestic and agricultural waste. In the view of generating consistent and precise model for prediction of WQI-based groundwater quality, a Levenberg-Marquardt three-layer back propagation algorithm was used in ANN architecture. Further, MLR model is used to check the efficiency of ANN prediction. The results corroborated that predictions of ANN model are satisfactory and confirms consistently acceptable performance for both the seasons. The proposed ANN model may be useful in similar studies of groundwater quality prediction for drinking purpose.
In order to understand the relative importance and elucidated seasonal variation samples were collected from two stations at monthly intervals. The results of ANOVA suggested that temperature and salinity shows significant variation from station-wise as well as season wise. From the Box plot analysis, it is inferred that the changes in the physio-chemical parameters are mainly due to climatic change, anthropogenic activity and urbanization and these play a key role in changes in the water column. © 2018, National Institute of Science Communication and Information Resources (NISCAIR). All rights reserved.
The water quality index (WQI) has been used to identify threats to water quality and to support better water resource management. This study combines a machine learning algorithm, WQI, and remote sensing spectral indices (difference index, DI; ratio index, RI; and normalized difference index, NDI) through fractional derivatives methods and in turn establishes a model for estimating and assessing the WQI. The results show that the calculated WQI values range between 56.61 and 2,886.51. We also explore the relationship between reflectance data and the WQI. The number of bands with correlation coefficients passing a significance test at 0.01 first increases and then decreases with a peak appearing after 1.6 orders. WQI and DI as well as RI and NDI correlation coefficients between optimal band combinations of the peak also appear after 1.6 orders with R² values of 0.92, 0.58 and 0.92. Finally, 22 WQI estimation models were established by POS-SVR to compare the predictive effects of these models. The models based on a spectral index of 1.6 were found to perform much better than the others, with an R² of 0.92, an RMSE of 58.4, and an RPD of 2.81 and a slope of curve fitting of 0.97.
This paper demonstrates the application of data mining techniques to predict river water quality index. The usefulness of these techniques lies in the automated extraction of novel knowledge from the data to improve decision-making. The popular classification techniques, namely k-nearest neighbor, decision trees, Naive Bayes, artificial neural networks, rule-based and support vector machines were used to develop the predictive environment to classify water quality into understandable terms based on the Overall Index of Pollution. Experimentation was conducted on two types of data sets: synthetic and real. A repeated k-fold cross-validation procedure was followed to design the learning and testing frameworks of the predictive environment. Based on the validation results, it was found that the error rate in defining the true water quality class was 20 and 28%, 11 and 24%, 1 and 38% and 10 and 20% for the k-nearest neighbor, Naive Bayes, artificial neural network and rule-based classifiers for synthetic and real data sets, respectively. The decision tree and support vector machines classifiers were found to be the best predictive models with 0% error rates during automated extraction of the water quality class. This study reveals that data mining techniques have the potential to quickly predict water quality class, provided data given are a true representation of the domain knowledge.
The present work was carried out to assess a water quality index (WQI) of the Loktak Lake, an important wetland which has been under pressure due to the increasing anthropogenic activities. Physicochemical
parameters like temperature (Tem), potential hydrogen (pH), electrical conductivity (EC), turbidity (T), dissolved
oxygen (DO), total hardness (TH), calcium (Ca), chloride (Cl), fluoride (F), sulphate (SO2 4�), magnesium (Mg),
phosphate (PO3 4�), sodium (Na), potassium (K), nitrite (NO2), nitrate (NO3), total dissolved solids (TDS), total carbon (TC), biochemical oxygen demand (BOD), and chemical oxygen demand (COD) were analyzed using standard procedures. The values obtained were compared with the guidelines for drinking purpose suggested by the World Health Organization and Bureau of Indian Standard. The result shows the higher concentration of nitrite in all the location which is beyond the permissible limit. Eleven parameters were selected to derive the WQI for the estimation of water potential for five sampling sites. A relative weight was assigned to each parameter range from 1.46 to 4.09 based on its importance. The WQI values range from 64 to 77 indicating that the Loktak Lake water is not fit for drinking, including both human and animals, even though the people living inside the Lake are using it for drinking purposes. The implementation of WQI is necessary for proper management of the Loktak Lake and it will be a very helpful tool for the public and decision makers to evaluate the water quality of the Loktak Lake for sustainable management.
High resolution measurements were carried out
to understand the short-term (\1 h) variability of surface
water quality parameters in mangrove-dominated Sundarban
Estuarine System of West Bengal, India during flood
phases of spring-neap tidal cycle in a peak monsoon season
August 2014. We observed that tidal propagation of both
phases strongly influenced the water quality properties.
During spring tide salinity, DO, pH, nitrate, phosphate,
silicate, chlorophyll a and phaeopigments concentration
exhibited increasing trends; whereas at neap tide nitrate,
ammonia and chlorophyll a showed decreasing trends.
Average nutrient concentrations were much higher during
neap tide than spring tide. All the measured water quality
parameters varied in every 15-min interval influenced by
the tidal current, mangrove litter fall, re-suspension of
bottom sediment and river runoff. The effect of tidal
amplitude was observed to be the important factor in
determining the variability in most of the water quality
parameters.
The study was carried out to assess some physico-chemical water quality parameters and pollution scenario of the Ichamati river. Water samples were collected
from nine different selected stations at origin of the river
Majhdia to Taki end portion of the Ichamati river during
the pre-monsoon, monsoon and post-monsoon periods. A
seasonal variation in these parameters was observed
throughout the study period and monthly comparisons were
made as monsoon, pre-monsoon and post-monsoon. The
results of the present investigation was undertaken to asses
seasonal and spatial variation in pH, Electrical Conductivity, Turbidity, Salinity, Chlorophyll, DO and Water
Temperature are compared with literature values and
investigation reveals that there is a fluctuation in the physico-chemical characters of the water, this will be due to
ebb and flow and change in the temperature and salinity as
season changes. All parameters except turbidity and conductivity have shown high concentration in pre-monsoonmonsoon and post-monsoon, overall the concentration of
water quality parameters were governed by flushing of
rainfall, river water flow, sea water intrusion runoff from
agricultural fields. Turbidity content in the study area was
higher because the Ichamati river is dynamic zone of lower
stretch. This river only depends on upper stretch rainy
season rain water; no tidal fluctuation but lower stretch of
the river is high tidal fluctuation the salinity is must high
then upper stretch the value of Salinity 3–8.5 ppm that the
parallely fluctuation the huge amount of sediment continuing; the turbidity is very high 600–700 NTU.
KeywordsSeasonal variation� Pre-monsoon� Pollution�
Water quality parameters and post-season
The study aims to assess variations in spatio-temporal characteristics of water quality parameters from three tropical estuaries, namely Muri-Ganga, Saptamukhi, and Hooghly, in the western portion of the Indian Sundarbans. Reliable retrieval of near-surface concentration of water quality parameters such as Chlorophyll-a, SST & TSM from diverse aquatic ecosystems with broad ranges of tropical requirements has always remained a complex issue. In this study, application of Case 2 Regional
Colour Correction (C2RCC) processor has been tested for its accuracy across different bio-optical regimes in both inland and coastal waters. Satellite images for the same period were also collected and analysed using the C2RCC processing sequence to retrieve parameters like the depth of water, surface reflectance, water temperature, inherent optical properties (IOPs),
chlorophyll-a, salinity, total suspended matter (TSM), etc., using the SNAP software. In situ sampling from specific locations
within these estuaries and water quality analysis were conducted for the period 2017–2019. The OLCI retrieved datasets were compared and corroborated with field survey datasets. It was observed that the highest amount of TSM was recorded
at Diamond Harbour during the 2018 pre-monsoon season (301.40 mg/L field-based value and 308.54 mg/L estimated value). Similarly, chlorophyll-a had higher concentrations throughout the monsoon season (3.03 mg m− 3, (field survey), and
2.96 mg m− 3, (estimated) at Fraserganj and Sagar south points. A very good correlation was observed for all seasons for Chl-a (r = 0.829) and TSM (r = 0.924) between the OLCI data and in situ measurements. Higher correlation and significant
‘r’ values highlight the importance of having both field-based as well as remotely-sensed information in understanding any dynamic system in a sustained manner. Results also confirm that the water quality model using OLCI Chl-a and TSM products outperforms conventional techniques. The study demonstrates the efficacy of using Sentinel 3 OCLI data for shallow marine and estuarine remote sensing applications, especially for monitoring TSM and Chl-a concentrations.
Mapping the changes in the deltaic-coastal zone under changing hydrodynamic conditions is crucial for developing a concise picture of coastal vulnerability. The present study provides a comprehensive concept of changing scenarios of rivers in the world's largest delta, Sundarban, using a variety of remotely sensed data and measurements, and relating these changes to hydrodynamic conditions. Bathymetric changes have also been estimated using Landsat imageries, calibrated with bathymetric chart data. We document a substantial dynamic variation between western and eastern sections of the Sundarban tidal rivers, as well as between the northern and southern parts. Banks adjoining the Saptamukhi and Thakuran rivers in the west have accreted by +43.48 km² and +6.13 km² respectively. Net change in the eastern rivers like Matla, Gosaba, and Hariabhanga river systems shows a loss of −51.54 km², –13.92 km², and –13.82 km², respectively, over the last century. Erosion rates have decreased from the southern seafront zone to the northern interior parts due to the low wave exposure, and high tidal range. The accretion rate has increased on the same ground. The depth of these rivers has also changed significantly. For instance, the depth of most sections along the Thakuran river has increased from 5-7 m to about 7–10 m during the period 1987–2016.
Delta shapes are governed by relative dominance of wave, tidal, and fluvial processes, while their coastline changes primarily depend on activation and abandonment of distributary channels. The partly-reclaimed Sundarban Mangrove Wetlands occupy the fluvially abandoned western part of the macro-mesotidal Lower Ganga–Brahmaputra–Meghna Delta (GBMD) in India and Bangladesh. To ascertain the evolution of the planform of this 15,500-km² region over a century, maps and images pertaining to 1904–24 (Survey of India topographical maps), 1967 (Corona space photographs), 2001 (IRS-1D LISS-3 + Pan merged images), and 2015–16 (Resourcesat-2 LISS-4 fmx images) were digitally compared for documenting the changes in the areas of ~250 mangrove-covered and reclaimed tidal islands above the spring high water level. Area change of the individual islands was also studied based on their relative north–south and west–east positions.
The results indicated that while erosion of the estuary margins and the sea facing coastline—up to 40 m/yr—was continuing for decades in the southern islands, intervening channels between the northern islands were getting silted up, especially in the western sector, resulting in land gain. Area change in the central sector mostly tended to be small and erosional. Overall, the total island area & counts changed from 11,903 km² & 253 (1904–24), respectively, through 11,663 km² & 250 (1967), 11,506 km² & 244 (2001), and 11,455 km² & 251 (2015–16). The reduction rate of area, at −4.46 km²/yr, remained noticeably similar across all intervals of mapping / imaging years and projects that the region will lose 3.4 % of its present extent by 2100 if the observed tendencies continue. The trend of area reduction was 2.55-times higher in the western (Indian) segment of the region, than the eastern (Bangladeshi) section. At the level of individual islands, the trends of area change were classified into nine types involving linear and non-linear changes, with dominance of continuous (post-2001) erosion in 48.3 % (68.9 %) of the islands. Conversely, continuous (post-2001) accretion dominates in 15.8% (31.1%) of the islands.
The retrogradation of the southern Sundarban can be ascribed to sediment starvation of the western GBMD due to abandonment of its deltaic distributaries and shelf bypassing of sediments through the Swatch of No Ground submarine canyon. On the other hand, the accretion of the northern interior areas, especially in the west, was mostly related to sediment reworking in a floodtide dominated environment, intervened by reclamation efforts. Factors like relative sea level rise, locational shifts in landfalls of cyclonic storms, and reclamation-related deforestation had little detectable influence on island area changes. As the observed tendencies of area change are likely to continue, planning for the region must integrate the transformations into management and development initiatives.
Monitoring water quality is essential for protecting human health and the environment and controlling water quality. Artificial Intelligence (AI) offers significant opportunities to help improve the classification and prediction of water quality (WQ). In this study, various AI algorithms are assessed to handle WQ data collected over an extended period and develop a dependable approach for forecasting water quality as accurately as possible. Specifically, various machine learning classifiers and their stacking ensemble models were used to classify the WQ data via the Water Quality Index (WQI). The studied classifiers included Support Vector Machine (SVM), Random Forest (RF), Logistic Regression (LR), Decision Tree (DT), CATBoost, XGBoost, and Multilayer Perceptron (MLP). The dataset used in the study included 1679 samples and their meta-data collected over nine years. In addition, precision-recall curves and Receiver Operating Characteristic curves (ROC) were used to assess the performance of the various classifiers. The findings revealed that the CATBoost model offered the most accurate classifier with a percentage of 94.51. Moreover, after applying stacking ensemble models with all classifiers, accuracy reached 100% in various Meta-classifiers. Furthermore, the CATBoost achieved the highest accuracy as a primary gradient boosting algorithm and a meta classifier. Therefore, the boosting algorithm is proposed as a reliable approach for the WQ classification. The analysis presented in this article presents a framework that can support the efforts of researchers working toward water quality improvement using artificial intelligence.
The sea level (SL) at Sundarbans started rising at the onset of the Holocene era, then gradually slowed down at 7,000 years before the present (BP), and then it nearly stabilized at 2,000~3,000yr BP. There was a steady increase in SLR by 1.7 mm yr‐1 throughout the 19th century, but it escalated to 3mm yr‐1 during the final decade of the 20th century (4th IPCC). From 1990 to 2019, thermal expansion of seawater and melting of land ice contributed to about half of the SLR. Average rate of SLR was estimated to vary from 1.4 to 2 mm yr‐1 during the last century. Our estimation, however, is about 4 mm yr‐1 up to the year 2090 after considering the future scenarios. Using tidal gauge data, we have found higher rate of SLR in the study area compared to worldwide trends. On analyzing temporal Landsat images, it was found that the mangroves covered about 1599.9 sq. km in the year 1990 and 1582.4 sq. km in the year 2019. Thus a significant amount (8.5 sq. km) of mangrove area has been lost during the study period. The results point out that SLR, combined with anthropogenic development, has caused the forests' depletion.
The current calculations of water quality index (WQI) were sometimes can be very complex and time-consuming which involves sub-index calculation like BOD and COD, however with the support vector machine (SVM) and least squares support vector machine (LS-SVM) models, the WQI can be predicted immediately using directly measured physical data by using the same predictors used in the numerical approach without any sub-index calculation. There were three main parameters that control the performance of the SVM model however only the type of kernel function was investigated, they were linear, radial basis function (RBF) and polynomial kernel functions. The results of the model were then analysed by using sum squares error (SSE), mean of sum squares error (MSSE) and coefficient of determination (R²). It was found that the best kernel function for the SVM model was polynomial kernel function with R² of 0.8796. Furthermore, the LS-SVM model that trained with correct predictors had higher accuracy with R² of 0.9227 as compared with SVM model that trained with all the predictors with R² of 0.9184. The SSE and MSSE are 74.78 and 1.5594, 1.6454 for LS-SVM and SVM respectively.
This study aims to analyse the shoreline oscillations of three estuarine Islands in Sundarban delta and its impact on mangrove forests around the Islands. Six multi-temporal Landsat images spanning 42 years (1975–2017) have been used in the study. Band ratio was computed to discriminate the water line from the land, which was later digitized. Digital shoreline analysis system (DSAS) was employed for estimation and analysis of the shorelines changes by End point rate (EPR) model and Linear regression rate (LRR) model after laying transects offshore of the baseline. Sea level and topography of the islands have also been analyzed. To assess the mangrove health, time series Normalized Differential Vegetation Index (NDVI) analysis has been performed using the Mann Kendall Tau statistics and Sen’s slope. Mangrove degradation maps were produced from the data and combined with evidences collected from field works. The results point to a very dynamic shoreline ensuing in erosion of mangrove forests while some areas do show encouraging trends due to sustained accretion especially in the southern and eastern parts. Overall erosion is higher than accretion in the Islands. Results show that NDVI has been decreasing along patches that are near to erosion hotspots irrespective of climatic trends. Thus it can be concluded that mangrove forests are under severe stress due to shoreline ingression and sea level rise and not climatic alterations. Going forward this work could provide significant information on the nature of shoreline changes and could assist in sustainable development for Sundarban biodiversity niche management
Water quality has a crucial impact on human health; therefore, water quality index modeling is one of the challenging issues in the water sector. The accurate prediction of water quality index is an essential requisite for water quality management, human health, public consumption, and domestic uses. A comprehensive review as an initial attempt is conducted on existing solutions through data-driven models. In addition, the ensemble Kalman filter is found to be a suitable data assimilation method, which is successfully applied in hydrological variables modeling and other complexes, nonlinear, and chaotic problems. In this study, a new application of ensemble Kalman filter-artificial neural network is proposed to predict water quality index using physicochemical parameters for two commonly pollutant rivers, namely Klang and Langat, in Malaysia. As a further attempt, in order to improve the models’ performance, a new preprocessing technique is adopted as the newly constructed assimilated model. The results confirm that ensemble hybrid based intrinsic time-scale decomposition has reduced root mean square error by 24 % for Klang and 34 % for Langat, respectively, compared with the intrinsic time-scale decomposition-conventional neural network model. Overall, the developed assimilated methodology shows the robustness of the proposed ensemble hybrid model in analyzing water quality index over monthly horizons that experts could evaluate the water quality of rivers more efficiently.
Clean and safe groundwater is the basic guarantee for social and human sustainable development. With the increasing groundwater pollution, it is essential to characterize hydrogeochemistry and assess groundwater quality accurately for water supply purpose. In this study, investigation of groundwater was conducted in the urban area of Xi’an, which has a glorious city history more than 3100 years. 97 groundwater samples were collected from domestic tube wells for physical and chemical analysis. Results showed that groundwater in the study area was predominantly the HCO3-Ca and HCO3-Ca·Mg type, which were controlled by multiple processes of water-rock interaction, evaporation, cation exchange etc. Some samples fall in Zone 4 (mixed type) and Zone 2 (SO4-Na type) in Piper diagram, indicating the complex influence of both rock-water interactions and anthropogenic activities. To assess groundwater quality accurately, an innovative integrated-weight water quality index (IWQI) was proposed by combining objective and subjective weights through additive model. The calculated weights showed that integrated weights balanced the relationship between subjective expertise about impacts of chemical components on human health risk and objective entropy information of ion concentration. The high integrated weight for F⁻ (0.237), NO2-N (0.104) and HCO3⁻ (0.103) indicated their significant influences on groundwater quality. According to the IWQI, overall situation of groundwater in the study area was described as good, while only 9.4% of groundwater samples was of medium to poor quality and unsuitable for drinking. Investigation and historical documents data showed that this poor groundwater quality in the city centre can be attributed to the low terrain, special characteristics of loess deposit, modern pollution in recent decades and the migration of ancient pollutants over one millennia. The sensitive analysis of IWQI indicated the innovative IWQI could describe the overall water quality reliably, stably and correctly, and have the potential suitability for extensive application.
River water quality assessment is one of the most important tasks to enhance water resources management plans. A water quality index (WQI) considers several water quality variables simultaneously. Traditionally WQI calculations consume time and are often fraught with errors during derivations of sub-indices. In this study, 4 standalone (random forest (RF), M5P, random tree (RT), and reduced error pruning tree (REPT)) and 12 hybrid data-mining algorithms (combinations of standalones with bagging (BA), CV parameter selection (CVPS) and randomizable filtered classification (RFC)) were used to create Iran WQI (IRWQIsc) predictions. Six years (2012 to 2018) of monthly data from two water quality monitoring stations within the Talar catchment were compiled. Using Pearson correlation coefficients, 10 different input combinations were constructed. The data were divided into two groups (ratio 70:30) for model building (training dataset) and model validation (testing dataset) using a 10-fold cross-validation technique. The models were evaluated using several statistical and visual evaluation metrics. Result show that fecal coliform (FC) and total solids (TS) had the greatest and least effect on the prediction of IRWQIsc. The best input combinations varied among the algorithms; generally variables with very low correlations displayed weaker performance. Hybrid algorithms improved the prediction power of several of the standalone models, but not all. Hybrid BA-RT outperformed the other models (R² = 0.941, RMSE = 2.71, MAE = 1.87, NSE = 0.941, PBIAS = 0.500). PBIAS indicated that all algorithms, with the exceptions of RT, BA-RT and CVPS-REPT, overestimated WQI values.
Seawater quality status of shore and offshore areas of four selected locations (Visakhapatnam, Kakinada, Ennore, and Pondicherry) along the east coast of India were studied based on the analysis of various water quality parameters (Temperature, pH, Dissolved Oxygen, Biological Oxygen Demand, Suspended Sediment Concentration, Nitrate, Phosphate, and Fecal Coliforms collected during 1993–2014 under the COMAPS program of ICMAM-PD, Ministry of Earth Sciences, Govt. of India. The National Sanitation Foundation Water Quality Index was used to estimate the indices for different seasons. The water quality parameters have strong seasonal and spatial variability along the coast. Higher concentration of BOD and SSC toward shore waters and lower concentration toward offshore is noticed. In Visakhapatnam and Kakinada, the nitrate and phosphate concentration was comparatively higher than Ennore and Pondicherry. The Fecal Coliform counts in the shore waters were significantly high for all the four locations. Computation of Water Quality Index based on different water quality parameters reveals that the water quality along these sites varied from ‘medium’ to ‘good’ depending on the location and the season. The analysis of the data clearly emphasize the need for continuous monitoring of these water quality parameters to maintain and preserve the water quality as well as the related coastal ecosystem productivity of the Indian coast. Further, comprehensive studies are required for the Indian coastal water to determine the relative weightages of various water quality parameters and to develop an optimum WQI index methodology.
The present study investigates the impact of monsoon on meiofaunal and free-living nematode communities of the Sundarban estuarine system (SES) both from taxonomic and functional point of view. In 2013, SES experienced an unusual rainfall event followed by cloud burst event at upper Himalayan regime. Average meiobenthic abundance declined considerably in the study area from early phase of monsoon (EM) (699 ± 1569.4 ind. 10 cm−2) to later one (LM) (437 ± 949.9 ind. 10 cm−2) probably due to high annual rainfall which completely flushed the estuary. Free-living marine nematodes were the dominant group among all other meiobenthic taxa in both phases of monsoon. Nematode community was made up of 49 genera in 22 families. Comesomatidae, Chromadoridae, Linhomoeidae and Xylidae were the richest and most abundant families. During both phases of monsoon, stations, which were represented by fine sediments and high amount of organic carbon, harbored higher meiofaunal densities and nematode diversity with a strong dominance of 1B and 2B trophic guilds of nematodes. Different feeding guilds of nematode would be able to reveal anthropogenic-induced stress, which could be useful in assessing ecological quality of estuarine ecosystems. The present study indicates that climate change mediated unusual monsoonal precipitation may notoriously affect the meiobenthic assemblages in tropical estuaries like SES. Thus, this study could be an important first stepping stone for monitoring the future environmental impact on meiobenthic community in the largest mangrove region of the world.
The spatial and seasonal distribution of trace elements (TEs) (n = 16) in surficial sediment were examined along the Hooghly River Estuary (~ 175 km), India. A synchronous elevation of majority of TEs concentration (mg kg− 1) was encountered during monsoon with the following descending order: Al (67070); Fe (31300); Cd (5.73); Cr (71.17); Cu (29.09); Mn (658.74); Ni (35.89). An overall low and homogeneous concentration of total Hg (THg = 17.85 ± 4.98 ng g− 1) was recorded in which methyl mercury (MeHg) shared minor fraction (8–31%) of the THg. Sediment pollution indices, viz. geo-accumulation index (Igeo) and enrichment factor (EF) for Cd (Igeo = 1.92–3.67; EF = 13.83–31.17) and Ba (Igeo = 0.79–5.03; EF = 5.79–108.94) suggested high contamination from anthropogenic sources. From factor analysis it was inferred that TEs primarily originated from lithogenic sources. This study would provide the latest benchmark of TE pollution along with the first record of MeHg in this fluvial system which recommends reliable monitoring to safeguard geochemical health of this stressed environment.
Observations were carried out along the western coastal Bay of Bengal, to examine the physical, chemical and biological parameters during the summer monsoon particularly when the rivers of India are in flood condition and discharge large quantities of fresh water into the Bay of Bengal. River discharge has a significant impact on plankton biomass in the coastal Bay of Bengal. High concentrations of nutrients were observed at the Southern coastal Bay of Bengal (SCB), which were associated with high suspended matter (SPM) that limits the phytoplankton biomass (Chl-a). In contrast, the Northern coastal Bay of Bengal (NCB) was characterized by low nutrients and SPM coupled with higher phytoplankton biomass and zooplankton abundance. Therefore primary production in the coastal Bay of Bengal appears to be controlled by light availability in the water column more so than by nutrients, particularly during the peak river discharge. Relatively higher zooplankton biomass and abundance have been found in NCB than in SCB. Zooplankton biomass showed a strong linear relationship with phytoplankton biomass in NCB. On the other hand, a strong linear relationship was observed with particulate organic carbon (POC) in the SCB.
High resolution measurements were carried out to understand the short-term (<1 h) variability of surface water quality parameters in mangrove-dominated Sundarban Estuarine System of West Bengal, India during flood phases of spring-neap tidal cycle in a peak monsoon season August 2014. We observed that tidal propagation of both phases strongly influenced the water quality properties. During spring tide salinity, DO, pH, nitrate, phosphate, silicate, chlorophyll a and phaeopigments concentration exhibited increasing trends; whereas at neap tide nitrate, ammonia and chlorophyll a showed decreasing trends. Average nutrient concentrations were much higher during neap tide than spring tide. All the measured water quality parameters varied in every 15-min interval influenced by the tidal current, mangrove litter fall, re-suspension of bottom sediment and river runoff. The effect of tidal amplitude was observed to be the important factor in determining the variability in most of the water quality parameters.
Sagar coastline is a major attraction site for tourist and also source of income for the local peoples. However shoreline has been changing due to erosion. The shoreline position is difficult to predict but the trend of erosion or accretion can be determinate by statistical techniques. The study aims to assess the shoreline changes and prediction in Sagar Island, a delta of Ganges, situated in West Bengal, India. This study sought to find the trend of shoreline changes and factors. Shoreline can be detected by using PCA and non-directional edge techniques from Landsat images. The shoreline mapping of Sagar Island during (1975–2015) using geospatial techniques. The present study focuses the shoreline change and in future prediction from satellite derived multi-temporal Landsat MSS, Landsat TM, Landsat ETM+, Landsat OLI data using GIS; it is used to determinate or to estimate the change rate of shoreline in Sagar Island by End Point Rate, and Linear Regression models.
This paper proposes a method for the real-time prediction of water quality index by excluding the biological oxygen demand and chemical oxygen demand, which are not measured in real-time, from the model inputs. In this study, feedforward artificial neural networks are used to model the water quality index in Perak River Basin Malaysia due to its capability in modelling nonlinear systems. The results show that the developed single feed forward neural network model can predict water quality index very well with the coefficient of determination R² and mean squared error (MSE) of 0.9090 and 0.1740 on the unseen validation data respectively. In addition to that, the aggregation of multiple neural networks in predicting the water quality index further improves the prediction performance on the unseen validation data. Forward selection and backward elimination selective combination methods are used to combine multiple neural networks and both methods leads to 6 and 5 networks being combined with R² and MSE of 0.9340, 0.9270 and 0.1156, 0.1256 respectively. It is clearly shown that combining multiple neural networks does improve the performance for water quality index prediction.
The deteriorating quality of natural water resources like lakes, streams and estuaries, is one of the direst and most worrisome issues faced by humanity. The effects of un-clean water are far-reaching, impacting every aspect of life. Therefore, management of water resources is very crucial in order to optimize the quality of water. The effects of water contamination can be tackled efficiently if data is analyzed and water quality is predicted beforehand. This issue has been addressed in many previous researches, however, more work needs to be done in terms of effectiveness, reliability, accuracy as well as usability of the current water quality management methodologies. The goal of this study is to develop a water quality prediction model with the help of water quality factors using Artificial Neural Network (ANN) and time-series analysis. This research uses the water quality historical data of the year of 2014, with 6-minutes time interval. Data is obtained from the United States Geological Survey (USGS) online resource called National Water Information System (NWIS). For this paper, the data includes the measurements of 4 parameters which affect and influence water quality. For the purpose of evaluating the performance of model, the performance evaluation measures used are Mean-Squared Error (MSE), Root Mean-Squared Error (RMSE) and Regression Analysis. Previous works about Water Quality prediction have also been analyzed and future improvements have been proposed in this paper.