ArticlePublisher preview available

Smart sustainable architecture: leveraging machine learning for adaptive digital design and resource optimization

Authors:
Main Abushaikha at Amman Arab University
Main Abushaikha
Read publisher preview
Download citation
To read the full-text of this research, you can request a copy directly from the author.

Abstract and Figures

This study investigates the application of the Fruit Fly Optimization Algorithm (FOA) in enhancing the predictive performance of the Light Gradient Boosting Machine (LightGBM) model for smart sustainable architecture. Key features, including Energy Consumption, Water Usage, Material Cost, CO2 Emissions, and Design Flexibility, were selected using FOA to optimize the model’s predictive accuracy. The FOA-based feature selection significantly improved across all performance metrics: Accuracy increased from 0.85 to 0.88, Precision from 0.80 to 0.84, Recall from 0.78 to 0.82, and the F1-Score from 0.79 to 0.83. Moreover, the Root Mean Square Error (RMSE) decreased from 0.25 to 0.22, while the Area Under the Curve (AUC) improved from 0.76 to 0.8625. These findings underscore the effectiveness of FOA in refining feature selection, thereby enhancing the efficiency and reliability of predictive models in sustainable architectural design. The study highlights the potential of advanced optimization algorithms in developing more adaptive, resource-efficient, and sustainable architectural solutions.
Figures - available from: Asian Journal of Civil Engineering
This content is subject to copyright. Terms and conditions apply.
A preview of this full-text is provided by Springer Nature.
Learn more
Content available from Asian Journal of Civil Engineering
This content is subject to copyright. Terms and conditions apply.
Vol.:(0123456789)
Asian Journal of Civil Engineering (2025) 26:147–158
https://doi.org/10.1007/s42107-024-01180-z
RESEARCH
Smart sustainable architecture: leveraging machine learning
foradaptive digital design andresource optimization
Ma’inAbu‑shaikha1
Received: 3 September 2024 / Accepted: 20 September 2024 / Published online: 26 September 2024
© The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024
Abstract
This study investigates the application of the Fruit Fly Optimization Algorithm (FOA) in enhancing the predictive perfor-
mance of the Light Gradient Boosting Machine (LightGBM) model for smart sustainable architecture. Key features, includ-
ing Energy Consumption, Water Usage, Material Cost, CO2 Emissions, and Design Flexibility, were selected using FOA to
optimize the model’s predictive accuracy. The FOA-based feature selection significantly improved across all performance
metrics: Accuracy increased from 0.85 to 0.88, Precision from 0.80 to 0.84, Recall from 0.78 to 0.82, and the F1-Score
from 0.79 to 0.83. Moreover, the Root Mean Square Error (RMSE) decreased from 0.25 to 0.22, while the Area Under the
Curve (AUC) improved from 0.76 to 0.8625. These findings underscore the effectiveness of FOA in refining feature selec-
tion, thereby enhancing the efficiency and reliability of predictive models in sustainable architectural design. The study
highlights the potential of advanced optimization algorithms in developing more adaptive, resource-efficient, and sustainable
architectural solutions.
Keywords Smart· Sustainable architecture· Fruit Fly Optimization Algorithm (FOA)· LightGBM· Feature selection·
Machine learning· Energy efficiency· Sustainable design
Introduction
Integrating AI applications in sustainable building, housing,
and planning has revolutionized the architectural landscape
by enabling more adaptive, efficient, and resource-conscious
designs. In sustainable building, AI-driven systems are
employed to optimize energy consumption, enhance mate-
rial efficiency, and predict the environmental impact of con-
struction activities, leading to greener and more resilient
structures. Regarding housing and planning, AI facilitates
the creation of intelligent models that analyze urban pat-
terns, forecast population growth, and optimize land use,
ensuring that housing developments are sustainable and
well-integrated into existing urban ecosystems. This tech-
nological advancement allows for real-time adjustments
to design and resource allocation, ensuring that the built
environment meets both current needs and future challenges
more sustainably (Abid etal., 2024; Abusaleh, 2024; Al-
Haddad etal., 2024; Hussein etal., 2024).
Smart, sustainable architecture is a crucial element of
contemporary urban development, to create environmentally
friendly and resource-efficient buildings and cities. Integrat-
ing machine learning in the design and optimization pro-
cesses can significantly enhance the sustainability and effi-
ciency of architectural projects. By incorporating advanced
technologies such as quantum convolutional neural networks
(Cong etal., 2019), fuzzy and interval AHP approaches
(Milošević etal., 2021), and extensive data-driven energy
presumption services (Anthony etal., 2019), architects and
urban planners can make informed decisions that prioritize
sustainability and resource optimization.
Sustainable architecture, also known as green archi-
tecture, focuses on designing buildings that are energy-
efficient and have minimal impact on the environment
(Kadaei etal., 2021). Integrating sustainability principles
into architectural projects, such as using smart materi-
als and energy-efficient systems, is essential for creating
buildings that align with environmental goals. Addition-
ally, the development of smart and sustainable buildings,
like those incorporating cloud energy storage systems
* Ma’in Abu-shaikha
m.abushaikha@aau.edu.jo
1 Department ofArchitecture Engineering, College
ofEngineering, Amman Arab University, Amman, Jordan
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
... Improving the prognosis, manufacturing, and planning, it helps us to construct better, less parochial, and more sustainable solutions. [1]. Utility scale solar photovoltaic (PV) system constitutes the primary means of harnessing solar energy as a renewable energy form. ...
... Utility scale solar photovoltaic (PV) system constitutes the primary means of harnessing solar energy as a renewable energy form. Nevertheless, more variability like solar irradiance, temperature fluctuations and degradation of equipment has been shown to decrease the efficiency of such systems [1]. To this end, new advanced analytical instruments to solve these issues are required with the main focus on creating a system that will maintain maximum performance in more complex circumstances as a primary prerequisite. ...
... Accordingly, the dataset provides the basis for the ML approaches to mitigate PV system degradation performance loss factors. It is an open renewable energy dataset [1], that has the basic characteristics defining the most important characteristics of solar energy. The availability data includes some elements such as irradiance, ambient temperature, panel efficiency, the energy outputs, and system maintenance costs, some of which are the main factors to determine the PV system reliability. ...
Enhancing Predictive Accuracy of Renewable Energy Systems and Sustainable Architectural Design Using PSO Algorithm
Article
Full-text available
  • Jan 2025
This paper formulates and examines the approach of integrating PSO into the tune of DNNs for boosting the predictive capability in renewable energy systems and green building designs. The PSO method was then employed to select Key features such as; Solar Irradiance, Ambient Temperature, Panel Efficiency and Energy Output. The PSO-based feature selection resulted in significant enhancements across a set of four metrics, there was an improvement in accuracy from a previous 0.82 to 0.87, precision from the previous 0.78 to 0.83, as well as recall from the previous 0.76 to 0.81, and the F1-Score from a previous 0.77 to the current score of 0.82. Moreover, the RMSE values reduced from 0.27 to 0.23, and the AUC values enriched from 0.74 to 0.85. Thus, the results of the current study support PSO’s role in improving feature selection, which, in return, improves the predictive models of energy management. The paper presented emphasizes the possibility of the use of enhanced optimization algorithms in enhancing the best performing, less resource-intensive, and environmentally friendly energy solutions in architecture.
View
... Machine learning has greatly optimized energy functional results inside space by analyzing complex data on building performance, materials, and preferred interior design options. With this approach, the designer has the facility to optimize resources with logical decisions for improvement in indoor comfort while offering aesthetic appeal (Abu-shaikha, 2024;Arabasy et al., 2024;Bamdad Masouleh, 2018;Kaveh, 2024;Kaveh & Ghazaan, 2014a, 2014b. Coupled with design approaches, these techniques allow for more robust and adaptable housing projects that meet the principles of sustainable building and further efficiency in urban planning (Lu et al., 2022;Yang, 2011). ...
... This would greatly improve customer satisfaction and potentially limit the chances of costly revisions during the construction phase. When coupled with machine learning algorithms, these technologies allow designers to create highly personalized and adaptive environments capable of responding to users' needs in realtime (Abu-shaikha, 2024;Arabasy et al., 2024). ...
... This amalgamation of algorithms is unprecedented in this context since limited research has utilized both LightGBM and ECBO for sustainable housing initiatives. Consequently, this research paves the way for enhancing effective decision-making in sustainable design (Abu-Shaikha, 2024;Bisharah, 2024). Subsequent research may concentrate on augmenting the efficiency of the ECBO method and investigating alternative machine-learning models to improve scalability and precision in more intricate design contexts. ...
Metaheuristic machine learning for optimizing sustainable interior design: enhancing aesthetic and functional rehabilitation in housing projects
Article
Full-text available
  • Dec 2024
The paper investigates the amalgamation of LightGBM and Enhanced Colliding Bodies Optimization (ECBO) to establish a resilient framework for sustainable interior design optimization in residential projects. The main goal is to harmonize aesthetic appeal, functionality, and energy efficiency by applying modern machine learning and metaheuristic optimization methods. LightGBM was utilized for predictive modeling of essential design outcomes, achieving good prediction accuracy, with R-squared values of 0.892 for energy savings, 0.839 for functional enhancements, and 0.782 for aesthetics. Critical elements, including sustainable materials, project budget, and energy efficiency ratings, surfaced as pivotal influences on design improvements. The ECBO further refined these design elements, yielding a 28.13% enhancement in aesthetic evaluations, a 22.86% gain in functionality, a 41.56% advancement in energy savings, and a 29.17% decrease in carbon footprint. Compared to conventional algorithms such as Particle Swarm Optimization and Genetic Algorithm, the ECBO exhibited enhanced convergence velocity and solution efficacy. This study presents a thorough, data-centric methodology for sustainable interior design, offering an efficient framework for attaining many design objectives in housing rehabilitation.
View
Integrating machine learning in digital architecture: enhancing sustainable design and energy efficiency in urban environments
Article
Full-text available
  • Nov 2024
The following work applies metaheuristic optimization algorithms—PSO, ACO, Genetic Algorithm, and Enhanced Colliding Bodies Optimization (ECBO)—to the optimum design of a sustainable building with respect to prominent metrics such as energy savings, improvement in indoor comfort, and reduction in carbon footprint. These algorithms are applied to a wide dataset that includes variable intensity factors such as window-to-wall variation ratio, HVAC efficiency, and integration of renewable energy. Results also proved that PSO is the fittest strategy to balance energy efficiency and sustainability, with the highest energy savings of 24.1%. Besides, PSO wasn’t just the fastest convergence rate; it also obtained a Platinum LEED certification. ACO was second in order of magnitude, with high energy savings and carbon footprint reduction values, and also obtained the Platinum LEED certificate. The results obtained for GA were positive from the occupant comfort point of view but were slower in terms of energy savings and convergence speed. In contrast, ECBO had the slowest convergence and lowest energy savings, demonstrating the limitation of the application of ECBO for large-scale multi-objective optimization. These results imply that PSO and ACO would be suitable for practical applications linked to urban sustainable design, while GA and ECBO are more suited for niche applications. The obtained results can provide useful guidelines in developing more energy-efficient and sustainable designs for architects, urban planners, and policymakers.
View
Enhancing preservation outcomes for architectural heritage buildings through machine learning-driven future search optimization
Article
Full-text available
  • Jul 2024
Architectural heritage represents an invaluable tapestry of human civilization’s artistic, cultural, and historical milestones. As urbanization and societal dynamics evolve, preserving these architectural marvels becomes increasingly imperative. Drawing upon a meticulously curated dataset of UNESCO World Heritage Sites, we introduce a novel machine-learning model that harnesses the capabilities of XGBoost in conjunction with Future Search Optimization (FSO). Our findings reveal that the XGBoost-FSO hybrid accurately identifies and categorizes at-risk heritage sites. From an architectural preservation perspective, the transformative potential of such predictive analytics is immense. They enable timely interventions, ensuring that heritage structures, each with its unique narrative and significance, endure the tests of time. By bridging the realms of technology and architectural heritage, this research underscores the promise of data-driven strategies in championing the cause of global heritage preservation. Through this interdisciplinary approach, we envision a future where technology acts as the vanguard, safeguarding the architectural legacies of yesteryears for generations to come.
View
Forecasting and managing urban futures: machine learning models and optimization of urban expansion
Article
Full-text available
  • Jul 2024
This paper presents a novel method for predicting and controlling urban growth by combining convolutional neural networks (CNN) with Spider Monkey Optimization (SMO) to efficiently use their combined capabilities. This strategy utilizes sophisticated machine learning algorithms to forecast urban development patterns, while optimization technologies enhance these forecasts by including sustainable urban design ideas. Integration plays a crucial role in tackling the difficulties presented by fast urbanization, including issues related to land use, resource administration, and environmental sustainability in the fields of civil and architectural engineering. The study employs large datasets to assess the efficacy of CNN models in detecting urban expansion patterns and enhances these models with optimization scenarios encompassing land use, traffic flow, electricity efficiency, water resources, and waste management, all with the goal of enhancing urban sustainability. The findings demonstrate a significant improvement in the precision of predictions and the ability to maintain positive results, highlighting the crucial role of integrating machine learning and optimization in urban planning methodologies. This method not only provides urban planners and politicians with strong and effective tools for making decisions but also creates opportunities for implementing creative and sustainable solutions for urban growth. The results provide a substantial contribution to the existing urban planning literature by demonstrating the actual use of these technologies in regulating urban expansion. This will stimulate more study in this rapidly evolving subject.
View
Enhancing building sustainability through aerodynamic shading devices: an integrated design methodology using finite element analysis and optimized neural networks
Article
Full-text available
  • Apr 2024
In the quest for sustainable building solutions, attention has increasingly turned to innovative structural designs and technologies that minimize environmental impact. Within this context, this study explores the integration of advanced sun-breakers and aerodynamic features into building design. Recent developments in shading devices are analysed to optimize the use of airflow in aerodynamic performance. Due to the computational intensity of Finite Element Analysis (FEA), an Artificial Neural Network (ANN) based on Stochastic Gradient Descent (ANN-SGD) is employed as a substitute for such limitations. A predictive model was developed to estimate fluid flow fluent full iteration range variables which included wind velocity, static pressure, air density, and turbulent kinetic energy. These predictions are initially validated using a first short run of workbench simulations then the ANN-SGD model is applied to expedite the computational process. The adopted ANN-SGD model exhibited high regression accuracy that was evidenced by a Root Mean Square Error (RMSE) of 4.66% while the Coefficient of Determination (R²) had scored a highest score of 0.995 in addition to the Coefficient of Variation of the RMSE (CVRMSE) scoring 8.33%. The findings of this work offer future development perspectives and strategies in building sustainability and aerodynamical shading devices’ design.
View
Machine learning-driven sustainable urban design: transforming Singapore's landscape with vertical greenery
Article
Full-text available
  • Apr 2024
Integrating state-of-the-art technology is now essential in pursuing environmentally sustainable urban development. This research focuses on Singapore's lush vertical landscape and explores the potential of machine learning. Specifically, Convolutional Neural Networks (CNN) to enhance sustainable urban design. The CNN-MOA model was created by incorporating the Mayfly Optimization Algorithm (MOA) to improve the performance of the CNN-based model further. Without the Mayfly Optimization Algorithm, the convolutional neural network (CNN) achieved impressive results. It had a total accuracy of 0.977725, a weighted average precision of 0.977679, a weighted average recall of 0.977725, a weighted average F1-Score of 0.977621, and a macro average precision of 0.953458. These measures unequivocally demonstrated CNN's ability to process and analyze data about urban design effectively. A significant advancement occurred when the fusion of the CNN model with the Mayfly Optimization Algorithm resulted in the creation of the CNN-MOA hybrid. The installation led to a substantial enhancement in the model's performance. The results revealed a weighted average accuracy of 99.98%, recall of 99.92%, macro average F1-Score of 99.95%, weighted average precision of 99.98%, weighted average recall of 99.98%, and weighted average F1-Score of 99.98%. Each of these indicators exhibited exceptional performance. The model's ability to comprehend and evaluate intricate urban design features has been significantly enhanced. These findings demonstrate significant prospects for the sustainable development of metropolitan areas, particularly in Singapore, as observed by urban planners. Combining machine learning with the Mayfly Optimization Algorithm offers a powerful method for enhancing the integration of vertical greenery and improving overall urban design. These developments align with Singapore's commitment to sustainable urban development, contributing to creating environmentally friendly and visually appealing cities. This research emphasizes the transformative potential of machine learning-powered solutions in shaping the future of sustainable and ecologically harmonious urban architecture.
View
Research on power system small signal stability analysis and correction based on LightGBM algorithm
Article
Full-text available
  • Jan 2024
  • ELECTR ENG
This paper proposes a method for the small signal stability analysis and correction of power system based on Light Gradient Boosting Machine (LightGBM). Taking the load power, branch power, and generator power as inputs, the minimum damping ratio is output to build the mapping relationship between input and output. A small signal stability analysis model is established to assess the minimum damping ratio of the system, and the influence of noise on the accuracy of assessment results is also considered. The damping ratio sensitivity of generator is estimated based on LightGBM method, and the approximate sensitivity optimization model of the generator damping ratio is established when the system is weakly damped. The outputs of generators are adjusted according to the optimization model to correct the minimum damping ratio to enhance the system’s stability and finally estimate the modified minimum damping ratio by LightGBM algorithm. Test results on 3-machine 9-node and 10-machine 39-node systems indicate that the proposed method is hardly prone to over-fitting under noise interference with better robustness and could maintain better performance in assessing and correcting the small signal stability of the power system.
View
A REVIEW OF SMART GREEN BUILDING TECHNOLOGIES: INVESTIGATING THE INTEGRATION AND IMPACT OF AI AND IOT IN SUSTAINABLE BUILDING DESIGNS
Article
Full-text available
  • Jan 2024
This scholarly paper delves into the dynamic realm of smart green building technologies, focusing on the integration and impact of Artificial Intelligence (AI) and the Internet of Things (IoT) within the sphere of sustainable architecture. The study is anchored in the background of evolving green building principles, underscored by the burgeoning rise of smart technologies that are reshaping modern architectural practices. Aimed at comprehensively understanding the transformative role of AI and IoT in enhancing building performance and sustainability, the paper adopts a ethodological approach centered on an extensive literature review and qualitative analysis. It meticulously examines the synergy between AI and IoT, their implementation challenges, environmental and social impacts, and the economic implications of investing in such technologies.The main findings reveal that the integration of AI and IoT significantly elevates energy efficiency, optimizes building performance, and contributes to environmental sustainability. The study highlights innovative IoT solutions in building management, demonstrating their effectiveness in creating more efficient and sustainable living spaces. However, it also identifies barriers to the adoption of these technologies, including economic constraints and the need for skilled professionals.Conclusively, the paper recommends a multi-faceted approach to overcome these challenges, emphasizing policy interventions, educational initiatives, and the development of cost-effective green building technologies. The study underscores the need for collaborative efforts from various stakeholders to advance sustainable architecture and building management.This paper provides a comprehensive exploration of the integration of AI and IoT in sustainable building designs, offering insights into their potential to revolutionize the construction industry and pave the way for sustainable urban development. Keywords: Smart Green Building Technologies, Artificial Intelligence, Internet of Things, Sustainable Architecture, Energy Efficiency, Building Performance.
View
Digital twins, big data governance, and sustainable tourism
Article
Full-text available
  • Nov 2023
  • Ethics Inform Tech
The rapid adoption of digital technologies has revolutionized business operations and introduced emerging concepts such as Digital Twin (DT) technology, which has the potential to predict system responses before they occur, making it an attractive option for smart and sustainable tourism. However, implementing DT software systems poses significant challenges, including compliance with regulations and effective communication among stakeholders, and concerns surrounding security, privacy, and trust with the use of big data. To address these challenges, this paper proposes a documentation framework for architectural decisions (DFAD) that applies the concept of big data governance to the digital system. The framework aims to ensure accountability, transparency, and trustworthiness while adhering to rules and regulations. To demonstrate its applicability, a case study and three case scenarios on the potential use of Mobile Positioning Data (MPD) in Indonesia for DT technology in smart and sustainable tourism were examined. The paper highlights the benefits of DFAD in shaping stakeholder communication and human–machine interactions while leveraging the potential of MPD to measure tourism statistics by Statistics Indonesia since 2016. Not only the documentation framework promotes compliance with regulations, but it also facilitates effective communication among stakeholders and enhances trust and transparency in the use of big data in DT technology for smart and sustainable tourism. This paper emphasizes the importance of effective big data governance and its potential to promote sustainable tourism practices. The multidisciplinarity approach on political science, software engineering, tourism, and official statistics provides an opportunity for academic contribution and decision-making processes.
View
View
View
Techniques to Predict Employee Attrition Using Optimized Levy Fruit Fly Optimization Algorithm
Article
  • Mar 2024
Competent people are a valuable asset for strong businesses. The issue of retaining competent staff with expertise poses a challenge to business owners. Employee attrition may be costly for businesses since it takes a lot to compensate for their experience and efficiency. As a result, this study proposes a novel model for predicting employee attrition utilizing machine learning techniques. The datasets are collected from Kaggle resource. The dataset has been pre-processed using standard scalar with Label Encoding method. The dataset has been trained with ML algorithm. The best features are selected by using modified genetic algorithm (MGA). The classification has been done with KNN, Gradient Boosting and Extra tree classifier. Finally, the attrition prediction using optimized levy fruit fly optimization (OLFFO). The experimental results are compared with ML algorithms with classification metrics (Accuracy, Precision, recall and f-measure).
View