Integrating Digital Twins and Artificial Intelligence Multi-Modal Transformers into Water Resource Management: Overview and Advanced Predictive Framework DOI Creative Commons
Toqeer Ali Syed, Muhammad S. Khan, Salman Jan

et al.

AI, Journal Year: 2024, Volume and Issue: 5(4), P. 1977 - 2017

Published: Oct. 25, 2024

Various Artificial Intelligence (AI) techniques in water resource management highlight the current methodologies’ strengths and limitations forecasting, optimization, control. We identify a gap integrating these diverse approaches for enhanced prediction management. critically analyze existing literature on artificial neural networks (ANNs), deep learning (DL), long short-term memory (LSTM) networks, machine (ML) models such as supervised (SL) unsupervised (UL), random forest (RF). In response, we propose novel framework that synergizes into unified, multi-layered model incorporates digital twin multi-modal transformer approach. This integration aims to leverage collective advantages of each method while overcoming individual constraints, significantly enhancing accuracy operational efficiency. paper sets foundation an innovative twin-integrated solution, focusing reviewing past works precursor detailed exposition our proposed subsequent publication. advanced approach promises redefine demand forecasting contribute global sustainability efficiency use.

Language: Английский

Sustainability assessment of wastewater treatment techniques in urban areas of Iraq using multi-criteria decision analysis (MCDA) DOI Creative Commons

Isam I. Omran,

Nabeel Hameed Al-Saati,

Hyam H. Al-Saati

et al.

Water Practice & Technology, Journal Year: 2021, Volume and Issue: 16(2), P. 648 - 660

Published: Feb. 18, 2021

Abstract Sustainable development is based on environmental, social, economic, and technical dimensions. In this study, the sustainability of wastewater treatment techniques in urban areas Iraq was assessed using a multi-criteria decision analysis (MCDA)/the weighted sum model (WSM). The performed 13 operating plants 10 provinces, Iraq, questionnaire sheet with assistance 52 specialists Ministry Municipalities Public Works, Iraq. Four types (Conventional Treatment, Oxidation Ditches, Aeration Lagoons, membrane bio-reactor (MBR)) were assessed. dimensions represented by 11, 5, 7, 4 indicators, respectively. main results study indicate that MBR recorded highest total importance; order importance from to lowest was: > Ditches Lagoons Conventional Treatment. environmental dimension proved its dominance four studied techniques' as it maximum contribution sustainability. While least sustainability, Environmental Dimension Economic Social Technical Dimension.

Language: Английский

Citations

41
Performance evaluation of a novel improved slime mould algorithm for direct current motor and automatic voltage regulator systems DOI
Davut İzci, Serdar Ekinci, H. L. Zeynelgil

et al.

Transactions of the Institute of Measurement and Control, Journal Year: 2021, Volume and Issue: 44(2), P. 435 - 456

Published: Aug. 19, 2021

This study deals with the controlling speed of a direct current (DC) motor via fractional order proportional–integral–derivative (FOPID) controller and maintaining terminal voltage level an automatic regulator (AVR) plus second derivative (PIDD 2 ) controller. To adjust parameters those controllers, novel improved slime mould algorithm (ISMA) is proposed. The latter metaheuristic developed in this work. proposed aims to improve original SMA terms exploration aid modified opposition-based learning scheme exploitation Nelder–Mead simplex search method. A time domain objective function, which includes response specifications steady state error maximum overshoot along rise settling times, used as performance index design FOPID controller-based DC system PIDD AVR system. approaches for both systems are assessed through frequency simulations statistical tests show greater algorithm. Further this, efficacy compared other available effective literature. extensive comparative results demonstrate method be superior state-of-the-art control systems.

Language: Английский

Citations

41
Multi-objective optimal allocation of regional water resources based on slime mould algorithm DOI
Xian Wu, Zhaocai Wang

The Journal of Supercomputing, Journal Year: 2022, Volume and Issue: 78(16), P. 18288 - 18317

Published: June 6, 2022

Language: Английский

Citations

37
LSMA-TLBO: A hybrid SMA-TLBO algorithm with lévy flight based mutation for numerical optimization and engineering design problems DOI
Tanmay Kundu, Harish Garg

Advances in Engineering Software, Journal Year: 2022, Volume and Issue: 172, P. 103185 - 103185

Published: July 28, 2022

Language: Английский

Citations

32
Improved slime mould algorithm with elitist strategy and its application to structural optimization with natural frequency constraints DOI
A. Kaveh, Kiarash Biabani Hamedani,

Mohammad Kamalinejad

et al.

Computers & Structures, Journal Year: 2022, Volume and Issue: 264, P. 106760 - 106760

Published: Feb. 11, 2022

Language: Английский

Citations

29
Gaussian bare-bone slime mould algorithm: performance optimization and case studies on truss structures DOI Open Access

Shubiao Wu,

Ali Asghar Heidari, Siyang Zhang

et al.

Artificial Intelligence Review, Journal Year: 2023, Volume and Issue: 56(9), P. 9051 - 9087

Published: Jan. 20, 2023

Language: Английский

Citations

20
An evolutionary hybrid method based on particle swarm optimization algorithm and extreme gradient boosting for short-term streamflow forecasting DOI
Hüseyin Çağan Kılınç, Bülent Haznedar, Furkan Ozkan

et al.

Acta Geophysica, Journal Year: 2024, Volume and Issue: 72(5), P. 3661 - 3681

Published: Feb. 25, 2024

Language: Английский

Citations

8
Artificial Intelligence for Water Consumption Assessment: State of the Art Review DOI Creative Commons

Almando Morain,

Nivedita Ilangovan,

Christopher Delhom

et al.

Water Resources Management, Journal Year: 2024, Volume and Issue: 38(9), P. 3113 - 3134

Published: April 25, 2024

Abstract In recent decades, demand for freshwater resources has increased the risk of severe water stress. With growing prevalence artificial intelligence (AI), many researchers have turned to it as an alternative linear methods assess consumption (WC). Using PRISMA (Preferred Reporting Items Systematic Reviews and Meta-Analyses) framework, this study utilized 229 screened publications identified through database searches snowball sampling. This introduces novel aspects AI's role in assessment by focusing on innovation, application sectors, sustainability, machine learning applications. It also categorizes existing models, such standalone hybrid, based input, output variables, time horizons. Additionally, classifies learnable parameters performance indexes while discussing AI models' advantages, disadvantages, challenges. The translates information into a guide selecting models WC assessment. As no one-size-fits-all model exists, suggests utilizing hybrid alternatives. These offer flexibility regarding efficiency, accuracy, interpretability, adaptability, data requirements. They can address limitations individual leverage strengths different approaches, provide better understanding relationships between variables. Several knowledge gaps were identified, resulting suggestions future research.

Language: Английский

Citations

6
Multi-threshold image segmentation based on an improved whale optimization algorithm: A case study of Lupus Nephritis DOI
Jinge Shi, Yi Chen, Zhennao Cai

et al.

Biomedical Signal Processing and Control, Journal Year: 2024, Volume and Issue: 96, P. 106492 - 106492

Published: June 7, 2024

Language: Английский

Citations

6
Predicting Rainfall-Induced Soil Erosion Based on a Hybridization of Adaptive Differential Evolution and Support Vector Machine Classification DOI Open Access
Tuan Vu Dinh,

Hieu Nguyen,

Xuan-Linh Tran

et al.

Mathematical Problems in Engineering, Journal Year: 2021, Volume and Issue: 2021, P. 1 - 20

Published: Feb. 20, 2021

Soil erosion induced by rainfall is a critical problem in many regions the world, particularly tropical areas where annual amount often exceeds 2000 mm. Predicting soil challenging task, subjecting to variation of characteristics, slope, vegetation cover, land management, and weather condition. Conventional models based on mechanism processes generally provide good results but are time-consuming due calibration validation. The goal this study develop machine learning model support vector (SVM) for prediction. SVM serves as main prediction machinery establishing nonlinear function that maps considered influencing factors accurate predictions. In addition, order improve accuracy model, history-based adaptive differential evolution with linear population size reduction population-wide inertia term (L-SHADE-PWI) employed find an optimal set parameters SVM. Thus, proposed method, named L-SHADE-PWI-SVM, integration metaheuristic optimization. For purpose training testing dataset consisting 236 samples Northwest Vietnam collected 10 factors. includes 90% original dataset; rest reserved assessing generalization capability model. experimental indicate newly developed L-SHADE-PWI-SVM method competitive predictor superior performance statistics. Most importantly, can achieve high classification rate 92%, which much better than backpropagation artificial neural network (87%) radial basis (78%).

Language: Английский

Citations

38