Using multiple machine learning techniques to enhance the performance prediction of heat pump-driven solar desalination unit

Solar stills are sustainable devices that generate freshwater through solar-powered desalination. However, traditional solar stills often struggle with variability in environmental conditions. This study proposes a predictive model using machine learning (ML) techniques to improve the accuracy and a...

Full description

Saved in:
Bibliographic Details
Main Authors: Swellam W. Sharshir, Abanob Joseph, Mohamed S. Abdalzaher, A.W. Kandeal, A.S. Abdullah, Zhanhui Yuan, Huizhong Zhao, Mahmoud M. Salim
Format: Article
Language:English
Published: Elsevier 2025-01-01
Series:Desalination and Water Treatment
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1944398624204264
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850077248402489344
author Swellam W. Sharshir
Abanob Joseph
Mohamed S. Abdalzaher
A.W. Kandeal
A.S. Abdullah
Zhanhui Yuan
Huizhong Zhao
Mahmoud M. Salim
author_facet Swellam W. Sharshir
Abanob Joseph
Mohamed S. Abdalzaher
A.W. Kandeal
A.S. Abdullah
Zhanhui Yuan
Huizhong Zhao
Mahmoud M. Salim
author_sort Swellam W. Sharshir
collection DOAJ
description Solar stills are sustainable devices that generate freshwater through solar-powered desalination. However, traditional solar stills often struggle with variability in environmental conditions. This study proposes a predictive model using machine learning (ML) techniques to improve the accuracy and adaptability of active solar still performance. The study focuses on a modern heat pump-operated solar still, where the heat pump's cold side facilitates condensation, and its condenser provides additional heat to complement solar radiation. Furthermore, five ML regressors namely, extra trees (ET), adaptive boosting (Adaboost), random forest (RF), K-nearest neighbors (KNN), and light gradient boosting (LGB) are employed to model and forecast cumulative yield, total exergy, and thermal efficiencies. Besides, four separate train-test splits, 95 %:5 %, 90 %:10 %, 80 %:20 %, and 70 %:30 %, are employed to assess the performance of each regressor in terms of R-squared (R2), mean squared error (MSE), and mean absolute error (MAE). All the models showed prediction accuracy enhancement with increasing the train dataset size. The best perdition accuracy was achieved by the Extra Trees model as the model exhibited MSE of 0.0020, 0.0027, and 0.0033 for total yield, total exergy, and thermal efficiencies forecasting, respectively.
format Article
id doaj-art-4fc9fb407ddb4b32acc95cdfcf9d1ac9
institution DOAJ
issn 1944-3986
language English
publishDate 2025-01-01
publisher Elsevier
record_format Article
series Desalination and Water Treatment
spelling doaj-art-4fc9fb407ddb4b32acc95cdfcf9d1ac92025-08-20T02:45:50ZengElsevierDesalination and Water Treatment1944-39862025-01-0132110091610.1016/j.dwt.2024.100916Using multiple machine learning techniques to enhance the performance prediction of heat pump-driven solar desalination unitSwellam W. Sharshir0Abanob Joseph1Mohamed S. Abdalzaher2A.W. Kandeal3A.S. Abdullah4Zhanhui Yuan5Huizhong Zhao6Mahmoud M. Salim7College of Materials Engineering, Fujian Agriculture and Forestry University, Fuzhou 350002, China; Mechanical Engineering Department, Faculty of Engineering, Kafrelsheikh University, Kafrelsheikh 33516, Egypt; Corresponding author at: College of Materials Engineering, Fujian Agriculture and Forestry University, Fuzhou 350002, China.Mechanical Engineering Department, Faculty of Engineering, Kafrelsheikh University, Kafrelsheikh 33516, EgyptSeismology Department, National Research Institute of Astronomy and Geophysics, Helwan, Cairo 11421, Egypt; Electrical Engineering Department, Collage of Engineering, American University of Sharjah, Sharjah, United Arab Emirates; Corresponding author at: Seismology Department, National Research Institute of Astronomy and Geophysics, Helwan, Cairo 11421, Egypt.Mechanical Engineering Department, Faculty of Engineering, Kafrelsheikh University, Kafrelsheikh 33516, EgyptMechanical Power Engineering Department, Faculty of Engineering, Tanta University, Tanta City, EgyptCollege of Materials Engineering, Fujian Agriculture and Forestry University, Fuzhou 350002, China; Corresponding author.Merchant Marine College, Shanghai Maritime University, Shanghai 201306, ChinaDepartment of Electronics and Electrical Communications, October 6 University, 6 of October City, 12585 Giza, Egypt; Center for Communications Systems and Sensing, King Fahd University of Petroleum and Minerals (KFUPM), Dhahran 31261, Saudi ArabiaSolar stills are sustainable devices that generate freshwater through solar-powered desalination. However, traditional solar stills often struggle with variability in environmental conditions. This study proposes a predictive model using machine learning (ML) techniques to improve the accuracy and adaptability of active solar still performance. The study focuses on a modern heat pump-operated solar still, where the heat pump's cold side facilitates condensation, and its condenser provides additional heat to complement solar radiation. Furthermore, five ML regressors namely, extra trees (ET), adaptive boosting (Adaboost), random forest (RF), K-nearest neighbors (KNN), and light gradient boosting (LGB) are employed to model and forecast cumulative yield, total exergy, and thermal efficiencies. Besides, four separate train-test splits, 95 %:5 %, 90 %:10 %, 80 %:20 %, and 70 %:30 %, are employed to assess the performance of each regressor in terms of R-squared (R2), mean squared error (MSE), and mean absolute error (MAE). All the models showed prediction accuracy enhancement with increasing the train dataset size. The best perdition accuracy was achieved by the Extra Trees model as the model exhibited MSE of 0.0020, 0.0027, and 0.0033 for total yield, total exergy, and thermal efficiencies forecasting, respectively.http://www.sciencedirect.com/science/article/pii/S1944398624204264Active solar stillHeat pumpSustainabilityMachine learningPrediction modellingExtra trees
spellingShingle Swellam W. Sharshir
Abanob Joseph
Mohamed S. Abdalzaher
A.W. Kandeal
A.S. Abdullah
Zhanhui Yuan
Huizhong Zhao
Mahmoud M. Salim
Using multiple machine learning techniques to enhance the performance prediction of heat pump-driven solar desalination unit
Desalination and Water Treatment
Active solar still
Heat pump
Sustainability
Machine learning
Prediction modelling
Extra trees
title Using multiple machine learning techniques to enhance the performance prediction of heat pump-driven solar desalination unit
title_full Using multiple machine learning techniques to enhance the performance prediction of heat pump-driven solar desalination unit
title_fullStr Using multiple machine learning techniques to enhance the performance prediction of heat pump-driven solar desalination unit
title_full_unstemmed Using multiple machine learning techniques to enhance the performance prediction of heat pump-driven solar desalination unit
title_short Using multiple machine learning techniques to enhance the performance prediction of heat pump-driven solar desalination unit
title_sort using multiple machine learning techniques to enhance the performance prediction of heat pump driven solar desalination unit
topic Active solar still
Heat pump
Sustainability
Machine learning
Prediction modelling
Extra trees
url http://www.sciencedirect.com/science/article/pii/S1944398624204264
work_keys_str_mv AT swellamwsharshir usingmultiplemachinelearningtechniquestoenhancetheperformancepredictionofheatpumpdrivensolardesalinationunit
AT abanobjoseph usingmultiplemachinelearningtechniquestoenhancetheperformancepredictionofheatpumpdrivensolardesalinationunit
AT mohamedsabdalzaher usingmultiplemachinelearningtechniquestoenhancetheperformancepredictionofheatpumpdrivensolardesalinationunit
AT awkandeal usingmultiplemachinelearningtechniquestoenhancetheperformancepredictionofheatpumpdrivensolardesalinationunit
AT asabdullah usingmultiplemachinelearningtechniquestoenhancetheperformancepredictionofheatpumpdrivensolardesalinationunit
AT zhanhuiyuan usingmultiplemachinelearningtechniquestoenhancetheperformancepredictionofheatpumpdrivensolardesalinationunit
AT huizhongzhao usingmultiplemachinelearningtechniquestoenhancetheperformancepredictionofheatpumpdrivensolardesalinationunit
AT mahmoudmsalim usingmultiplemachinelearningtechniquestoenhancetheperformancepredictionofheatpumpdrivensolardesalinationunit