article · Energy Technology
Predicting the output of solar desalination systems can be achieved effectively through machine learning. Four distinct predictive approaches, including artificial neural networks, random forest, support vector regression, and linear support vector regression, were evaluated to forecast the performance of a double slope solar still. Each model underwent parameter tuning via the Bayesian optimisation algorithm to identify the optimal configuration and establish the most dependable predictor. The models relied on empirical testing data gathered under Egyptian environmental conditions. The findings confirm that machine learning techniques provide strong forecasting capabilities for solar still output. Among the tested algorithms, the random forest model delivered the superior outcome, registering the highest coefficient of determination alongside the lowest absolute error rate. Furthermore, the solar still yielded an average daily freshwater productivity of 4.3 litres per square metre during experimental operations.
Accurate performance forecasting is essential for designing and operating solar-powered desalination devices reliably. Using optimised machine learning algorithms allows operators and engineers to predict freshwater yields under specific climatic conditions with minimal error. This predictive capability supports more consistent clean water generation in arid and sunny regions where conventional water infrastructure may be limited.
This predictive modelling tool can assist solar desalination system designers and water facility operators seeking to anticipate daily freshwater outputs. Tested using experimental data from Egyptian conditions, the computational framework operates at an applied research stage. Further development into operational software could provide predictive monitoring tools for commercial solar still manufacturers or off-grid water supply projects.
AI-generated from the published abstract. Always read the original work before citing.
Herein, double slope solar still (DSSS) performance is accurately forecast with the aid of four different machine learning (ML) models, namely, artificial neural network (ANN), random forest (RF), support vector regression (SVR), and linear SVR. Furthermore, the tuning of ML models is optimized using the Bayesian optimization algorithm (BOA) to get the optimal performance of all models and identify the best predictive one. All the models are trained, tested, and validated depending on experimental data acquired under Egyptian climatic conditions. The results reveal that ML models can be a powerful tool to forecast DSSS performance. Among them, RF is the most potent ML model obtaining the highest determination coefficient ( R 2 ) and the lowest absolute error percentage of 0.997% and 2.95%, respectively. Furthermore, the experimental results also show that the mean value of accumulated (daily) freshwater productivity from DSSS is 4.3 L m −2 .
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1002/ente.202100189
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
