Optimizing water resources for sustainable desalination: The integration of expert systems and solar energy in experimental applications

The integration of renewable energy sources with multi-energy systems present challenges and opportunities to enhance sustainability. Among these, solar stills have emerged as a solution for water desalination. With the advent of expert system technologies, avenues are opened for improving the operational efficiency of solar distillers. This paper presents an innovative approach utilizing correlation analysis, ReliefF for feature selection, and a k-Nearest Neighbor (kNN) algorithm for forecasting the cumulative distillate output of a double slope solar still. The analysis is based on a 6-cases-based dataset, which includes variations in distillate output relative to different operational-environmental conditions. Key features that significantly impact overall performance were identified to manage the solar distiller productivity. The findings reveal that the maximum distillate output was 1610 ML/m².day due to incorporating reflective materials and phase change materials (PCM) in enhancing distillation rates. The kNN model was evaluated based on its R2, RMSE, and CVRMSE, with the best models achieving scores of 0.995, 0.0033, and 0.1666, respectively. These metrics underscore the effectiveness of the proposed machine learning approach in predicting distillate output, thereby enabling informed management of solar distillation processes. Combining renewable energy technologies and computational intelligence holds significant promise for sustainable environmental management, as the study presented.