Evaluation of Machine and Deep Learning Models for Predicting Water Distillate Rate

Freshwater scarcity has become a critical global challenge due to rapid population growth and environmental pollution caused by industrial and urban expansion. Solar stills offer a sustainable solution by desalinating impure water using solar energy, making them valuable for domestic, industrial, and academic applications. However, traditional methods for optimizing solar still performance face significant limitations, including time-consuming experimental data collection, computational inaccuracies, and high development costs. To address these challenges, this study leverages machine learning (ML) and deep learning (DL) techniques to predict the distilled water production rate of solar stills before physical construction or modification. A heat pump solar still (HPSS) was used as the test case, with meteorological data serving as key input features for model training. The results demonstrate that data preprocessing, particularly normalization, enhances prediction accuracy. Among the tested models, Artificial Neural Networks (ANN) and Random Forest (RF) delivered the best performance, with RF emerging as the most robust, balancing low error rates (with 62.8% MSE reduction) and high R-squared values. Additionally, solar radiation was identified as the most influential factor in predicting distillate output. This research highlights the potential of AI-driven predictive modeling to optimize solar desalination systems and improve freshwater production efficiency.