Abstract Solar desalination is a technology that demonstrates an environmental innocuous method of freshwater generation in water‐stressed areas; however, the application of the technology is limited by low thermal efficiency and unpredictable performance in different climatic conditions. This paper presents an experimental study of a inclined solar still, which has been complemented with a phase‐change material (PCM) and optimized using a hybrid Genetic Algorithms (GA) and Machine Learning (ML) algorithm. Design and operating variables, such as the angle of the glass cover, the depth of the water in the basin, and the temperature of the glass surface were all optimized to achieve maximum thermal efficiency as well as to achieve maximum distillate yield. It was experimentally shown that the optimized configuration achieved a peak thermal efficiency of about 44%, and the highest freshwater yield of 4.9 L m −2 day −1 . The combined GA‐ML approach, in turn, will optimize the usage of energy and predictability of its operations, which in turn facilitates the evolution of smart and low‐emission solar desalination systems allowing it to be used in decentralized and off‐grid water‐supply systems.
Shanmugam et al. (Mon,) studied this question.