Solar drying offers a sustainable alternative to energy-intensive and environmentally harmful food preservation methods. This review highlights advances in efficiency and reliability achieved through the integration of Phase Change Material (PCM) for thermal energy storage, as well as optimization using neural algorithms optimization and Evolutionary Polynomial Regression (PCM). PCMs absorb surplus heat during peak radiation and release it later, stabilizing drying temperatures, reducing energy demand, shortening drying times, and improving product quality. Studies across different dryer designs confirm these benefits. Machine learning methods, including ANN, SVM, LSTM, and ensemble models provide accurate prediction and optimization of drying performance, surpassing conventional modeling. EPR also demonstrates a strong capability in forecasting outlet temperature and thermal efficiency when PCM parameters are considered. The review further covers solar dryer classifications, PCM selection and placement strategies, and integration with solar collectors under varying conditions. Remaining challenges include limited experimental datasets and the need for advanced computation to model dynamic heat storage. Overall, combining PCMs with intelligent optimization offers a promising pathway to more efficient, resilient, and sustainable solar drying technologies.
