Measuring the performance of solar energy and heat transfer systems requires a lot of time, economic cost, and manpower. Meanwhile, directly predicting their performance is challenging due to the complicated internal structures. Fortunately, a knowledge-based machine learning method can provide a promising prediction and optimization strategy for the performance of energy systems. In this chapter, the authors show how they utilize the machine learning models trained from a large experimental database to perform precise prediction and optimization on a solar water heater (SWH) system. A new energy system optimization strategy based on a high-throughput screening (HTS) process is proposed. This chapter consists of: 1) comparative studies on varieties of machine learning models (artificial neural networks [ANNs], support vector machine [SVM], and extreme learning machine [ELM]) to predict the performances of SWHs; 2) development of an ANN-based software to assist the quick prediction; and 3) introduction of a computational HTS method to design a high-performance SWH system.