Abstract
Efficient energy conversion and storage are crucial for the sustainable development and growth of renewable energy sources. However, the limited varieties of traditional energy catalytic materials cannot match the fast-expansion requirement of raising various clean energy for industrial applications. Thus, accelerating the design and synthesis of high-performance catalysts is necessary for the application of energy equipment. Recently, with artificial intelligence (AI) technology being advanced by leaps and bounds, it is feasible to efficiently and precisely screen materials and optimize synthesis conditions in a huge unknown space. Here, we introduce and review AI techniques used in the development of catalytic materials in detail. We describe the workflow for designing and synthesizing new materials using machine learning (ML) and robotics. We summarize the sources of data collection, the intelligent algorithms commonly used to build ML models, and the laboratory modules for the intelligent synthesis of materials. We provide the illustrations of predicting the properties of catalytic materials with ML assistance in different material types. In addition, we present the potential strategies for finding material synthesis pathways, and advances in robotics to accelerate high-performance catalytic materials synthesis in the review. Finally, the summary, challenges, and potential directions in the development of AI-assisted catalytic materials are presented and discussed.