Accelerated Discovery of CO<sub>2</sub> Solid Sorbents Using Active Machine Learning: Review and Perspectives
Deyang Xu, Jing Yang, Zhaoxiang Xu, Guo-yu-lin Gu, Fen Qiao, Junfeng Wang, Bin Li, Chaoen Li, Dongjing Liu
Abstract
With the escalating severity of global climate change, the significance of carbon capture technology has become increasingly evident with respect to the aim of reaching carbon peak and carbon neutrality. Due to the exceptional selectivity, high adsorption capacity, and long-term stability, solid sorbents are regarded as crucial materials for effective CO 2 capture. Machine learning, as an emerging and crucial tool in artificial intelligence, has been adopted for the high-efficient screen of catalysts and sorbents in recent years. By analyzing available data on material properties, machine learning can greatly enhance the effectiveness and precision in identifying high-efficiency CO 2 sorbents. This work provides an overview of the latest advancements in the application of machine learning technology in CO 2 capture, which specifically focuses on CO 2 capture by sorbents. Several machine learning techniques and their applications in different types of CO 2 sorbents are fully summarized with concise comments, followed with conclusion and some challenges and perspectives. This review can serve as a guide for the development of carbon capture technology and facilitate the extensive utilization of machine learning technology in environmental protection.