Yang Li, Sun Lei, Zhao Yanliang, Sun Jikai, Deng Qiwen, Wang Honglei, Deng Weiqiao
Institute of Molecular Sciences and Engineering, Institute of Frontier and Interdisciplinary Science, Shandong University, Qingdao 266237, China.
State Key Laboratory of Molecular Reaction Dynamics, Dalian National Laboratory for Clean Energy, Dalian Institute of Chemical Physics, Chinese Academy of Sciences, Dalian 116023, China.
Phys Chem Chem Phys. 2021 Oct 20;23(40):22835-22853. doi: 10.1039/d1cp03456a.
Microporous organic polymers (MOPs) are a new class of microporous materials. Due to their high porosity, large pore volume, and large surface area, MOPs exhibit excellent performance in gas adsorption and storage, membrane separation, ion capture, heterogeneous catalysis, light energy conversion and storage, capacitance, and other fields. However, selecting high-performance materials for specific applications from thousands of candidate MOPs is a key problem. Traditional design strategies for new materials with targeted properties, including trial-and-error and relying on the experiences of domain experts, are time- and cost-consuming. With the rapid development of computation technology and theoretical chemistry, the discovery of new materials is no longer a purely experimental subject. Breaking away from the traditional trial-and-error strategy for materials discovery, materials design is emerging and gaining increasing attention. In addition, the ability to collect "big data" has greatly improved and has further stimulated the development of new methods for materials design and discovery. In this perspective, we examine how data-driven techniques combine artificial intelligence (AI) and human expertise, playing a significant role in the design of MOPs. Such analytics can significantly reduce time-to-insight and accelerate the cost-effective materials discovery, which is the goal for designing future MOPs.
微孔有机聚合物（MOPs）是一类新型的微孔材料。由于其高孔隙率、大孔体积和大表面积，MOPs在气体吸附与存储、膜分离、离子捕获、多相催化、光能转换与存储、电容等领域表现出优异的性能。然而，从数千种候选MOPs中为特定应用选择高性能材料是一个关键问题。传统的具有目标性能的新材料设计策略，包括试错法和依赖领域专家的经验，既耗时又费钱。随着计算技术和理论化学的快速发展，新材料的发现不再是一个纯粹的实验课题。摆脱传统的材料发现试错策略，材料设计正在兴起并越来越受到关注。此外，收集“大数据”的能力有了很大提高，进一步推动了材料设计和发现新方法的发展。从这个角度出发，我们研究数据驱动技术如何将人工智能（AI）与人类专业知识相结合，在MOPs的设计中发挥重要作用。这样的分析可以显著减少洞察时间，并加速具有成本效益的材料发现，这是设计未来MOPs的目标。
