Machine Learning in Computational Design and Optimization of Disordered Nanoporous Materials.

This review analyzes the current practices in the data-driven characterization, design and optimization of disordered nanoporous materials with pore sizes ranging from angstroms (active carbon and polymer membranes for gas separation) to tens of nm (aerogels). While the machine learning (ML)-based prediction and screening of crystalline, ordered porous materials are conducted frequently, materials with disordered porosity receive much less attention, although ML is expected to excel in the field, which is rich with ill-posed problems, non-linear correlations and a large volume of experimental results. For micro- and mesoporous solids (active carbons, mesoporous silica, aerogels, etc.), the obstacles are mostly related to the navigation of the available data with transferrable and easily interpreted features. The majority of published efforts are based on the experimental data obtained in the same work, and the datasets are often very small. Even with limited data, machine learning helps discover non-evident correlations and serves in material design and production optimization. The development of comprehensive databases for micro- and mesoporous materials with low-level structural and sorption characteristics, as well as automated synthesis/characterization protocols, is seen as the direction of efforts for the immediate future. This paper is written in a language readable by a chemist unfamiliar with the data science specifics.