Combining Computational Screening and Machine Learning to Predict Metal–Organic Framework Adsorbents and Membranes for Removing CH4 or H2 from Air

Abstract

Separating and capturing small amounts of CH4 or H2 from a mixture of gases, such as coal mine spent air, at a large scale remains a great challenge. We used large-scale computational screening and machine learning (ML) to simulate and explore the adsorption, diffusion, and permeation properties of 6013 computation-ready experimental metal–organic framework (MOF) adsorbents and MOF membranes (MOFMs) for capturing clean energy gases (CH4 and H2) in air. First, we modeled the relationships between the adsorption and the MOF membrane performance indicators and their characteristic descriptors. Among three ML algorithms, the random forest was found to have the best prediction efficiency for two systems (CH4/(O2 + N2) and H2/(O2 + N2)). Then, the algorithm was further applied to quantitatively analyze the relative importance values of seven MOF descriptors for five performance metrics of the two systems. Furthermore, the 20 best MOFs were also selected. Finally, the commonalities between the high-performance MOFs were analyzed, leading to three types of material design principles: tuned topology, alternative metal nodes, and organic linkers. As a result, this study provides microscopic insights into the capture of trace amounts of CH4 or H2 from air for applications involving coal mine spent air and hydrogen leakage.

Combining computational screening and machine learning to explore MOFs and COFs for methane purification

“…After performing GCMC and MD simulations to compute the adsorption and diffusion properties of 6013 synthesized MOFs, ML models were developed to predict adsorption selectivity, diffusion selectivity, permeability, and membrane selectivity based on the pore size, porosity, surface area, density, Q st , and Henry's constant of the MOFs. 57 Several membrane design strategies were presented by comparing MOFs that differ solely in terms of metal, organic linker, or topology and exhibit promising and poor separation performance. This shows the importance of integrating molecular simulations and ML to rapidly design promising MOF membranes even only altering topology, organic linkers, or metal centers rather than synthesizing a completely new material.…”

Active Learning for Adsorption Simulations: Evaluation, Criteria Analysis, and Recommendations for Metal–Organic Frameworks

“…Over the past years, ML has been used in material science research for a variety of reasons, including polymer property prediction, zeolite structure categorization, crystal structure prediction, etc. The estimation of gas storage capacity has been predicted using ML, − as well as predicting the oxidation state of MOFs, optimizing the swing adsorption process conditions with MOFs, and assigning partial charges to MOF atoms. , The high-throughput screening of MOFs for hydrogen separation have also been studied using ML. , …”

“…17,24 The high-throughput screening of MOFs for hydrogen separation have also been studied using ML. 25,26 The rule of thumb is that ML requires a large set of data for the proper training of the model, but given the high cost of running many molecular simulations, there is need for an alternative. Several authors have developed ML models to predict isotherms; 27−29 however, a large dataset is required to train these models.…”