Accelerating the prediction of CO2 capture at low partial pressures in metal-organic frameworks using new machine learning descriptors

Abstract

Metal-Organic frameworks (MOFs) have been considered for various gas storage and separation applications. Theoretically, there are an infinite number of MOFs that can be created; however, a finite amount of resources are available to evaluate each one. Computational methods can be adapted to expedite the process of evaluation. In the context of CO2 capture, this paper investigates the method of screening MOFs using machine learning trained on molecular simulation data. New descriptors are introduced to aid this process. Using all descriptors, it is shown that machine learning can predict the CO2 adsorption, with an R2 of above 0.9. The introduced Effective Point Charge (EPoCh) descriptors, which assign values to frameworks’ partial charges based on the expected CO2 uptake of an equivalent point charge in isolation, are shown to be the second most important group of descriptors, behind the Henry coefficient. Furthermore, the EPoCh descriptors are hundreds of thousands of times faster to obtain compared with the Henry coefficient, and they achieve similar results when identifying top candidates for CO2 capture using pseudo-classification predictions.

Accelerated Discovery of Metal–Organic Frameworks for CO2 Capture by Artificial Intelligence

“…95 Another new descriptor, effective point charge, was recently introduced and used together with the Henry coefficients of CO 2 in ML models to predict CO 2 capture properties of MOFs at very low-pressure conditions mimicking direct air capture. 96 Development and usage of new features in the future will lead to much accurate ML models.…”

“…For example, energy-based descriptors, including Gibbs free energy and Boltzmann weighted energy distributions of xenon (Xe) and krypton (Kr) gases, were demonstrated to be more important for determining Xe/Kr selectivities of MOFs compared to their structural and chemical features . Another new descriptor, effective point charge, was recently introduced and used together with the Henry coefficients of CO 2 in ML models to predict CO 2 capture properties of MOFs at very low-pressure conditions mimicking direct air capture . Development and usage of new features in the future will lead to much accurate ML models.…”

Informative Training Data for Efficient Property Prediction in Metal–Organic Frameworks by Active Learning

“…To assist in this endeavor, computational techniques such as molecular simulations and density-functional theory − were used to screen large MOF data sets. Alternatively, machine learning (ML) approaches were exploited to further accelerate MOF discovery. − Based on a training sample, a descriptor-based ML model is learned, for e.g., kernel ridge regression, random forests, or gradient boosting regression trees, ,− to predict electronic and gas adsorption properties of unseen samples. Recently, deep learning methods such as crystal graph convolutional neural networks (CGCNNs , ) and transformer-based models ,, were also investigated.…”

Machine Learning Approach for the Estimation of Henry’s Law Constant Based on Molecular Descriptors

“…Additionally, Hou et al (2022) developed a deep learning model based on Bidirectional long short-term memory with Channel and Spatial Attention network (BCSA) using the molecular Simplified Molecular Input Line Entry System (SMILES) to predict aqueous solubility [14]. Furthermore, machine learning aids in characterizing the absorption and adsorption kinetics of CO 2 in ionic liquids and metal-organic frameworks by predicting its HLC using Random Forest (RF), Multiple Linear Regression (MLP), and Support Vector Machine (SVM) [15][16][17]. Wang et al (2020) used an Adaptive Neuro-Fuzzy Inference System (ANFIS) and a Least Squares Support Vector Machine (LSSVM) to predict HLC in water based on the molecular structure of compounds.…”