Graph Neural Network Predictions of Metal Organic Framework CO2 Adsorption Properties

Published

July 1, 2022

Author(s)

Kamal Choudhary, Taner N. Yildirim, Daniel Siderius, A. Gilad Kusne, Austin McDannald, Diana Ortiz-Montalvo

Abstract

The increasing CO$_2$ level is a critical concern and suitable materials are needed to directly capture such gases from the environment. While experimental and conventional computational methods are useful in finding such materials, they are usually slow and there is a need to expedite such processes. We use Atomistic Line Graph Neural Network (ALIGNN) method to predict CO$_2$ adsorption in metal organic frameworks (MOF), which are known for their high functional tunability. We train ALIGNN models for hypothetical MOF (hMOF) database with 137953 MOFs with grand canonical Monte Carlo (GCMC) based CO$_2$ adsorption isotherms. We develop high accuracy and fast models for pre-screeing applications. We apply the trained model on CoREMOF database and computationally rank them for experimental synthesis. In addition to the CO$_2$ adsorption isotherm, we also train models for electronic bandgaps, surface area, void fraction, lowest cavity diameter, and pore limiting diameter, and illustrate the strength and limitation of such graph neural network models. For a few candidate MOFs we carry out GCMC calculations to evaluate the deep-learning (DL) predictions.

Citation

Computational Materials Science

Pub Type

Journals

Download Paper

https://doi.org/10.1016/j.commatsci.2022.111388

Local Download

Keywords

Machine learning, Metal organic framework, CO2 absorption.

Citation

Choudhary, K. , Yildirim, T. , Siderius, D. , Kusne, A. , McDannald, A. and Ortiz-Montalvo, D. (2022), Graph Neural Network Predictions of Metal Organic Framework CO2 Adsorption Properties, Computational Materials Science, [online], https://doi.org/10.1016/j.commatsci.2022.111388, https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=933844 (Accessed October 7, 2025)