Prediction of $\textrm{CO}_2$ Adsorption in Nano-Pores with Graph Neural Networks

TL;DR

This paper presents a graph neural network model that predicts CO2 adsorption in MOFs using only structural data, achieving accuracy comparable to complex models with fewer features, enabling scalable industrial gas capture optimization.

Contribution

The study introduces a novel GNN-based method that accurately predicts gas adsorption in MOFs using minimal input data, reducing computational costs compared to traditional models.

Findings

Achieved high prediction accuracy with minimal structural input.

Matched classical machine learning models' performance.

Facilitated scalable industrial gas capture optimization.

Abstract

We investigate the graph-based convolutional neural network approach for predicting and ranking gas adsorption properties of crystalline Metal-Organic Framework (MOF) adsorbents for application in post-combustion capture of $\textrm{CO}_2$. Our model is based solely on standard structural input files containing atomistic descriptions of the adsorbent material candidates. We construct novel methodological extensions to match the prediction accuracy of classical machine learning models that were built with hundreds of features at much higher computational cost. Our approach can be more broadly applied to optimize gas capture processes at industrial scale.