Predicting the Efficiency of CO$_2$ Sequestering by Metal Organic Frameworks Through Machine Learning Analysis of Structural and Electronic Properties

TL;DR

This paper develops a machine learning algorithm to predict CO₂ uptake efficiency of Metal-Organic Frameworks, aiding rapid identification of promising materials for carbon capture and reducing experimental costs.

Contribution

The study introduces a novel ML-based predictive model for MOF CO₂ adsorption efficiency and identifies key structural and electronic features influencing performance.

Findings

The model accurately predicts CO₂ uptake with high correlation.

Key features influencing efficiency are identified.

The approach accelerates the discovery of effective MOFs.

Abstract

Due the alarming rate of climate change, the implementation of efficient CO$_2$ capture has become crucial. This project aims to create an algorithm that predicts the uptake of CO$_2$ adsorbing Metal-Organic Frameworks (MOFs) by using Machine Learning. These values will in turn gauge the efficiency of these MOFs and provide scientists who are looking to maximize the uptake a way to know whether or not the MOF is worth synthesizing. This algorithm will save resources such as time and equipment as scientists will be able to disregard hypothetical MOFs with low efficiencies. In addition, this paper will also highlight the most important features within the data set. This research will contribute to enable the rapid synthesis of CO$_2$ adsorbing MOFs.