Machine Learning-Based Prediction of Metal-Organic Framework Materials: A Comparative Analysis of Multiple Models

TL;DR

This paper compares multiple machine learning models for predicting properties of metal-organic frameworks, finding ensemble methods like Random Forest perform best, with efficiency and accuracy insights for materials science applications.

Contribution

It provides a comprehensive comparison of five machine learning models for MOF property prediction, highlighting the superior performance of ensemble methods and computational efficiency.

Findings

Random Forest achieved R^2 of 0.891 and RMSE of 0.152.

LightGBM trained in 25.7 seconds with high accuracy.

Ensemble models outperform traditional single models in MOF prediction.

Abstract

Metal-organic frameworks (MOFs) have emerged as promising materials for various applications due to their unique structural properties and versatile functionalities. This study presents a comprehensive investigation of machine learning approaches for predicting MOF material properties. We employed five different machine learning models: Random Forest, XGBoost, LightGBM, Support Vector Machine, and Neural Network, to analyze and predict MOF characteristics using a dataset from the Kaggle platform. The models were evaluated using multiple performance metrics, including RMSE, R^2, MAE, and cross-validation scores. Results demonstrated that the Random Forest model achieved superior performance with an R^2 value of 0.891 and RMSE of 0.152, significantly outperforming other models. LightGBM showed remarkable computational efficiency, completing training in 25.7 seconds while maintaining high accuracy. Our comparative analysis revealed that ensemble learning methods generally exhibited better performance than traditional single models in MOF property prediction. This research provides valuable insights into the application of machine learning in materials science and establishes a robust framework for future MOF material design and property prediction.