Explainable AI for Curie Temperature Prediction in Magnetic Materials

TL;DR

This paper applies explainable machine learning models to predict Curie temperatures in magnetic materials, providing insights into key physicochemical factors and improving interpretability of the predictions.

Contribution

It introduces an explainable AI framework for Curie temperature prediction, combining advanced ML models with interpretability techniques like SHAP analysis.

Findings

Extra Trees Regressor achieved R^2 of 0.85

SHAP analysis identified atomic number and magnetic moment as key drivers

Clustering revealed chemically distinct groups with different behaviors

Abstract

We explore machine learning techniques for predicting Curie temperatures of magnetic materials using the NEMAD database. By augmenting the dataset with composition-based and domain-aware descriptors, we evaluate the performance of several machine learning models. We find that the Extra Trees Regressor delivers the best performance reaching an R^2 score of up to 0.85 $\pm$ 0.01 (cross-validated) for a balanced dataset. We employ the k-means clustering algorithm to gain insights into the performance of chemically distinct material groups. Furthermore, we perform the SHAP analysis to identify key physicochemical drivers of Curie behavior, such as average atomic number and magnetic moment. By employing explainable AI techniques, this analysis offers insights into the model's predictive behavior, thereby advancing scientific interpretability.