Why Physics Still Matters: Improving Machine Learning Prediction of Material Properties with Phonon-Informed Datasets

TL;DR

This paper demonstrates that physically informed, phonon-based datasets significantly improve machine learning predictions of material properties over random datasets, emphasizing the importance of data quality and physical relevance.

Contribution

It introduces a physically guided data generation strategy for training graph neural networks, outperforming random sampling in predicting properties of materials at finite temperatures.

Findings

Phonon-informed datasets lead to better GNN performance with fewer data.

Physically guided data improves model explainability and relevance.

Larger datasets do not always enhance predictive accuracy.

Abstract

Machine learning (ML) methods have become powerful tools for predicting material properties with near first-principles accuracy and vastly reduced computational cost. However, the performance of ML models critically depends on the quality, size, and diversity of the training dataset. In materials science, this dependence is particularly important for learning from low-symmetry atomistic configurations that capture thermal excitations, structural defects, and chemical disorder, features that are ubiquitous in real materials but underrepresented in most datasets. The absence of systematic strategies for generating representative training data may therefore limit the predictive power of ML models in technologically critical fields such as energy conversion and photonics. In this work, we assess the effectiveness of graph neural network (GNN) models trained on two fundamentally different types of datasets: one composed of randomly generated atomic configurations and another constructed using physically informed sampling based on lattice vibrations. As a case study, we address the challenging task of predicting electronic and mechanical properties of a prototypical family of optoelectronic materials under realistic finite-temperature conditions. We find that the phonons-informed model consistently outperforms the randomly trained counterpart, despite relying on fewer data points. Explainability analyses further reveal that high-performing models assign greater weight to chemically meaningful bonds that control property variations, underscoring the importance of physically guided data generation. Overall, this work demonstrates that larger datasets do not necessarily yield better GNN predictive models and introduces a simple and general strategy for efficiently constructing high-quality training data in materials informatics.