From Data-Driven Models to Physical Insight: Vibrational Entropy Governed by Atomic Volume

TL;DR

This paper develops an efficient, interpretable model for predicting vibrational entropy in materials, combining data-driven methods with physical insights to enable entropy-informed materials screening.

Contribution

It introduces a neural network-based approach that identifies atomic volume as key to vibrational entropy and derives a simple, physically meaningful analytical model.

Findings

Neural network achieves high accuracy in predicting vibrational entropy.

Atomic volume is identified as the dominant factor influencing vibrational entropy.

A logarithmic dependence model accurately describes vibrational entropy across materials.

Abstract

Vibrational entropy plays a central role in determining phase stability and temperature dependent behavior in materials, yet its calculation from first-principles phonon methods remains computationally demanding. In this work, we combine data-driven modeling with physically motivated analysis to develop an efficient and interpretable framework for predicting vibrational entropy. Using a dataset derived from PhononDB, a feedforward neural network trained on Materials Project and composition based descriptors achieves high predictive accuracy, while SHAP analysis identifies atomic volume as the dominant factor governing vibrational entropy. Guided by this insight, simplified analytical models are constructed, revealing a logarithmic dependence of vibrational entropy on atomic volume consistent with lattice dynamical considerations. A logarithmic linear model is shown to provide an accurate and physically interpretable description across the full range of materials. To extend the analysis to finite temperatures, a temperature dependent formulation is introduced that incorporates T3 scaling at low temperatures and logarithmic dependence at higher temperatures, consistent with Debye and Einstein type behavior. This unified model captures both structural and thermal contributions to vibrational entropy with good accuracy. Overall, the proposed framework demonstrates that vibrational entropy can be predicted using simple, physically meaningful relationships, offering a computationally efficient alternative to full phonon calculations and enabling entropy informed materials screening.