Refining Tc Prediction in Hydrides via Symbolic-Regression-Enhanced Electron-Localization-Function-Based Descriptors

TL;DR

This paper improves the prediction of superconducting critical temperatures in hydrides by combining ELF-based descriptors with symbolic regression, addressing limitations of previous models and enabling more accurate screening of new materials.

Contribution

It introduces the molecularity index and applies symbolic regression to enhance ELF-based Tc predictions in complex hydrides, expanding the model's applicability.

Findings

Enhanced prediction accuracy with the molecularity index and symbolic regression.

The model performs well across binary and ternary hydrides.

Provides a robust framework for high-throughput screening of superconductors.

Abstract

Hydrogen-based materials are able to possess extremely high superconducting critical temperatures, \tc s, due to hydrogen's low atomic mass and strong electron-phonon interaction. Recently, a descriptor based on the Electron Localization Function (ELF) has enabled the rapid estimation of the \tc\ of hydrogen-containing compounds from electronic networking properties, but its applicability has been limited by the small size and homogeneity of the training dataset used. Herein, the model is re-examined compiling a publicly available combined dataset of 244 binary and ternary hydride superconductors. Our analysis shows that though ELF-based networking remains a valuable descriptor, its predictive power declines with increasing compositional complexity. However, by introducing the molecularity index, defined as the highest value of the ELF at which two hydrogen atoms connect, and applying symbolic regression, the accuracy of the predictions can be substantially enhanced. These results establish a more robust framework for assessing superconductivity in hydride materials, facilitating accelerated screening of novel candidates through integration with crystal structure prediction methods or high-throughput searches.