Robust Machine Learning Framework for Reliable Discovery of High-Performance Half-Heusler Thermoelectrics

TL;DR

This paper develops a robust machine learning workflow for predicting thermoelectric performance in half-Heusler compounds, emphasizing model generalizability and physical insight, leading to the discovery of new high-performance candidates.

Contribution

It introduces a PCA-based data splitting method, integrates Bayesian hyperparameter optimization with feature filtering, and combines physical insight tools, enhancing ML model reliability for thermoelectric material discovery.

Findings

Improved model generalizability for zT prediction.

Identification of key physical drivers like dopant concentration and heat of vaporization.

Discovery of several novel high-zT thermoelectric candidates.

Abstract

Machine learning (ML) can facilitate efficient thermoelectric (TE) material discovery essential to address the environmental crisis. However, ML models often suffer from poor experimental generalizability despite high metrics. This study presents a robust workflow, applied to the half-Heusler (hH) structural prototype, for figure of merit (zT) prediction, to improve the generalizability of ML models. To resolve challenges in dataset handling and feature filtering, we first introduce a rigorous PCA-based splitting method that ensures training and test sets are unbiased and representative of the full chemical space. We then integrate Bayesian hyperparameter optimization with k-best feature filtering across three architectures-Random Forest, XGBoost, and Neural Networks - while employing SISSO symbolic regression for physical insight and comparison. Using SHAP and SISSO analysis, we identify A-site dopant concentration (xA'), and A-site Heat of Vaporization (HVA) as the primary drivers of zT besides Temperature (T). Finally, a high-throughput screening of approximately 6.6x10^8 potential compositions, filtered by stability constraints, yielded several novel high-zT candidates. Breaking from the traditional focus of improving test RMSE/R^2 values of the models, this work shifts the attention on establishing the test set a true proxy for model generalizability and strengthening the often neglected modules of the existing ML workflows for the data-driven design of next-generation thermoelectric materials.