Li-P-S Electrolyte Materials as a Benchmark for Machine-Learned Interatomic Potentials

TL;DR

This paper introduces LiPS-25, a comprehensive benchmark dataset for Li-P-S electrolyte materials, along with performance evaluation methods for graph-based machine-learned interatomic potentials, facilitating robust and insightful model assessment.

Contribution

The paper presents LiPS-25, a curated dataset and a suite of evaluation tests for MLIP models on Li-P-S electrolytes, enabling standardized benchmarking and analysis.

Findings

Assessment of hyperparameter effects on MLIP performance

Evaluation of pre-trained MLIP models' fine-tuning behavior

Demonstration of benchmark adaptability to other materials

Abstract

With the growing availability of machine-learned interatomic potential (MLIP) models for materials simulations, there is an increasing demand for robust, automated, and chemically insightful benchmarking methodologies. In response, we here introduce LiPS-25, a curated benchmark dataset for a canonical series of solid-state electrolyte materials from the Li2S-P2S5 pseudo-binary compositional line, including crystalline and amorphous configurations. Together with the dataset, we present a suite of performance tests that range from conventional numerical error metrics to physically motivated evaluation tasks. With a focus on graph-based MLIP architectures, we run numerical experiments that assess (i) the effect of hyperparameters and (ii) the fine-tuning behavior of selected pre-trained ("foundational") MLIP models. Beyond the Li-P-S solid-state electrolytes, we expect that such benchmarks and their code implementations can be readily adapted to other material systems.