Data-driven chemical feature extraction and material design for halide solid-state electrolytes

All-solid-state batteries (ASSBs) are promising candidates for next-generation energy storage, offering high safety and energy density. Halide solid-state electrolytes (HSSEs) have garnered significant research interest due to their high ionic conductivity and exceptional high-voltage stability. However, the discovery of HSSEs largely relies on trial-and-error strategies that lack guidance from knowledge of structure–performance relationships. Here, we present a data-driven study of HSSE identification assisted by large language models, including dataset construction, data analysis, and machine learning, to extract key features governing ionic conductivity and predict HSSEs with high conductivity. We find that cationic potential, lithium content, and cationic charge density play a crucial role in the ionic conductivity of HSSEs. Guided by the machine learning predictions, we design LiTa 0.9 Al 0.1 O 0.5 Cl 4.8 (LTAOC), which achieves a high ionic conductivity of 12.2 mS cm −1 , demonstrating the reliability of the data-driven research. ASSBs with LTAOC exhibit a long cycling stability of 2000 cycles at 5 C, while high-loading ASSBs achieve a high areal capacity of 4.2 mAh cm −2 . This work establishes a data-driven framework for materials research, promoting a shift from conventional trial-and-error strategies toward systematic and predictive exploration, thereby accelerating material discovery. • A data-driven paradigm accelerates halide SSE discovery. • Machine learning identifies key features governing the ionic conductivity of halide SSEs. • Data-driven prediction discovers LTAOC, which has a high conductivity of 12.2 mS cm −1 . • ASSBs with LTAOC deliver a long cycling stability of 2000 cycles and a high areal capacity of 4 mAh cm −2 after 550 cycles.