Data-driven Prediction of Ionic Conductivity in Solid-State Electrolytes with Machine Learning and Large Language Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918417957650432 |
|---|---|
| author | Kim, Haewon Lee, Taekgi Hong, Seongeun Kim, Kyeong-Ho Chung, Yongchul G. |
| author_facet | Kim, Haewon Lee, Taekgi Hong, Seongeun Kim, Kyeong-Ho Chung, Yongchul G. |
| contents | Solid-state electrolytes (SSEs) are attractive for next-generation lithium-ion batteries due to improved safety and stability but their low room-temperature ionic conductivity hinders practical application. Experimental synthesis and testing of new SSEs remain time-consuming and resource intensive. Machine learning (ML) offers an accelerated route for SSE discovery; however, composition-only models neglect structural factors important for ion transport while graph neural networks (GNNs) are challenged by the scarcity of structure-labeled conductivity data and the prevalence of crystallographic disorder in CIFs. Here, we train two complementary predictors on the same room-temperature, structure-labeled dataset (n = 499). A gradient-boosted tree regressor (GBR) combining stoichiometric and geometric descriptors achieves best performance (MAE = 0.543 in log(S cm-1)), and Shapley Additive exPlanations (SHAP) identifies probe-occupiable volume (POAV) and lattice parameters as key correlations for conductivity. In parallel, we fine-tune large language models (LLMs) using compact text prompts derived from CIF metadata (formula with optional symmetry and disorder tags), avoiding direct use of raw atomic coordinates. Notably, Llama-3.1-8B-Instruct achieves high accuracy (MAE = 0.657 in log(S cm-1)) using formula and symmetry information, eliminating the need for numerical feature extraction from CIF files. Together, these results show that global geometric descriptors improve tree-based predictions and enable interpretable structure-property analysis, while LLMs provide a competitive low-preprocessing alternative for rapid SSE screening. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_10997 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Data-driven Prediction of Ionic Conductivity in Solid-State Electrolytes with Machine Learning and Large Language Models Kim, Haewon Lee, Taekgi Hong, Seongeun Kim, Kyeong-Ho Chung, Yongchul G. Materials Science Solid-state electrolytes (SSEs) are attractive for next-generation lithium-ion batteries due to improved safety and stability but their low room-temperature ionic conductivity hinders practical application. Experimental synthesis and testing of new SSEs remain time-consuming and resource intensive. Machine learning (ML) offers an accelerated route for SSE discovery; however, composition-only models neglect structural factors important for ion transport while graph neural networks (GNNs) are challenged by the scarcity of structure-labeled conductivity data and the prevalence of crystallographic disorder in CIFs. Here, we train two complementary predictors on the same room-temperature, structure-labeled dataset (n = 499). A gradient-boosted tree regressor (GBR) combining stoichiometric and geometric descriptors achieves best performance (MAE = 0.543 in log(S cm-1)), and Shapley Additive exPlanations (SHAP) identifies probe-occupiable volume (POAV) and lattice parameters as key correlations for conductivity. In parallel, we fine-tune large language models (LLMs) using compact text prompts derived from CIF metadata (formula with optional symmetry and disorder tags), avoiding direct use of raw atomic coordinates. Notably, Llama-3.1-8B-Instruct achieves high accuracy (MAE = 0.657 in log(S cm-1)) using formula and symmetry information, eliminating the need for numerical feature extraction from CIF files. Together, these results show that global geometric descriptors improve tree-based predictions and enable interpretable structure-property analysis, while LLMs provide a competitive low-preprocessing alternative for rapid SSE screening. |
| title | Data-driven Prediction of Ionic Conductivity in Solid-State Electrolytes with Machine Learning and Large Language Models |
| topic | Materials Science |
| url | https://arxiv.org/abs/2601.10997 |