硅酸盐学报

机器学习势在正极材料电化学性质预测中的评测

PDF下载

蒋冰鉴 ¹^,² , 杨涛 ¹^,² , 路宽 ³ , 张艺馨 ⁴

硅酸盐学报 | 研究论文 2026,54(7): 2338-2351

收起

硅酸盐学报 |研究论文 2026 , 54 (7) : 2338 -2351

机器学习势在正极材料电化学性质预测中的评测

全屏

蒋冰鉴¹^,², 杨涛¹^,², 路宽³, 张艺馨⁴

作者信息

^1．北京信息科技大学计算机学院，北京 100101

^2．北京信息科技大学，北京材料基因工程高精尖创新中心，北京 100101

^3．中国科学院山西煤炭化学研究所，煤炭高效低碳利用全国重点实验室，太原 030001

^4．宁夏大学化学化工学院，银川 750021

通讯作者:

杨涛（1980—），女，博士，助理研究员。

作者简介:

蒋冰鉴（2000—），男，硕士研究生。

Comparative Evaluation of Machine-Learning Potentials for Electrochemical Properties of Cathodes

Bingjian JIANG¹^,², Tao YANG¹^,², Kuan LU³, Yixin ZHANG⁴

Affiliations

^1.School of Computer, Beijing Information Science and Technology University, Beijing 100101, China

^2.Beijing Advanced Innovation Center for Materials Genome Engineering, Beijing Information Science and Technology University, Beijing 100101, China

^3.Institute of Coal Chemistry, Chinese Academy of Sciences, State Key Laboratory of Coal Conversion, Taiyuan 030001, China

^4.School of Chemistry and Chemical Engineering, Ningxia University, Yinchuan 750021, China

Corresponding Author:

{YANG} Tao (1980-), female, Ph.D., Assistant Professor. E-mail: ytyangmei@bistu.edu.cn

JIANG Bingjian (2000-), male, Master candidate. E-mail: 2023020608@bistu.edu.cn

出版时间: 2026-04-10 doi: 10.14062/j.issn.0454-5648.20250871

文章导航

摘要

收起

系统评估了8种具有代表性的预训练机器学习势（MACE、M3GNet、CHGNet、ALIGNN、SevenNet、AlphaNet、GRACE和Orb）在典型Na/Li正极材料（层状氧化物、磷酸盐及其他快离子导体）上的性能，涵盖电压预测、离子迁移与热稳定性3大关键任务，旨在为不同电化学性质预测任务中机器学习势的合理选择提供定量依据。结果显示，M3GNet在电压预测中整体误差最小，其次为AlphaNet与CHGNet；离子迁移的MSD分析表明，MACE与SevenNet给出的扩散系数最接近参考值；热稳定性对比表明，M3GNet与MACE对释氧温度及阶梯分解特征的预测更为准确。上述体系覆盖Li/Na化学体系、层状与聚阴离子结构、多种过渡金属氧化还原对，为定量基准测试提供了可靠的DFT/实验数据支撑。

关键词

机器学习势 / 钠离子电池 / 锂离子电池 / 电压曲线 / 离子扩散 / 热稳定性

Abstract

收起

Introduction

Lithium-ion and sodium-ion batteries underpin portable electronics, electric vehicles, and grid-scale energy storage. Their performance and safety are strongly constrained by cathode behavior, and practical screening repeatedly requires three types of predictions, i.e., voltage profiles during (de)intercalation, alkali-ion migration kinetics, and thermal stability against oxygen release and decomposition. Density functional theory (DFT) can provide accurate baselines, but its cost limits supercell sizes, configuration sampling, and the time/length scales accessible to ab initio molecular dynamics (AIMD). Pretrained machine-learning interatomic potentials (MLIPs) offer near-DFT accuracy at far lower cost, thus enabling high-throughput evaluation and long-time molecular dynamics. However, the fidelity required for voltage thermodynamics, migration kinetics, and high-temperature decomposition is not identical, and a model that performs well on one task may be unreliable on another. In this study, eight representative pretrained MLIPs (i.e., MACE, M3GNet, CHGNet, ALIGNN, SevenNet, AlphaNet, GRACE, and Orb) were systematically benchmarked across these three cathode-relevant tasks under matched protocols.

Methods

All crystallographic prototypes were obtained from the Materials Project. All the MLIPs were used as released pretrained models without fine-tuning to reflect a "drop-in" screening scenario. For voltage profiles, four representative cathodes spanning layered oxides and polyanion frameworks were selected, i.e., NaMnO₂, LiCoO₂, NaFePO₄, and Na₃V₂(PO₄)₃. Each parent structure was expanded to a supercell containing 8-12 alkali sites. Partially (de)intercalated configurations were generated by exhaustive enumeration of alkali-vacancy patterns and symmetry-deduplicated with a space-group analysis tool. Each MLIP evaluated energies for all configurations. Formation energies were referenced to alkali-rich/poor endmembers, and lower convex hulls were constructed to obtain piecewise average voltages. Accuracy and curve-shape fidelity were quantified using metrics including mean absolute error (MAE), root mean square error (RMSE), integrated absolute error (IAE), and bias indicators.

For ion migration, Li₃Sc₂(PO₄)₃ was chosen as a representative fast-ion conductor. Molecular dynamics was performed at 600 K for 2 ns with each MLIP, and the Li self-diffusion coefficient was extracted from the mean-square displacement (MSD) via the Einstein relation in three dimensions. A fixed regression window (200-1500 ps) was applied consistently to reduce transient and finite-sampling effects.

For thermal stability, oxygen-release/decomposition was benchmarked on phosphate systems with clear stepwise pathways, i.e., MnPO₄ and FePO₄ in olivine and trigonal polymorphs. Each step was represented by balanced solid-state reactions with explicit O₂ release. Reaction energies from MLIPs were combined with an ideal-gas oxygen chemical potential in an oxygen grand-potential framework to estimate onset temperatures and cumulative O₂-evolution curves.

Results and discussion

The benchmark reveals a pronounced task dependence among pretrained MLIPs. For voltage profiles, most models reproduce the qualitative multi-plateau behavior, yet quantitative accuracy differs because voltages are sensitive to small energy differences among near-degenerate vacancy orderings that determine convex-hull vertices and plateau boundaries. Across the four cathodes, M3GNet achieves the minimum overall voltage error with a small systematic bias, followed by AlphaNet and CHGNet. GRACE is generally mid-tier, whereas Orb and ALIGNN exhibit larger offsets and shape errors. A notable system dependence occurs for LiCoO₂, where most MLIPs tend to underestimate voltages relative to the reference, indicating that layered Co-O chemistry remains a challenging regime for the existing universal pretrained models.

For ion migration in Li₃Sc₂(PO₄)₃ at 600 K, the ranking differs from the voltage benchmark. MACE and SevenNet yield diffusivities closest to the reference, with Orb and GRACE moderately higher. CHGNet and M3GNet overestimate a diffusivity by severalfold, while AlphaNet underestimates it more strongly. Importantly, ALIGNN can not reliably complete the long-timescale molecular-dynamics runs under our resource constraints, highlighting a practical limitation (memory footprint) that can matter in screening pipelines. These support the interpretation that diffusion is governed primarily by local force accuracy and barrier-region smoothness along hopping pathways, whereas voltage profiles depend on consistent ranking of many competing configurations across composition.

For thermal stability, all the MLIPs qualitatively reproduce the existence of stepwise oxygen evolution and pyrophosphate-forming decomposition, but predicted onset temperatures can deviate substantially. For MnPO₄, deviations span a wide range. ALIGNN and M3GNet provide the smallest deviations for this system, while AlphaNet and CHGNet delay oxygen release. Across the full phosphate set, M3GNet and MACE deliver the optimum overall agreement with experimental step positions and temperatures, and GRACE often captures intermediate steps with moderate errors. The results indicate that generalization to high-temperature, oxygen-deficient pathways remains sensitive to both training coverage and architectural bias.

Conclusions

This work established a unified, extensible benchmark for comparing pretrained MLIPs on cathode-relevant thermodynamics, kinetics, and high-temperature stability. No single MLIP could be universally optimal. M3GNet was most reliable for voltage prediction on the tested cathodes, MACE and SevenNet were strongest for long-time MSD-based diffusion in Li₃Sc₂(PO₄)₃, and M3GNet together with MACE best captured oxygen-release/decomposition trends in representative phosphate systems. The proposed workflow could provide a practical guidance for task-aware MLIP selection and a foundation for larger, more decoupled benchmarks in future studies.

Key words

machine-learning interatomic potentials / sodium-ion batteries / lithium-ion batteries / voltage profile / ion diffusion / thermal stability

引用本文

蒋冰鉴, 杨涛, 路宽, 张艺馨. 机器学习势在正极材料电化学性质预测中的评测. 硅酸盐学报, 2026 , 54 (7) : 2338 -2351 . DOI: 10.14062/j.issn.0454-5648.20250871

Bingjian JIANG, Tao YANG, Kuan LU, Yixin ZHANG. Comparative Evaluation of Machine-Learning Potentials for Electrochemical Properties of Cathodes[J]. Journal of the Chinese Ceramic Society, 2026 , 54 (7) : 2338 -2351 . DOI: 10.14062/j.issn.0454-5648.20250871

基金

收起

国家自然科学基金项目(22272009)

参考文献

收起

文献

收起

参考文献引证文献

排序方式：

2026年第54卷第7期

PDF下载

引用本文

BibTeX

文章信息

doi: 10.14062/j.issn.0454-5648.20250871

接收时间：2025-11-28
首发时间：2026-10-22
出版时间：2026-04-10

补充材料

相关文章

文章信息

作者

出版历史

收稿日期：2025-11-28
修回日期：2025-12-24

基金

国家自然科学基金项目(22272009)

作者信息

^1．北京信息科技大学计算机学院，北京 100101

^2．北京信息科技大学，北京材料基因工程高精尖创新中心，北京 100101

^3．中国科学院山西煤炭化学研究所，煤炭高效低碳利用全国重点实验室，太原 030001

^4．宁夏大学化学化工学院，银川 750021

通讯作者:

杨涛（1980—），女，博士，助理研究员。

参考文献

分享链接

https://castjournals.cast.org.cn/joweb/gsyxb/CN/10.14062/j.issn.0454-5648.20250871

分享至

全文二维码

扫描看全文

引用本文

BibTeX

本文的引用情况

2种不同金属材料的力学参数

科 Family	属数 Number of genus	种数 Number of species	占总种数比例 Percentage of total species (%)	属 Genus	种数 Number of species	占总种数比例 Percentage of total species (%)
鹅膏菌科Amanitaceae	2	11	5.26	鹅膏菌属 Amanita	10	4.78
小菇科 Mycenaceae	2	12	5.74	丝盖伞属 Inocybe	5	2.39
多孔菌科 Polyporaceae	8	14	6.70	蜡蘑属 Laccaria	5	2.39
红菇科 Russulaceae	3	23	11.00	小皮伞属 Marasmius	6	2.87
				小菇属 Mycena	11	5.26
				光柄菇属 Pluteus	5	2.39
				红菇属 Russula	17	8.13
				栓菌属 Trametes	5	2.39

关闭全屏

BibTeX
EndNote
RefWorks
TxT