发表机构
Alpha Ladder Particle Pte. Ltd.（Alpha Ladder Particle 私人有限公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
SCALE是一种物理驱动、真实数据校准的混合学习架构，通过确定性算子与图Transformer结合，在储氢材料预测中实现高精度（MAE 0.0582 wt%）并将筛选成本降低约1亿倍。
AI 中文摘要
能源系统在安全性、可负担性、韧性和可持续性方面面临汇聚性压力，这催生了对可部署能源材料进行更快发现的需求。本文介绍了SCALE（面向能源材料的仿真校准摊销学习），这是一种基于物理、经真实世界数据校准的学习架构，它将确定性科学算子、实验校准、扩展的校准标签生成以及Transformer规模推理连接起来。SCALE将选定的高成本机理计算和实测证据转化为可复用的模型，用于快速筛选、排序、逆向设计和主动学习。我们构建了该框架，识别了十种基于方法的应用场景，并展示了SCALE在固态金属氢化物储氢容量预测中的应用。在该实现中，氢化物相平衡容量算子针对381个实测ML-HydPARK容量锚点进行校准，并用于生成5000个候选条件原型教师标签。一种晶体学锚定的周期图表示保留了原子位点、周期邻居关系以及仅用分子式编码所缺失的局部金属环境。一个具有290万参数的边偏置图Transformer以五折替代保真度再现了校准后的教师标签，MAE为0.0582 wt% H2，RMSE为0.0833 wt% H2，R2=0.9927，Pearson r=0.9963。事后注意力分析表明，SCALE学习了与既有氢化物化学一致的化学组织元素分组和金属-金属关系，而无需化学基团标签作为监督。一旦训练完成，SCALE将百万候选评估从重复的确定性工作流执行转变为批量学习推理，将每个候选的筛选成本降低约10^7至10^8倍，同时保持与仿真和实验证据的联系。
英文摘要
Energy systems face converging pressures for security, affordability, resilience, and sustainability, creating a need for faster discovery of deployable energy materials. Here we introduce SCALE (Simulation-Calibrated Amortized Learning for Energy Materials), a physics-grounded, real-world-data-calibrated learning architecture that connects deterministic scientific operators, experimental calibration, expanded calibrated label generation, and transformer-scale inference. SCALE converts selected high-cost mechanistic computation and measured evidence into reusable models for rapid screening, ranking, inverse design, and active learning. We formulate the framework, identify ten method-based application regimes, and demonstrate SCALE for solid-state metal-hydride hydrogen-storage capacity prediction. In this implementation, a hydride phase-equilibrium capacity operator is calibrated against 381 measured ML-HydPARK capacity anchors and used to generate 5,000 candidate-condition-prototype teacher labels. A crystallographically anchored periodic-graph representation preserves atomic sites, periodic neighbor relationships, and local metal environments absent from formula-only encodings. An edge-biased graph transformer with 2.90 million parameters reproduces calibrated teacher labels with five-fold surrogate fidelity of MAE 0.0582 wt% H2, RMSE 0.0833 wt% H2, R2 = 0.9927, and Pearson r = 0.9963. Post hoc attention analysis suggests that SCALE learns chemically organized element groupings and metal-metal relationships consistent with established hydride chemistry, without chemistry-group labels as supervision. Once trained, SCALE shifts million-candidate evaluation from repeated deterministic workflow execution to batched learned inference, reducing per-candidate screening cost by approximately 10^7-10^8 while retaining links to simulation and experimental evidence.
Comments16 pages, 5 figures
