AI 中文总结
研究旨在设计高效的机器学习原子间势，提出TRACE架构结合原子簇扩展密度相关性与局部多头交叉注意力，在多晶型铯碘化铅、液态水等体系的训练测试中表现良好，能捕获多种物质特性。
AI 中文摘要
设计机器学习原子间势需要精确表示复杂的多体相互作用以及可扩展分子动力学所需的效率。我们引入了Transformer原子簇扩展（TRACE），这是一种节能架构，它将原子簇扩展密度相关性与局部多头交叉注意力相结合。相关性为每个中心形成一个O(3)等变状态，该状态查询张量邻居特征，这些特征是物种和几何形状的固定函数。原子之间不传递学习状态。在笔记本电脑MacBook-M1上，我们针对多晶型铯碘化铅、液态水和分子内甲基迁移对TRACE进行了训练和测试。对于铯碘化铅，TRACE再现了四种多晶型的r$^2$SCAN+rVV10排序，并给出了经典的边共享六方非钙钛矿（$\delta$）到角共享立方钙钛矿（$\alpha$）的吉布斯自由能交叉点约为580K，接近实验观测值约600K。通过采用增强采样跨越高能垒，相同的TRACE势成功捕获了$\delta$到$\alpha$钙钛矿转变，无需任何强化学习。在一组减少的CCSD(T)构型上训练的水势将第一个氧-氧最大值置于2.85Å，而实验值为2.80Å。对于2,2-二甲基异吲哚中的气相甲基迁移，伞形采样产生的活化自由能为$27.92\pm0.03$kcal mol$^{-1}$，与实验测量值$29.2\pm1.1$kcal mol$^{-1}$密切一致。在这些不同的基准测试中，一个单一的统一架构成功捕获了多物种结晶、液体结构、相图和化学反应性。
英文摘要
Designing machine-learning interatomic potentials involves achieving the precise representation of complex many-body interactions alongside the efficiency required for scalable molecular dynamics. We introduce Transformer Atomic Cluster Expansion (TRACE), an energy-conserving architecture that combines atomic cluster expansion density correlations with local multihead cross-attention. The correlations form an O(3)-equivariant state for each center, which queries tensorial neighbor features that remain fixed functions of species and geometry. No learned state is passed between atoms. On a laptop MacBook-M1, we train and test TRACE for polymorphic cesium lead iodide, liquid water, and intramolecular methyl migration against experiments. For cesium lead iodide, TRACE reproduces the r$^2$SCAN+rVV10 ordering of four polymorphs and gives a classical edge-sharing hexagonal non-perovskite($δ$) to corner-sharing cubic perovskite($α$) Gibbs-free-energy crossing $\simeq$580K near the experimental observations of $\simeq$600K. By employing enhanced sampling to cross high energy barriers, the same TRACE potential successfully captures the $δ$-to-$α$ perovskite transformation without any reinforcement learning. A water potential trained on a reduced set of CCSD(T) configurations places the first oxygen--oxygen maximum at 2.85~Å, compared to the experimental value of 2.80~Å. For the gas-phase methyl migration in 2,2-dimethylisoindene, umbrella sampling yields an activation free energy of $27.92\pm0.03$~kcal~mol$^{-1}$, in close agreement with the experimental measurement of $29.2\pm1.1$~kcal~mol$^{-1}$. Across these diverse benchmarks, a single unified architecture successfully captures multi-species crystallization, liquid structures, phase diagrams, and chemical reactivity.
