发表机构
Department of Chemistry, Department of Physics, and the Indiana University Quantum Science and Engineering Center (IU-QSEC)（化学系、物理系以及印第安纳大学量子科学与工程中心（IU-QSEC））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对复杂通量化学系统AIMD模拟受限于高计算量的问题，提出图论分子碎片化框架与机器学习集成，直接模拟核力，建立协变描述符，经验证可再现动力学和结构特征，为化学动力学模拟的迁移学习奠定基础。
AI 中文摘要
复杂通量化学系统的精确从头算分子动力学（AIMD）模拟受到相关电子结构方法高计算量的严重限制。为克服这一瓶颈，我们提出一个强大的图论分子碎片化框架，与机器学习集成，以耦合簇精度直接模拟后哈特里 - 福克核力。该方法绕过自动微分在学习能量表面上的局限性，直接预测核力向量。通过将这些向量投影到片段固定的惯性主轴上，建立自然保持旋转、平移和置换不变性的协变描述符。该方法通过向量值训练协议实现了极高的参数效率，减少了一个数量级以上的可训练参数，同时无监督小批量k均值空间镶嵌算法仅使用10%到20%的参考配置构建了具有高度代表性的训练数据库。我们在高度通量的溶剂化祖德尔阳离子H₁₃O₆⁺上严格验证了这个框架。我们完全由机器学习预测的AIMD轨迹成功再现了复杂的动力学特征和关键结构特征，包括径向分布函数和速度自相关功率谱。最终，这个可扩展、可系统改进的框架弥合了高级相关波函数理论与长时间尺度反应采样之间的差距，为现代化学动力学模拟中受大语言模型启发的高级迁移学习奠定了基础。
英文摘要
Accurate ab initio molecular dynamics (AIMD) simulations of complex, fluxional chemical systems are severely limited by the high computational scaling of correlated electronic structure methods. To overcome this bottleneck, we present a robust, graph-theoretic molecular fragmentation framework integrated with machine learning to directly model post-Hartree-Fock nuclear forces at coupled cluster accuracy. Bypassing the limitations of automatic differentiation on learned energy surfaces that may struggle with link-atom Jacobians, our approach directly predicts nuclear force vectors. By projecting these vectors onto fragment-fixed principal axes of inertia, we establish co-variant descriptors that naturally preserve rotational, translational, and permutational invariance. The methodology achieves exceptional high parameter efficiency through a vector-valued training protocol that reduces trainable parameters by over an order of magnitude, while an unsupervised mini-batch k-means space tessellation algorithm constructs highly representative training databases using only 10% to 20% of reference configurations. We rigorously validated this framework on the highly fluxional solvated Zundel cation H_{13}O_6^+ ). Our fully machine-learning-predicted AIMD trajectories successfully reproduced complex dynamical signatures and key structural characteristics, including radial distribution functions and the velocity autocorrelation power spectrum. Ultimately, this scalable, systematically improvable framework bridges the gap between high-level correlated wavefunction theories and long-timescale reactive sampling, laying the foundation for advanced, LLM-inspired transfer learning in modern chemical dynamics simulations.
