发表机构
Massachusetts Institute of Technology; Emory University; Honda Research Institute USA（麻省理工学院; 埃默里大学; 美国本田研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出等变网络MEHnet-MG，以单次DFT计算成本实现主族元素的耦合团精度分子性质预测，可外推至更大体系，解决了耦合团理论精度高但计算成本过高的问题。
AI 中文摘要
耦合团（Coupled-cluster）理论是分子电子结构性质的精度标准，但计算规模增长过快，难以常规应用；而密度泛函理论（DFT）计算成本低，但存在系统性偏差。我们通过单一等变网络MEHnet-MG解决了这一权衡问题，该网络基于一次低成本的B3LYP/def2-SVP计算预测有效单电子哈密顿量，并从中推导得到一系列性质（能量、光学带隙、偶极矩、四极矩、极化率、Mulliken原子电荷、Mayer键级），覆盖9种主族元素，包括研究较少的磷、硫、氯化学体系，达到耦合团精度。模型在内部新数据集上训练，该数据集包含9种元素所有性质的CCSD(T)级计算标签。在保留的测试集上，相对于半局域、杂化和双杂化DFT（以复合CCSD(T)/cc-pVTZ为基准），该模型将每种性质的误差降低了3.8至230倍，且每个分子仅增加约25毫秒的运行时间，以单次DFT计算的成本实现了耦合团质量的预测。关键在于，该模型架构通过从预测的哈密顿量推导所有性质而非汇集原子特征，构建了正确的规模缩放特性：在π共轭低聚噻吩上，它在有限场CCSD极化率和EOM-CCSD光学带隙上达到约2%的精度，对应最大规模为44和37个原子，此时单个CCSD场点的计算成本已约为模型全部推理成本的500倍，并将校正后的趋势外推至58个原子的链，而基于汇集特征的架构在该区域因自身结构缺陷失效。因此，准确的外推由模型的归纳偏置决定，而非训练数据。
英文摘要
Coupled-cluster theory defines the accuracy standard for molecular electronic-structure properties but scales too steeply for routine application, whereas density-functional theory is affordable yet systematically biased. We resolve this trade-off with a single equivariant network, HARP (Hamiltonian Read-out for Properties), that predicts an effective one-electron Hamiltonian from one inexpensive B3LYP/def2-SVP calculation and derives a broad suite of properties from it (energy, optical gap, dipole, quadrupole, polarizability, Mulliken atomic charges, and Mayer bond orders) at coupled-cluster accuracy across nine main-group elements, including the under-served phosphorus, sulfur, and chlorine chemistries. The model is trained on a new in-house dataset of multi-property labels computed at the CCSD(T) level for all nine elements. On a held-out test set, it reduces the error of every property by a factor of 3.8 to 270 relative to semi-local, hybrid, and double-hybrid DFT (referenced to composite CCSD(T)/cc-pVTZ), while adding only ~0.1 s wall time per molecule, delivering coupled-cluster-quality predictions at the cost of a single DFT calculation. Critically, deriving every property from a predicted Hamiltonian rather than pooling per-atom features builds the correct size-scaling into the model architecture: on pi-conjugated oligothiophenes it matches finite-field CCSD polarizability to ~1% and the EOM-CCSD optical gap to ~3% at the largest sizes where those references remain affordable (44 and 37 atoms, where a single CCSD field point already costs ~500x the model's entire inference) and extrapolates the corrected trends to 58-atom chains, a regime where pooling-based architectures fail by construction. Accurate extrapolation is therefore set by the model's inductive bias rather than by the training data.
Comments13 pages, 5 figures, 2 tables; Supplementary Information (22 pages) appended. v2: model renamed from MEHnet-MG to HARP; results at the final released checkpoint; SI added; code and weights at https://github.com/He-Wenhao/HARP
