Decomposing Chemical Space: Applications to the Machine Learning of Atomic Energies
Frederik Ø. Kjeldal, Janus J. Eriksen
备注：
21+7 pages, 6 figures. SI as an ancillary file. Version 2: All PhysNet-based results are now based on NN models trained on a combination of atomic and molecular energies (as opposed to only the former in Version 1). SI also updated with a total of four figures
We apply a number of atomic decomposition schemes across the standard QM7 dataset -- a small model set of organic molecules at equilibrium geometry -- to inspect the possible emergence of trends among contributions to atomization energies from distinct elements embedded within molecules. Specifically, a recent decomposition scheme of ours based on spatially localized molecular orbitals is compared to alternatives that instead partition molecular energies on account of which nuclei individual atomic orbitals are centred on. We find these partitioning schemes to expose the composition of chemical compound space in very dissimilar ways in terms of the grouping, binning, and heterogeneity of discrete atomic contributions, e.g., those associated with hydrogens bonded to different heavy atoms. Furthermore, unphysical dependencies on the one-electron basis set are found for some, but not all of these schemes. The relevance and importance of these compositional factors for training tailored neural network models based on atomic energies are next assessed. We identify both limitations and possible advantages with respect to contemporary machine learning models and discuss the design of potential counterparts based on atoms and the intrinsic energies of these as the principal decomposition units.
NMR Chemical Shift Computations at Second-Order Møller-Plesset Perturbation Theory Using Gauge-Including Atomic Orbitals and Cholesky-Decomposed Two-Electron Integrals
Chemical bonding concepts emerge naturally from maximally entangled atomic orbitals
Ludwig-Maximilians-Universität München（慕尼黑大学）；Munich Center for Quantum Science and Technology (MCQST)（慕尼黑量子科学与技术中心）；Donostia International Physics Center (DIPC)（圣塞巴斯蒂安国际物理中心）
Manipulation of Diatomic Molecules with 'Oriented External Electric Fields': Linear Correlations in Atomic Properties Lead to Non-Linear Molecular Responses
Obtaining transferable chemical insight from solving machine-learning classification problems: Thermodynamical properties prediction, atomic composition as good as Coulomb matrix
QT-Net: Rethinking Evaluation of AI Models in Atomic Chemical Space
Department of Computer Science and Engineering（计算机科学与工程系）；Chalmers University of Technology（楚姆勒技术大学）；University of Gothenburg（哥德堡大学）；Department of Chemistry and Chemical Engineering（化学与化工系）；Technology Research（技术研究部）；Intel Corporation（英特尔公司）；Chief Technology Office（首席技术办公室）；EMD Electronics（EMD电子公司）；Lila Sciences（Lila科学）；M Ventures（M资本）
Atomic level structure of Ge-Sb-S glasses: chemical short range order and long Sb-S bonds
Ge $_{20}$ Sb $_{10}$ S $_{65}$的结构ABMO和Ge $_{26}$ Sb $_{13}$ S $_{61}$玻璃的Ge和Sb K边结构进行了研究。对于每种组合物，大规模的结构模型，通过拟合同时衍射和EXAFS数据集的框架中的反向蒙特卡罗（RMC）模拟技术。Ge和S原子分别有4个和2个最近邻原子。这些玻璃的结构可以用化学有序网络模型来描述：Ge-S和Sb-S键总是优选的。这两种键类型充分描述了化学计量玻璃的结构，而S-S键也可以在富S组合物中找到。拉曼散射数据显示，在缺S玻璃中存在Ge-Ge，Ge-Sb和Sb-Sb键，但仅需要Ge-Sb键来拟合衍射和EXAFS数据集。很大一部分Sb-S对的键长比通常接受的共价键长（~2.45 π）长0.3-0.4 π。从这一观察结果可以推断，一部分Sb原子有超过3个S邻居。
Cholesky decomposition of two-electron integrals in quantum-chemical calculations with perturbative or finite magnetic fields using gauge-including atomic orbitals
