A long-standing goal of science is to accurately solve the Schrödinger equation for large molecular systems. The poor scaling of current quantum chemistry algorithms on classical computers imposes an effective limit of about a few dozen atoms for which we can calculate molecular electronic structure. We present a machine learning (ML) method to break through this scaling limit and make quantum chemistry calculations of very large systems possible. We show that Euclidean Neural Networks can be trained to predict the electron density with high fidelity from limited data. Learning the electron density allows us to train a machine learning model on small systems and make accurate predictions on large ones. We show that this ML electron density model can break through the quantum scaling limit and calculate the electron density of systems of thousands of atoms with quantum accuracy.
Enhancing molecular dynamics with equivariant machine-learned densities
BIFOLD and Machine Learning Group, Technische Universität Berlin（BIFOLD与机器学习组，柏林技术大学）；Department of Chemistry, New York University（纽约大学化学系）；Department of Artificial Intelligence, Korea University（韩国大学人工智能系）；Max-Planck-Institut für Informatik（马克斯·普朗克研究所（信息学））；Department of Physics and Astronomy, University of California, Irvine（加州大学 Irvine 分校物理与天文学系）；Department of Chemistry, University of California, Irvine（加州大学 Irvine 分校化学系）；Courant Institute of Mathematical Sciences, New York University（纽约大学数学科学学院）；NYU-ECNU Center for Computational Chemistry at NYU Shanghai（纽约大学上海计算化学中心）
Learned Free-Energy Functionals from Pair-Correlation Matching for Dynamical Density Functional Theory
TU Munich（慕尼黑工业大学）；Munich Center for Machine Learning（慕尼黑机器学习中心）；Van’t Hoff Institute for Molecular Sciences, University of Amsterdam（阿姆斯特丹大学范特霍夫分子科学研究所）；Informatics Institute, University of Amsterdam（阿姆斯特丹大学信息学研究所）；Institute for Theoretical Physics, Utrecht University（乌得勒支大学理论物理研究所）
All-electron machine-learned orbital-free density functional for periodic CHNO systems
Interdisciplinary Center for Scientific Computing (IWR), Heidelberg University（海德堡大学跨学科科学计算中心）；Centre for Science at Extreme Conditions and SUPA, School of Physics and Astronomy, University of Edinburgh（爱丁堡大学物理与天文学学院极端条件科学与SUPA中心）
University of California, Irvine（加州大学欧文分校）；Vanderbilt University（范德堡大学）；University of Basel（巴塞尔大学）；Technical University of Berlin（柏林工业大学）；Korea University（高丽大学）
Accurate and Transferable Intermolecular Potential Based on Machine-Learned Molecular Electron Density
University of Luxembourg（卢森堡大学）；Technische Universität Berlin（柏林工业大学）；Korea University（高丽大学）；Max-Planck-Institut für Informatik（马克斯·普朗克 informatics 研究所）
Constraint-aware functional cloning for stable and transferable machine-learned density functional theory
Catalan Institute of Nanoscience and Nanotechnology (ICN2)（加泰罗尼亚纳米科学与技术研究所）；Stony Brook University（石溪大学）；The New York Academy of Sciences（纽约科学院）；University of California, Irvine（加州大学尔湾分校）；Centro de Física de Materiales (CFM-MPC), CSIC-UPV/EHU（材料物理中心）
