![abstract colorful wave vector illustration abstract colorful wave vector illustration](https://static.vecteezy.com/system/resources/previews/000/150/551/original/abstract-background-with-colorful-wave-vector-template.jpg)
Every pair of atoms ( A, B) is mapped to a block in the feature matrix, with the row dimension of the block matching the atomic orbitals of the source atom A and the column dimension matching the atomic orbitals of the destination atom B. The features T are visualized by the density matrix of the molecular system, with red color indicating positive matrix elements and blue color indicating negative matrix elements. ( D) Characteristics of the atomic orbital features considered in OrbNet-Equi. An equivariant neural network efficiently learns the mapping, yielding improved transferability at an evaluation speed that is competitive to Atomistic ML methods. ( C) In our approach, features are extracted from a highly coarse-grained QM simulation to capture essential physical interactions. ( B) Atomistic ML approaches use geometric descriptors, such as interatomic distances, angles, and directions, to bypass the procedure of solving the electronic structure problem but often require vast amounts of data to generalize toward new chemical species. ( A) Conventional ab initio quantum chemistry methods predict molecular properties based on electronic structure theory through computing molecular wave functions and interaction terms, with general applicability but at high computational cost. QM-informed ML for modeling molecular properties. We anticipate that the strategy presented here will help to expand opportunities for studies in chemistry and materials science, where the acquisition of experimental or reference training data is costly.įig. Our method also describes interactions in challenging charge-transfer complexes and open-shell systems. Despite only using training samples collected from readily available small-molecule libraries, OrbNet-Equi outperforms traditional semiempirical and machine learning–based methods on comprehensive downstream benchmarks that encompass diverse main-group chemical processes. OrbNet-Equi accurately models a wide spectrum of target properties while being several orders of magnitude faster than density functional theory. Our method, OrbNet-Equi, leverages efficient tight-binding simulations and learned mappings to recover high-fidelity physical quantities.
![abstract colorful wave vector illustration abstract colorful wave vector illustration](https://static.vecteezy.com/system/resources/previews/000/536/834/original/vector-abstract-stripes-gradient-wave-line-art.jpg)
![abstract colorful wave vector illustration abstract colorful wave vector illustration](http://www.webdesignhot.com/wp-content/uploads/2012/06/Abstract-Wave-Vector-Illustration.jpg)
By developing a physics-inspired equivariant neural network, we introduce a method to learn molecular representations based on the electronic interactions among atomic orbitals. We overcome this barrier by systematically incorporating knowledge of molecular electronic structure into deep learning. However, existing machine learning techniques are challenged by the scarcity of training data when exploring unknown chemical spaces. Predicting electronic energies, densities, and related chemical properties can facilitate the discovery of novel catalysts, medicines, and battery materials.