A deep neural network for molecular wave functions in quasi-atomic minimal basis representation
This work addresses computational efficiency challenges in quantum chemistry for researchers, but it is incremental as it adapts an existing neural network model to a specific basis representation.
The paper tackles the problem of decoupling predictive accuracy from numerical bottlenecks in electronic structure calculations by adapting a deep neural network model for molecular wave functions in a quasi-atomic minimal basis representation, achieving accurate predictions of orbital energies and wavefunctions for organic molecules with 5 to 13 heavy atoms and outperforming the original method in accuracy and scaling for larger molecules.
The emergence of machine learning methods in quantum chemistry provides new methods to revisit an old problem: Can the predictive accuracy of electronic structure calculations be decoupled from their numerical bottlenecks? Previous attempts to answer this question have, among other methods, given rise to semi-empirical quantum chemistry in minimal basis representation. We present an adaptation of the recently proposed SchNet for Orbitals (SchNOrb) deep convolutional neural network model [Nature Commun. 10, 5024 (2019)] for electronic wave functions in an optimised quasi-atomic minimal basis representation. For five organic molecules ranging from 5 to 13 heavy atoms, the model accurately predicts molecular orbital energies and wavefunctions and provides access to derived properties for chemical bonding analysis. Particularly for larger molecules, the model outperforms the original atomic-orbital-based SchNOrb method in terms of accuracy and scaling. We conclude by discussing the future potential of this approach in quantum chemical workflows.