AI meets Chemistry in solving electronic Schrödinger equation

[fresh_42]

TL;DR Summary

PauliNet is an AI concept to calculate the chemical behavior of molecules - more complex than hydrogen and fewer than necessary for Monte Carlo approaches

Abstract:

The electronic Schrödinger equation can only be solved analytically for the hydrogen atom, and the numerically exact full configuration-interaction method is exponentially expensive in the number of electrons. Quantum Monte Carlo methods are a possible way out: they scale well for large molecules, they can be parallelized and their accuracy has, as yet, been only limited by the flexibility of the wavefunction ansatz used. Here we propose PauliNet, a deep-learning wavefunction ansatz that achieves nearly exact solutions of the electronic Schrödinger equation for molecules with up to $30$ electrons. PauliNet has a multireference Hartree–Fock solution built in as a baseline, incorporates the physics of valid wavefunctions and is trained using variational quantum Monte Carlo. PauliNet outperforms previous state-of-the-art variational ansatzes for atoms, diatomic molecules and a strongly correlated linear $H_{10}$, and matches the accuracy of highly specialized quantum chemistry methods on the transition-state energy of cyclobutadiene, while being computationally efficient.

https://www.nature.com/articles/s41557-020-0544-y

Hermann, J., Schätzle, Z. & Noé, F. Deep-neural-network solution of the electronic Schrödinger equation. Nat. Chem. 12, 891–897 (2020). https://doi.org/10.1038/s41557-020-0544-y

Popular Science version:

https://phys.org/news/2020-12-artificial-intelligence-schrdinger-equation.html

I begin to understand what scientists meant when they said we live in exciting times. It's not all about cosmology and quantum computing. This is also the first example I saw, where AI is substantially different from a smart program code.

 

[jbsteele]

Scientists from the Friedrich-Alexander-University Erlangen-Nuremberg (FAU), Germany, have developed an AI algorithm that can solve the Schrödinger equation of the electronic structure of molecules. The Schrödinger equation describes the wave function of a particle such as an electron in a molecule and is the basis of quantum mechanics.The AI algorithm, called PauliNet, is based on deep learning and is capable of accurately solving the Schrödinger equation for molecules with up to 30 electrons. This outperforms the accuracy of other quantum chemistry methods and is much more computationally efficient. The PauliNet algorithm also incorporates physics so that it only produces valid wave functions.The results of the study have been published in Nature Chemistry and show the potential for AI to revolutionize quantum chemistry. Scientists are hopeful that this development will lead to better understanding of the quantum world, and ultimately to more accurate predictions in various applications such as drug design and materials science.

 

[jbsteele]

Scientists from the Max Planck Institute for Intelligent Systems have developed a deep-learning neural network, PauliNet, capable of near-exact solutions of the elusive Schrödinger equation. This equation, which governs the behavior of particles, is notoriously difficult to solve, even with advanced numerical methods. However, the machine learning approach of PauliNet enables efficient and accurate solutions of the equation for molecules with up to 30 electrons. This technology could open the door to unprecedented predictive capabilities in chemistry, making it easier to design new materials with desired properties. The researchers demonstrated the potential of PauliNet by using it to approximate the transition-state energy of cyclobutadiene, matching the accuracy of highly specialized quantum chemistry methods. This suggests that the AI system can be used to accurately predict the properties of molecules and materials, saving time and effort in the development of novel technologies.