Quantum Chemistry in the Age of Machine Learning

Pavlo O. Dral is Full Professor at Xiamen University. He is a specialist in accelerating and improving quantum chemistry with artificial intelligence/machine learning. Together with his colleagues, he introduced and continues to develop methods such as ?-learning, AIQM1, fourdimensional spacetime atomistic artificial intelligence models, and artificial intelligence-based quantum dynamics. Pavlo Dral is also a founder of MLatom, a program package for atomistic machine learning, and a co-founder of the Xiamen Atomistic Computing Suite. His more than 40 publications were cited over 2800 times and his h-index is 22 (Google Scholar, Summer 2022). Pavlo O. Dral has won a gold medal in the 36th International Chemistry Olympiad, 2004. He did his PhD with Prof. Tim Clark at the University of Erlangen–Nuremberg in 2010–2013, postdoc with Prof. Walter Thiel at the Max Planck Institute for Coal Research in 2013–2019, and began his independent career at Xiamen University in 2019 first as an Associate Professor and from 2021 as a Full Professor. More information is available on Dral’s group website dr-dral.com.

1. Very brief introduction to quantum chemistry
2. Density functional theory
3. Semiempirical quantum mechanical methods
4. From small molecules to solid-state materials: A brief discourse on an example of carbon compounds
5. Basics of dynamics
6. Machine learning: An overview
7. Unsupervised learning
8. Neural networks
9. Kernel methods
10. Bayesian inference
11. Potentials based on linear models
12. Neural network potentials
13. Kernel method potentials
14. Constructing machine learning potentials with active learning
15. Excited-state dynamics with machine learning
16. Machine learning for vibrational spectroscopy
17. Molecular structure optimizations with Gaussian process regression
18. Learning electron densities
19. Learning dipole moments and polarizabilities
20. Learning excited-state properties
21. Learning from multiple quantum chemical methods: ?-learning, transfer learning, co-kriging, and beyond
22. Data-driven acceleration of coupled-cluster and perturbation theory methods
23. Redesigning density functional theory with machine learning
24. Improving semiempirical quantum mechanical methods with machine learning
25. Machine learning wavefunction
26. Analysis of nonadiabatic molecular dynamics trajectories
27. Design of organic materials with tailored optical properties: Predicting quantum-chemical polarizabilities and derived Quantities