Chapter “Machine Learning Methods in Photochemistry and Photophysics”

Surging efforts and fast progress in AI methods for photochemistry and photophysics make it difficult to track the current state of the art. We cover the recent developments in this field in the chapter on Machine learning methods in photochemistry and photophysics in Theoretical and Computational Photochemistry: Fundamentals, Methods, Applications and Synergy with Experimentation edited by Cristina García-Iriepa and Marco Marazzi. This chapter is rather self-contained and describes both fundamentals of machine learning and ML applications for photochemistry and photophysics, while other topics are introduced in the remainder of the book.

How rapidly the field of AI for science in the field of photochemistry and photophysics is developing, can be judged by the increasing number of reviews. Just to mention reviews with contributions from our group:

• Focus on learning excited-state properties in general: Julia Westermayr, Pavlo O. Dral, Philipp Marquetand. Learning excited-state properties. In Quantum Chemistry in the Age of Machine Learning, Pavlo O. Dral, Ed. Elsevier: 2023. DOI: 10.1016/B978-0-323-90049-2.00004-4.
• Focus on excited-state dynamics: Lina Zhang, Arif Ullah, Max Pinheiro Jr, Mario Barbatti, Pavlo O. Dral. Excited-state dynamics with machine learning. In Quantum Chemistry in the Age of Machine Learning, Pavlo O. Dral, Ed. Elsevier: 2023. DOI: 10.1016/B978-0-323-90049-2.00008-1.
• Focus on ML for both theoreticians and experimentalists: Pavlo O. Dral, Mario Barbatti*, Molecular excited states through a machine learning lens. Nat. Rev. Chem. 2021, 5, 388–405. DOI: 10.1038/s41570-021-00278-1. (blog post)

The new chapter gives an update and a unique perspective from several groups while bringing a valuable description of many technical details and ML background. It is highly recommended for those who want to start using ML in their theoretical simulations of photochemical and photophysical processes. The experts can also find their many useful nuggets of information and insight.

Reference:

• Jingbai Li, Morgane Vacher, Pavlo O. Dral, Steven A. Lopez. Machine learning methods in photochemistry and photophysics. In Theoretical and Computational Photochemistry: Fundamentals, Methods, Applications and Synergy with Experimentation, Cristina García-Iriepa and Marco Marazzi, Eds. Elsevier: 2023. DOI: 10.1016/B978-0-323-91738-4.00002-6.