"AI in chemistry and beyond: Highlights in the field" seminar "Deep learning for photochemical reaction discovery and targeted molecular design" by Julia Westermayr

Photochemical simulations are powerful tools to study the light-induced breaking and formation of bonds in molecules and materials and can provide a deeper understanding of the underlying mechanisms that are also crucial to deliver sustainable photocatalysis and efficient energy materials. However, existing limitations of conventional techniques, such as high computational costs and low transferability to systems with more than a few dozen atoms, mean that we currently cannot address the most interesting problems in materials science, photochemistry, and biology [1].  
In this talk, I will show how artificial intelligence can be used to overcome the current limitations of photochemical simulations. I will demonstrate that photodynamics can be sped up by machine learning to allow simulations on experimentally relevant time scales [2,3] and high-throughput screening for the property-driven design of novel molecules [4,5]. 
 
[1] J. Westermayr, P. Marquetand Chem. Rev. 121(16), 9873-9926 (2021). 
[2] J. Westermayr, M. Gastegger, M. Menger, S. Mai, L. González, P. Marquetand Chem. Sci. 10, 8100-8107 (2019). 
[3] J. Westermayr, M. Gastegger, D. Vörös, L. Panzenböck, F. Jörg, L. González, P. Marquetand, Nat. Chem., 14, 914-919 (2022).
[4] J. Westermayr and R. J. Maurer, Chem. Sci. 12, 10755-10764 (2021).  
[5] J. Westermayr, J. Gilkes, R. Barrett, R. J. Maurer, arXiv:2207.01476 (2022).