BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Machine Learning for Molecular Spectra and Solvent Effects - Micha
 el Gastegger\, Technische Universität Berlin
DTSTART:20210614T160000Z
DTEND:20210614T163000Z
UID:TALK160912@talks.cam.ac.uk
CONTACT:Bingqing Cheng
DESCRIPTION:Machine learning is emerging as a versatile tool in quantum ch
 emistry. It offers access to force fields\ncombining the accuracy of high-
 level electronic structure methods with excellent computational\nefficienc
 y. In this talk\, I will present how machine learning can be used to const
 ruct models of\nmolecular potential energy surfaces and properties. By inc
 luding equivariant components it is\nfurthermore possible to enhance accur
 acy and data-efficiency. I then explore how these models can be\nextended 
 to capture a wide range of physical phenomena by introducing a dependence 
 on external\nfields. This makes possible to simultaneously predict differe
 nt types of molecular spectra such as\ninfrared and Raman\, as well as che
 mical shifts. This approach also offers a simple way to account for\nexter
 nal influences in the form of explicit and implicit solvation environments
 \, e.g. in the context of\nQM/MM simulations. Finally\, I show how the ful
 ly analytic nature of the model can be leveraged to\ndesign specific chemi
 cal environments.
LOCATION:virtual ZOOM meeting ID: 263 591 6003\, Passcode: 000042\, https:
 //us02web.zoom.us/j/2635916003?pwd=ZlBEQnRENGwxNmJGMENGMWxjak5nUT09
END:VEVENT
END:VCALENDAR