Highlight Seminar

TYC Highlight Seminar

Click the title to see a recording of the event:

Finding surface structure with evolutionary algorithms and reinforcement learning

Bjørk Hammer - Aarhus University

Thursday 11 March 2021
Time: 15:00 - 16:00 GMT
Venue: Zoom

https://ucl.zoom.us/j/95700258318?pwd=T2ZNc0E4VlNnK2gwMDRJZE0xTmJkUT09

Meeting ID: 957 0025 8318
Passcode: TYCHighlig
Contact: Johannes Lischner

Atomistic simulations of the physico-chemical processes at inorganic surfaces often require knowledge of the energetically most optimal state of the surfaces. In this talk, examples are given of intricate surface reconstructions and surprising shapes assumed by metal nano-particles supported on oxide surfaces. The focus of the talk will be on how to identify such optimal structure given a costly total energy method as implemented in an electronic structure program, typicallyusing density functional theory (DFT). A number of approaches will be presented. 1) A pure evolutionary approach in which new structural candidates are created by random cross-over and mutation operations, 2) a machine learned-enhanced evolutionary approach in which an on-the-fly learned surrogate energy landscape directs the candidate production, and finally 3) a pure reinforcement learning approach in which image recognition via a convolutional neural network is used to build up rational knowledge about the energy landscape, that eventually leads to the construction of globally optimal structure.

 

[1] Evolutionary approach (EA): Phys. Rev. Lett. 108, 126101 (2012).

[2] ML assisted EA: Phys. Rev. Lett. 124, 086102 (2020) and https://gofee.au.dk

[3] Reinforcement learning:  Phys. Rev. B, 102, 075427 (2020).

6yBGvF_web.jpg

Follow @tyc_london for updates from the Thomas Young Centre.