BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Modelling of Complex Energy Materials with Machine Learning - Nong
 nuch Artrith\, Utrecht University
DTSTART:20211018T153000Z
DTEND:20211018T160000Z
UID:TALK162301@talks.cam.ac.uk
CONTACT:Dr Christoph Schran
DESCRIPTION:The properties of materials for energy applications\, such as 
 heterogeneous catalysts and battery materials\, often depend on complicate
 d chemical compositions and complex structural features including defects 
 and disorder. This complexity makes the direct modelling with first princi
 ples methods challenging. Machine-learning (ML) potentials trained on firs
 t principles reference data enable linear-scaling atomistic simulations wi
 th an accuracy that is close to the reference method at a fraction of the 
 computational cost. ML models can also be trained to predict the outcome o
 f simulations or experiments\, bypassing explicit atomistic modelling alto
 gether.\n\nHere\, I will give an overview of our contributions to the deve
 lopment of ML potentials based on artificial neural networks (ANNs) [1-3] 
 and applications of the method to challenging materials classes including 
 metal and oxide nanoparticles\, amorphous phases\, and interfaces [4-5]. F
 urther\, I will show how large computational and small experimental data s
 ets can be integrated for the ML-guided discovery of catalyst materials [6
 ]. These examples show that the combination of first-principles calculatio
 ns and ML models is a useful tool for the modelling of nanomaterials and f
 or materials discovery. All data and models are made publicly available. T
 o promote Open Science\, we also\nformulated guidelines for the publicatio
 n of ML models for chemistry that aim at transparency and reproducibility 
 [7].\n\n1. N. Artrith and A. Urban\, Comput. Mater. Sci.\, 2016\, 114\, 13
 5.\n\n2. N. Artrith\, A. Urban\, and G. Ceder\, Phys. Rev. B\, 2017\, 96\,
  014112.\n\n3. A. Cooper\, J. Kästner\, A. Urban\, and N. Artrith\, npj C
 omput. Mater.\, 2020\, 6\, 54.\n\n4. N. Artrith and A.M. Kolpak\, Nano Let
 t.\, 2014\, 14 2670.\n\n5. N. Artrith\, J. Phys. Energy\, 2019\, 1\, 03200
 2.\n\n6. N. Artrith\, Z. Lin\, and J. G. Chen\, ACS Catal.\, 2020\, 10\, 9
 438\; N. Artrith\, Matter 3 (2020) 985–986.\n\n7. N. Artrith\, K. Butler
 \, F.X. Coudert\, S. Han\, O. Isayev\, A. Jain\, and A. Walsh\, Nat. Chem.
  13 (2021) 505–508.
LOCATION:https://zoom.us/j/92447982065?pwd=RkhaYkM5VTZPZ3pYSHptUXlRSkppQT0
 9
END:VEVENT
END:VCALENDAR