BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:FAIRmat Seminar with Janine George
DTSTART:20250605T090000Z
DTEND:20250605T100000Z
DTSTAMP:20260713T223700Z
UID:indico-event-38@events.fairmat-nfdi.eu
CONTACT:fairmat-events@physik.hu-berlin.de
DESCRIPTION:Materials Design Using Chemical Heuristics\, Workflows\, and M
 achine LearningThe FAIRmat Seminar series continues with a talk by Dr. Jan
 ine George\, head of the junior research group "Computational Materials De
 sign" at BAM and professor for Materials Informatics at the FSU Jena. Abs
 tract:Bonds and local atomic environments are key descriptors of material 
 properties\, used to establish design rules and heuristics\, and serve as 
 descriptors in machine-learned interatomic potentials and the general mach
 ine learning of material properties.[1] Software implementations such as 
 ChemEnv and LobsterEnv identify local atomic environments based on geometr
 ical characteristics and quantum-chemical bonding analysis (here using Cry
 stal Orbital Hamilton Populations as computed with LOBSTER[2]). Fully auto
 mated workflows and analysis tools now enable large-scale quantum-chemical
  bonding analysis.[3\,4] The first part of the lecture will demonstrate ho
 w these tools help develop new machine-learning models and intuitive under
 standings of material properties.[5\,6] New universal machine-learned int
 eratomic potentials\, such as MACE-MP-0\, have been developed.[7] The seco
 nd part of the lecture will showcase how these potentials\, combined with 
 DFT\, can accelerate research. It will focus on the interplay between DFT 
 and machine-learned interatomic potentials\, presenting automated workflow
 s for training\, fine-tuning\, and benchmarking these potentials\, impleme
 nted in our software autoplex. Additionally\, it will show how to train n
 ew interatomic potentials from scratch by exploring potential energy surfa
 ces\, with the potential to enhance current universal machine-learned pote
 ntials.[8] The lecture will also discuss the trend toward automation in c
 omputational materials science and our recent contributions.[9\,10][1] J. 
 George and G. Hautier\, Trends Chem. 2021\, 3\, 86. [2] R. Nelson\, C. Er
 tural\, J. George\, et al.\, J. Comput. Chem. 2020\, 41\, 1931. [3] J. Ge
 orge\, G. Petretto\, A. Naik\, et al.\, ChemPlusChem 2022\, 87\, e20220012
 3. [4] A. A. Naik\, K. Ueltzen\, C. Ertural\, et al.\, J. Open Source Sof
 tw. 2024\, 9\, 6286. [5] K. Ueltzen\, A. Naik\, C. Ertural\, et al.\, in 
 preparation\, 2024. [6] A. A. Naik\, C. Ertural\, N. Dhamrait\, et al.\, 
 Sci Data 2023\, 10\, 610. [7] I. Batatia\, P. Benner\, Y. Chiang\, et al.
 \, arXiv 2024\, DOI: 10.48550/arXiv.2401.00096. [8] Y. Liu\, J. D. Morrow
 \, C. Ertural\, et al.\, arXiv 2024\, DOI: 10.48550/arXiv.2412.16736. [9]
  A. S. Rosen\, M. Gallant\, J. George\, et al.\, J. Open Source Softw. 202
 4\, 9\, 5995. [10] A. M. Ganose\, H. Sahasrabuddhe\, M. Asta\, et al.\, C
 hemRxiv 2025\, DOI: 10.26434/chemrxiv-2025-tcr5h. Join us for this engagi
 ng discussion in person at the Center for the Science of Materials Berlin 
 or online. Registration is required for online participation.\n\nhttps://e
 vents.fairmat-nfdi.eu/event/38/
IMAGE;VALUE=URI:https://events.fairmat-nfdi.eu/event/38/logo-1943420652.pn
 g
LOCATION:2.049 (Center for the Science of Materials Berlin (CSMB))
URL:https://events.fairmat-nfdi.eu/event/38/
END:VEVENT
END:VCALENDAR