BEGIN:VCALENDAR
VERSION:2.0
METHOD:PUBLISH
CALSCALE:GREGORIAN
PRODID:-//WordPress - MECv7.32.0//EN
X-ORIGINAL-URL:https://csmb.hu-berlin.de/
X-WR-CALNAME:CSMB
X-WR-CALDESC:Center for the Science of Materials Berlin
X-WR-TIMEZONE:Europe/Berlin
BEGIN:VTIMEZONE
TZID:Europe/Berlin
X-LIC-LOCATION:Europe/Berlin
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20260329T030000
RRULE:FREQ=YEARLY;BYMONTH=03;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20261025T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=4SU
END:STANDARD
END:VTIMEZONE
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-PUBLISHED-TTL:PT1H
X-MS-OLK-FORCEINSPECTOROPEN:TRUE
BEGIN:VEVENT
CLASS:PUBLIC
UID:MEC-cc8090c4d2791cdd9cd2cb3c24296190@csmb.hu-berlin.de
DTSTART;TZID=Europe/Berlin:20241011T130000
DTEND;TZID=Europe/Berlin:20241011T150000
DTSTAMP:20240930T103552Z
CREATED:20240930
LAST-MODIFIED:20240930
PRIORITY:5
SEQUENCE:43
TRANSP:OPAQUE
SUMMARY:Uncertainty-aware molecular dynamics from Bayesian active learning for phase transformations and thermal transport in SiC
DESCRIPTION:Join us at the next Colloquium@T2P on\nUncertainty-aware molecular dynamics from Bayesian active learning for phase transformations and thermal transport in SiC\nDr. Yu Xie\nMicrosoft AI4Science Berlin // Email: mailto:yuxie1@microsoft.com ( mailto:mailto:yuxie1@microsoft.com )\nAbstract:\nMachine learning interatomic force fields are promising for combining high computational efficiency and accuracy in modeling quantum interactions and simulating atomistic dynamics. Active learning methods have been developed to train force fields efficiently and automatically. Among them, Bayesian active learning utilizes principled uncertainty quantification to make data acquisition decisions. In this talk, we present our development of a general Bayesian active learning workflow, where the force field is constructed from a sparse Gaussian process regression model based on atomic cluster expansion descriptors. Orders of magnitude of speedup is achieved by the development of an approximate mapping method, and the code implementation of GPU acceleration. We demonstrate the autonomous active learning workflow by training a Bayesian force field model for silicon carbide (SiC) polymorphs in only a few days of computer time and show that pressure-induced phase transformations are accurately captured. The resulting model exhibits close agreement with both ab initio calculations and experimental measurements, and outperforms existing empirical models on vibrational and thermal properties. The active learning workflow readily generalizes to a wide range of material systems and accelerates their computational understanding.\nShort Bio:\nDr. Yu Xie is a senior researcher at Microsoft AI for Science in Berlin. She obtained PhD from Harvard University, working with Prof. Boris Kozinsky, with a focus of development of machine learning force field and Bayesian active learning using kernel-based method, and its applications in molecular dynamics simulations of phase transitions of materials.\n\nThe talk will also be broadcast via Zoom:\nZoom Link: https://hu-berlin.zoom-x.de/j/63972785525?pwd=oJlOzIouJmLO5x5QLxIsyoIsXC3tbb.1 ( https://hu-berlin.zoom-x.de/j/63972785525?pwd=oJlOzIouJmLO5x5QLxIsyoIsXC3tbb.1 )\nMeeting ID: 639 7278 5525\nPassword: 676366\n \n \n
URL:https://csmb.hu-berlin.de/events/uncertainty-aware-molecular-dynamics/
LOCATION:Zum Großen Windkanal 2, 12489 Berlin
ATTACH;FMTTYPE=image/jpeg:https://csmb.hu-berlin.de/wp-content/uploads/2024/09/2024-10-11-Xie.jpg
END:VEVENT
END:VCALENDAR