BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Data-Driven UQ-Enhanced Approaches for Materials Design - Lori Gra
 ham-Brady (Johns Hopkins University)
DTSTART:20230713T150000Z
DTEND:20230713T160000Z
UID:TALK193939@talks.cam.ac.uk
DESCRIPTION:Design of materials in a high-throughput setting requires mode
 ling approaches that can provide rapid assessments to support real-time de
 cisions. Machine learning (ML) emerges as an excellent tool to support suc
 h models. While ML models may lack the accuracy and insights delivered by 
 full physics-based computational solutions\, these approaches are often pe
 rfectly sufficient to identify material chemistries and microstructures th
 at merit further exploration. In particular\, these data-driven ML models 
 are a very sensible approach in the context of a high-throughput experimen
 tation paradigm that provides lower quality data in statistically signific
 ant quantities. By providing rapid assessments to support screening of new
  materials\, ML models support real-time decision-making for control and o
 ptimization of high-throughput processes on the path to materials design. 
 A current facility in this regard is under development at Johns Hopkins Un
 iversity &ndash\; the AI for Materials Design (AIMD) facility\, which high
 lights some of the challenges\, pitfalls and opportunities inherent in an 
 integrated high-throughput and automated materials design framework. The r
 ole of ML models in guiding this automated materials design is highlighted
  and discussed in the context of a few example applications.
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR