Seminar

Date 2020-12-08 
Time 16:00 
Title Machine learning in materials informatics: applications and prospects 

■ 제 목:  Machine learning in materials informatics: applications and prospects

 

 연 사:  김치호 박사 (GIT )           

 

■  일 시:  2020년 12월 8(화) 오후 4시

 

■ Host : 이혁모 교수  

 

■ 참가자 접속정보 (3:50분까지 참가를 부탁드립니다)   

      접속 링크: https://kaist.zoom.us/j/8080757553 

      ID: 808 075 7553

      비밀번호: 2020mse

 

 Abstract : 

   The Materials Genome Instiative (MGI) has heralded a sea change in the philosophy of materials design.  In an increasing number of applications, the successful deployment of novel materials has benefited from the use of computational, experimental, and informatics methodologies.  Here, we describe the roles played by computational and experimental data generation and capture, fingerprinting, machine-learning-based property prediction models, and algorithms for designing materials, especially polymers, meeting target property requirements.  Challenges that remain will be examined, and systematic steps that may be taken to extend the applicability of such informatics efforts to a wide range of technological domains will be discussed.  These include strategies to deal with the data bottleneck, new methods to represent polymer morphology and processing conditions, and the applicability of emerging algorithms for design.