Work

Machine learning of phase diagrams

Year: 2022

Type: article

Abstract: A ML strategy is presented to infer the free energy state functions by using phase diagram images as input, resulting in optimized properties 3–5 orders of magnitude faster and dramatically increased accuracy as compared to current approaches.

Source: Materials Advances

DOI: 10.1039/d2ma00524g

Authors: J. Lund, H. Wang, R. D. Braatz, R. E. García

Institutions: Purdue University West Lafayette, Massachusetts Institute of Technology

Language: English

Topic: Machine Learning in Materials Science

Subfield: Materials Chemistry

Field: Materials Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $1,962

Funders: Toyota Research Institute, Toyota Research Institute, North America