skip to main content


Title: Accelerated discovery of metallic glasses through iteration of machine learning and high-throughput experiments

With more than a hundred elements in the periodic table, a large number of potential new materials exist to address the technological and societal challenges we face today; however, without some guidance, searching through this vast combinatorial space is frustratingly slow and expensive, especially for materials strongly influenced by processing. We train a machine learning (ML) model on previously reported observations, parameters from physiochemical theories, and make it synthesis method–dependent to guide high-throughput (HiTp) experiments to find a new system of metallic glasses in the Co-V-Zr ternary. Experimental observations are in good agreement with the predictions of the model, but there are quantitative discrepancies in the precise compositions predicted. We use these discrepancies to retrain the ML model. The refined model has significantly improved accuracy not only for the Co-V-Zr system but also across all other available validation data. We then use the refined model to guide the discovery of metallic glasses in two additional previously unreported ternaries. Although our approach of iterative use of ML and HiTp experiments has guided us to rapid discovery of three new glass-forming systems, it has also provided us with a quantitatively accurate, synthesis method–sensitive predictor for metallic glasses that improves performance with usemore » and thus promises to greatly accelerate discovery of many new metallic glasses. We believe that this discovery paradigm is applicable to a wider range of materials and should prove equally powerful for other materials and properties that are synthesis path–dependent and that current physiochemical theories find challenging to predict.« less
ORCiD logo [1] ; ORCiD logo [2] ; ORCiD logo [3] ; ORCiD logo ;  [4] ;  [5] ;  [1]
  1. SLAC National Accelerator Lab., Menlo Park, CA (United States). Stanford Synchrotron Radiation Lightsource (SSRL)
  2. Northwestern Univ., Evanston, IL (United States). Dept. of Materials Science and Engineering; Univ. of Chicago, IL (United States). Computational Institute
  3. Univ. of South Carolina, Columbia, SC (United States). College of Engineering and Computing
  4. Univ. of New South Wales, Sydney, NSW (Australia). School of Materials Science and Engineering
  5. National Inst. of Standards and Technology (NIST), Gaithersburg, MD (United States). Materials for Energy and Sustainable Development Group
Publication Date:
Grant/Contract Number:
Accepted Manuscript
Journal Name:
Science Advances
Additional Journal Information:
Journal Volume: 4; Journal Issue: 4; Journal ID: ISSN 2375-2548
Research Org:
SLAC National Accelerator Lab., Menlo Park, CA (United States)
Sponsoring Org:
USDOE Office of Science (SC), Basic Energy Sciences (BES) (SC-22) Funder #1: National Science Foundation Funder ID: (FUNDREF) 10.13039/100000001 Grant: 1250052 Funder #2: U.S. Department of Energy Funder ID: (FUNDREF) 10.13039/100000015 Grant: DE-AC02-76SF00515 Funder #3: U.S. Department of Energy Funder ID: (FUNDREF) 10.13039/100000015 Grant: FWP-100250 Funder #4: U.S. Department of Commerce Funder ID: (FUNDREF) 10.13039/100000190 Grant: 70NANB14H012
Country of Publication:
United States
OSTI Identifier: