A call for caution in the era of AI-accelerated materials science

被引:2
|
作者
Li, Kangming [1 ]
Kim, Edward [1 ,2 ]
Fehlis, Yao [3 ]
Persaud, Daniel [1 ]
DeCost, Brian [4 ]
Greenwood, Michael [5 ]
Hattrick-Simpers, Jason [1 ]
机构
[1] Univ Toronto, Dept Mat Sci & Engn, 27 Kings Coll Cir, Toronto, ON, Canada
[2] Cohere, 171 John St, Toronto, ON, Canada
[3] Adv Micro Devices Inc, 7171 Southwest Pkwy, Austin, TX USA
[4] NIST, Mat Measurement Lab, 100 Bur Dr, Gaithersburg, MD USA
[5] Canmet Mat, Canmet MAT, 183 Longwood Rd South, Hamilton, ON, Canada
关键词
D O I
10.1016/j.matt.2023.10.027
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
It is safe to state that the field of matter has successfully entered the fourth paradigm, where machine learning and artificial intelligence (AI) are universally seen as useful, if not truly intelligent. AI's utiliza-tion is near-ubiquitous from the prediction of novel materials to reducing computational overhead for material simulations; its value has been demonstrated time and again by both theorists and experimentalists. There is, however, a worrying trend toward large datasets and overparameterized models being all we need to accelerate science through accurate and robust machine learning systems.
引用
收藏
页码:4116 / 4117
页数:2
相关论文
共 50 条
  • [42] Foundational biomedical informatics research in the clinical and translational science era: a call to action
    Payne, Philip R. O.
    Embi, Peter J.
    Niland, Joyce
    JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION, 2010, 17 (06) : 615 - 616
  • [43] Scientific AI in materials science: a path to a sustainable and scalable paradigm
    DeCost, B. L.
    Hattrick-Simpers, J. R.
    Trautt, Z.
    Kusne, A. G.
    Campo, E.
    Green, M. L.
    MACHINE LEARNING-SCIENCE AND TECHNOLOGY, 2020, 1 (03):
  • [44] How AI application in pharmaceutical industries is beneficial to materials science
    Suzuki, Hideo
    Kurosawa, Shin
    Marcella, Stephen
    Kanba, Masaru
    Koretaka, Yuichi
    Tsuji, Akio
    Okumura, Toshiyuki
    JOURNAL OF PHYSICS D-APPLIED PHYSICS, 2022, 55 (24)
  • [45] Compound Knowledge Graph-Enabled AI Assistant for Accelerated Materials Discovery
    Kareem S. Aggour
    Andrew Detor
    Alfredo Gabaldon
    Varish Mulwad
    Abha Moitra
    Paul Cuddihy
    Vijay S. Kumar
    Integrating Materials and Manufacturing Innovation, 2022, 11 : 467 - 478
  • [46] Compound Knowledge Graph-Enabled AI Assistant for Accelerated Materials Discovery
    Aggour, Kareem S. S.
    Detor, Andrew
    Gabaldon, Alfredo
    Mulwad, Varish
    Moitra, Abha
    Cuddihy, Paul
    Kumar, Vijay S. S.
    INTEGRATING MATERIALS AND MANUFACTURING INNOVATION, 2022, 11 (04) : 467 - 478
  • [47] Materials Knowledge Systems in Python—a Data Science Framework for Accelerated Development of Hierarchical Materials
    David B Brough
    Daniel Wheeler
    Surya R. Kalidindi
    Integrating Materials and Manufacturing Innovation, 2017, 6 : 36 - 53
  • [48] Convergence of computational and experimental chemistries driving the new era of accelerated materials discovery
    Hedrick, J.
    ABSTRACTS OF PAPERS OF THE AMERICAN CHEMICAL SOCIETY, 2015, 250
  • [49] A Materials Screening Methodology for Scaled Non-Volatile Memory in the AI Era
    Lanzillo, Nicholas A.
    Robison, Robert R.
    2019 IEEE ALBANY NANOTECHNOLOGY SYMPOSIUM (ANS), 2019,
  • [50] Data science and cyberinfrastructure: critical enablers for accelerated development of hierarchical materials
    Kalidindi, Surya R.
    INTERNATIONAL MATERIALS REVIEWS, 2015, 60 (03) : 150 - 168