• Skip to primary navigation
  • Skip to main content
  • Skip to footer
Chemical Engineering
  • All Events
  • Seminars
  • Contact Us
  • Giving
  • About
    • Mission, Vision and Values
    • ChE Advisory Board
    • Diversity, Equity and Inclusion
    • Reporting Concerns and Misconduct
    • Faculty Search
    • Contact Us
  • News
  • Research
    • Research Areas
      • Biomolecular Engineering
      • Catalysis and Reaction
      • Cellular Engineering
      • Computing and Simulation
      • Materials
      • Microfabricated Systems
      • Nanotechnology
      • Polymers and Complex Fluids
      • Sustainable Energy
    • Facilities
    • Research Programs for Undergraduates
    • Partners in Industry
  • People
    • Administration
    • All Faculty
    • Core Faculty
    • Doctoral Students
    • Master’s Students
    • Postdoctoral Research Fellows
    • Staff
  • Graduate
    • Program
      • Graduate Degree Requirements
      • SUGS
      • Additional Options
      • Doctoral Candidacy Exam
      • Thesis Proposal Exam
      • Doctoral Committee
    • Prospective Students
      • Admissions Requirements
      • Admissions Timeline
      • TOEFL and GRE
      • Financial Support
      • Recruitment
      • Frequently Asked Questions
    • Current Students
      • Diversity, Equity and Inclusion
      • GSI Positions
      • Curricular Practical Training for F-1 Students
      • ChE Graduate Student Committee
    • Graduate Contacts
    • Why Michigan?
    • Housing
  • Undergraduate
    • Program
      • Mission
      • Incorporating Outreach
      • Program Improvement
      • Enrollment Data
    • Join Chemical Engineering
    • Degree Requirements
      • Intellectual Breadth
      • Courses & Course Profiles
    • Minors, Concentrations and Specialized Studies
    • Dual and Combined Degrees
    • Masters and SUGS Programs
    • Jobs and Research
      • Cooperative Education
    • Student Resources
      • Funding for Travel
      • Scholarships
      • Frequently Asked Questions
    • Student Groups
      • Funding for Groups
    • Undergraduate Contacts
  • Alumni
    • Stay Connected
    • Get Involved
    • Giving
    • Recruit Talent
    • Alumni Profiles
    • All Events
    • Seminars
    • Contact Us
    • Giving

Interpretable machine learning in catalysis

Recent research from U-M ChE professors Suljo Linic and Bryan Goldsmith and their co-advised PhD student Jacques Esterhuizen explores recent advances in machine learning approaches for heterogeneous catalysis.

Written by: Michigan Engineering

April 15, 2022

Jacques EsterhuizenJacques A. Esterhuizen
PhD Student in Chemical Engineering
Bryan Goldsmith portraitBryan R. Goldsmith
Dow Corning Assistant Professor of Chemical Engineering
portraitSuljo Linic
Martin Lewis Perl Collegiate Professor of Chemical Engineering

EXPERTS:

Machine learning is a subfield of artificial intelligence that focuses on the development of algorithms that can self-learn from data. Applications of machine learning are growing across all fields of research, including heterogeneous catalysis. However, most applications of machine learning in heterogeneous catalysis so far use difficult to interpret black-box models to predict catalytic properties, which makes extracting scientific insights from these models challenging.

A recent perspective from professors Suljo Linic and Bryan Goldsmith and their co-advised PhD student Jacques Esterhuizen discusses recent advances in machine learning approaches for heterogenous catalysis and classifies them in terms of their interpretability.

“We describe in the paper how machine learning tools are progressing to be used not only to compute certain properties but also to derive and test new hypotheses and generate new knowledge. We are interested in developing algorithms that will guide us in uncovering the fundamental concepts in science and engineering,” said Linic.

The authors outline best practices for interpreting machine-learned results in heterogeneous catalysis, as well as identify several critical challenges facing practitioners who wish to interpret machine-learned results in heterogeneous catalysis related to integration with experiment, dataset size, model reusability, and explaining interpretations.

 “Early applications of interpretable machine learning in catalysis highlight its promise for accelerating hypothesis formation, but there is certainly room for improvement, which will require future collaboration between experimental and computational chemists and material scientists and machine-learning experts,” said Esterhuizen.

There are many complex problems that further applications of interpretable machine learning will help to address. “We believe these approaches will aid the design of new materials for important reactions pertaining to energy and the environment, such as water splitting and CO2 conversion,” said Goldsmith.

The article can be found at Esterhuizen, Jacques A., Bryan R. Goldsmith, and Suljo Linic. “Interpretable machine learning for knowledge generation in heterogeneous catalysis.” Nature Catalysis (2022): 1-10.

Explore: Catalysis and Reaction Chemical Engineering Bryan Goldsmith Suljo Linic

Footer

  • All Events
  • Seminars
  • Contact Us
  • Giving
  • Michigan Engineering
  • Strategic Vision
  • Graduate and Professional
  • Undergraduate
  • Michigan Engineering Research News

  • Facebook
  • LinkedIn
  • Twitter

© 2023 The Regents of the University of Michigan Ann Arbor, MI 48109 USA Privacy Policy | Non-Discrimination Policy | Campus Safety