Symbolic regression in materials science

By Yiqun Wang, Nicholas Wagner, James M. Rondinelli. MRS Communications, 2019

326 citations recorded by the source corpus.

The authors showcase the potential of symbolic regression as an analytic method for use in materials research. First, the authors briefly describe the current state-of-the-art method, genetic programming-based symbolic regression (GPSR), and recent advances in symbolic regression techniques. Next, the authors discuss industrial applications of symbolic regression and its potential applications in materials science. The authors then present two GPSR use-cases: formulating a transformation kinetics law and showing the learning scheme discovers the well-known Johnson–Mehl–Avrami–Kolmogorov form, and learning the Landau free energy functional form for the displacive tilt transition in perovskite LaNiO_3. Finally, the authors propose that symbolic regression techniques should be considered by materials scientists as an alternative to other machine learning-based regression models for learning from data.

Subfields: Artificial Intelligence, Cultural Studies, Materials Chemistry

View Paper: https://www.semanticscholar.org/paper/b35410d025fd7caebbbf94d5c249043553dc79bb

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Rohit Batra
2. Nour Makke
3. Le Song
4. Rampi Ramprasad
5. Ryan Jacobs
6. Sanjay Chawla
7. Dane Morgan
8. Arturo Geigel

In Cultural Studies

1. Rohit Batra
2. Nour Makke
3. Le Song
4. Rampi Ramprasad
5. Sanjay Chawla

In Materials Chemistry

1. Ryan Jacobs
2. Rohit Batra
3. Dane Morgan
4. Nour Makke
5. Sanjay Chawla
6. Rampi Ramprasad
7. Le Song
8. Yuri Mishin

Citations in the corpus

• Interpretable scientific discovery with symbolic regression: a review (2022, methodology): “SR has been applied in fundamental and applied sciences such as astrophysics [34], chemistry [35, 36], materials science [37, 38], semantic similarity measurement [39], climatology [40], medicine [41], among many others.”
• Emerging materials intelligence ecosystems propelled by machine learning (2020, methodology): “Another direct method of extracting an explicit functional form of materials properties from the available data is symbolic regression 88,89 .”
• Opportunities and Challenges for Machine Learning in Materials Science (2020, background): “…experimental systems for alloy development Barnard, et al. 2019 218 Nanoinformatics, and the big challenges for the science of small things Wang et al. 2019 219 Symbolic regression in materials science Dimitrov et al. 2019 220 Autonomous Molecular Design: Then and Now Zhou et al. 2019 221…”