EUVIMEDOpdag EUVIMED
Open access

Beyond empirical models: Discovering constitutive laws in solids with graph-based equation discovery

Hao Xu iD, Yuntian Chen iD, Dongxiao Zhang iD

Science Advances · 2026-09-11 · 12 (37)

DOI: 10.1126/sciadv.aec0989 ↗

At a glance

Journal article in Science Advances, published on 2026-09-11. Written by Hao Xu and 2 co-authors. Institution: Zhejiang Key Laboratory of Industrial Intelligence and Digital Twin, Eastern Institute of Technology, Ningbo 315200, Zhejiang, China. Cited 1 times so far (Crossref); 88 references. The full text is freely available in PubMed Central. Funded by: Natural Science Foundation of Ningbo, National Natural Science Foundation of China, China Postdoctoral Science Foundation.

AbstractBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Constitutive models are fundamental to solid mechanics and materials science, underpinning the quantitative description of material behaviors. Traditional phenomenological models are often built on expert intuition and empirical fitting, which limits their generalizability. In this work, we propose a graph-based equation discovery framework for automated discovery of constitutive laws directly from multicase experimental data. This framework expresses equations as directed graphs, where nodes represent operators and variables, edges denote computational relations, and edge features encode parametric dependencies. This enables the generation and optimization of free-form symbolic expressions with undetermined material-specific parameters. Through the framework, we have found constitutive models for strain-rate effects in alloy steel materials, deformation behavior of lithium metal, and hyperelastic behavior of filled rubbers. The discovered models exhibit compact analytical structures and achieve higher accuracy than empirical models. The proposed framework provides a generalizable and interpretable approach for data-driven scientific modeling, particularly in contexts where traditional empirical models are inadequate for representing complex physical phenomena.

Authors and institutions

  • Zhejiang Key Laboratory of Industrial Intelligence and Digital Twin, Eastern Institute of Technology, Ningbo 315200, Zhejiang, China.
  • Department of Electrical Engineering, Tsinghua University, Beijing 100084, P. R. China.
  • Ningbo Institute of Digital Twin, Eastern Institute of Technology, Ningbo 315200, Zhejiang, P. R. China.
  • Institute for Advanced Study, Lingnan University, Tuen Mun, Hong Kong, China.

ORCID profiles: Hao Xu, Yuntian Chen, Dongxiao Zhang

Funding

  • Natural Science Foundation of Ningbo
  • National Natural Science Foundation of China
  • China Postdoctoral Science Foundation
  • China National Postdoctoral Program for Innovative Talents
  • High Performance Computing Centers at Eastern Institute of Technology
  • Ningbo Institute of Digital Twin

Cite

APA

Xu, H., Chen, Y., & Zhang, D. (2026). Beyond empirical models: Discovering constitutive laws in solids with graph-based equation discovery. Science Advances, 12(37). https://doi.org/10.1126/sciadv.aec0989

Vancouver

Xu H, Chen Y, Zhang D. Beyond empirical models: Discovering constitutive laws in solids with graph-based equation discovery. Science Advances. 2026;12(37). doi:10.1126/sciadv.aec0989

BibTeX
@article{Xu2026,
  author = {Xu, Hao and Chen, Yuntian and Zhang, Dongxiao},
  title = {Beyond empirical models: Discovering constitutive laws in solids with graph-based equation discovery},
  journal = {Science Advances},
  year = {2026},
  volume = {12},
  number = {37},
  doi = {10.1126/sciadv.aec0989}
}
Start for free →