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

arXiv:2511.09906 · cond-mat.mtrl-sci, cs.LG, physics.app-ph, physics.data-an · Submitted 2025-11-13 · Read on arXiv

Listen

Radio episode about this paper

Transcript

Introduction to the show: ident: Condensed Matter. The day in condensed matter: materials, phases and the measurements under them.

Kai: We're looking at the paper: "Beyond empirical models".

Mira: Here's the gist of the paper. Constitutive models are fundamental to solid mechanics and materials science, underpinning the quantitative description and prediction of material responses under diverse loading conditions This work proposes a graph-based equation discovery framework for the automated discovery of constitutive laws directly from multisource experimental data Framework Concept The proposed 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 The graph-based representation offers several advantages over conventional tree-based representations, such as allowing node sharing and flexible edge connectivity for more compact encoding Furthermore, the framework embeds material-specific parameters directly as edge features, avoiding the need for additional parameter nodes Optimization Strategy Genetic programming is utilized for optimization through a loop of “generation-evaluation-evolution” The generation process involves introducing graph templates to define structural rules and configurable subgraph patterns Candidate graphs are assembled from randomly generated subgraphs that adhere to these predefined templates, mitigating the risk of generating overly complex structures The evaluation metric for each graph is the mean error computed across all datasets, promoting the discovery of equations with generalizability The L-BFGS optimization algorithm is employed to fit material-specific parameters individually for each material dataset A multi-start optimization strategy is adopted to mitigate sensitivity and retain the solution corresponding to the lowest postoptimization error Key Discoveries The framework has discovered new constitutive models for strain-rate effects in alloy steel materials that exhibit compact analytical structures and higher accuracy compared to conventional empirical models For the deformation of lithium metal, the method identified new constitutive laws directly from experimental data with high accuracy Specifically, a generalized power-exponential form was discovered for the dynamic increase factor (DIF) model This discovered model achieved the lowest mean squared error (MSE) of 6.9×10-4 and the highest coefficient of determination (R2) of 0.980 when compared against classical DIF constitutive models Similarly, for strain hardening, an exponential-form model was selected as the final equation because it provides superior mathematical smoothness and avoids singularities within the plastic strain domain Model Integration and Validation The authors constructed an integrated rate-dependent constitutive relation by combining the independently discovered constitutive models for dynamic increase factor and strain hardening This integrated model achieved a higher accuracy, with an MSE of 646.4 and an R2 of 0.974, reducing the prediction error to nearly half that of the Johnson–Cook (J-C) model The framework demonstrated superior adaptability across different strain-rate regimes for high-strength steel Q460JSC compared to conventional models For lithium metal, the discovered constitutive law showed excellent agreement with experimental data across all temperature regimes, achieving a relative error of only 1.86% The final discovered equation for lithium metal combines a direct linear dependence on stress with a nonstandard evolution term involving an exponential function of temperature T Limitations and Future Directions Several limitations remain, including the specification of graph templates which introduces a form of prior structural bias The current implementation is limited to scalar constitutive responses, and extending the framework to accommodate tensorial quantities and anisotropic material behavior remains an open direction for future investigations Further research is needed to balance representational expressiveness with computational efficiency when dealing with complex problems involving multiple variables or coupled physical fields The work contributes to a new paradigm of scientifically grounded machine learning for physical law discovery Materials and Methods Each candidate equation is encoded as a directed acyclic graph (DAG), denoted by G = (V, E), where V is the set of nodes representing operators or variables, and E is the set of directed edges representing the computational dependencies between them Node types include Variable nodes for input variables like strain rate epsiloṅ or temperature T, and operator nodes drawn from a predefined set such as add, mul, exp, log, and pow Each edge is associated with an edge feature eij ∈ R that represents either a fixed scalar constant or a learnable undetermined coefficient Ci to be optimized during model evaluation Graph templates are introduced to constrain the symbolic search space by defining syntactic and topological constraints on how equations can be assembled Graph crossover is implemented as a subgraph exchange mechanism between two parent graphs to facilitate recombination of functional motifs Graph Evaluation To quantitatively assess the quality of a candidate equation, parameter identification is followed by graph evaluation, which reflects the model’s predictive accuracy with respect to observed data The optimization is performed using the L-BFGS algorithm(51), a quasi-Newton method suitable for smooth objective landscapes and small-to-moderate numbers of parameters The loss function is defined as L(theta) = L(theta) = 1/N ∑ (f(xi; θ) − yi) i=1 to N, where θ = C1 C2 Cn denotes the set of undetermined coefficients encoded in the graph’s edge features The loss is computed as the average loss across all M datasets when data from multiple sources are used, ensuring generalizability Graph Cross-over and Mutation Graph crossover is implemented as a subgraph exchange mechanism between two parent graphs where a random node is selected in each parent graph, and the corresponding subgraphs rooted at these nodes are swapped Three distinct mutation strategies are employed: Edge feature perturbation, Subgraph replacement, and Subgraph deletion Edge feature perturbation modifies a randomly selected edge by replacing its associated feature with a new randomly sampled value Subgraph replacement involves selecting a non-initial node and replacing its subgraph with one newly generated from the graph template Subgraph deletion promotes structural simplification by randomly choosing and removing a subgraph, replacing the parent node with a constant term The evolution process incorporates an extinction strategy where all but a small subset of top-performing graphs are eliminated to maintain population diversity References G.

Kai: A.

Mira: Holzapfel, Nonlinear solid mechanics: a continuum approach for engineering science E.

Kai: A.

Title and authors: Kai: So we're looking at this paper now called "Beyond empirical models: Discovering new constitutive laws in solids with graph-based equation discovery". They are Hao Xu, Yuntian Chen, and Dongxiao Zhang.

Mira: The title really tells you they're not just tweaking existing models; they are trying to discover entirely new ones using this graph structure.

Lev: I wonder how they handle the sheer complexity of finding a structure that is both compact and physically meaningful when you start generating everything randomly?

Kai: They use this graph approach where edges encode the parametric dependencies, which means the material specific parameters are baked right into the connections between operators.

Mira: That’s what’s interesting; they avoid having separate nodes just for those material-specific constants, which is a cleaner way to represent things.

Lev: But that means when you evaluate the graph, you have to be careful about how you're identifying those coefficients so they actually correspond to physical quantities.

Kai: They use L-BFGS optimization with a multi start strategy because they found that the objective function landscape can be tricky, and multiple starting points help them avoid getting stuck in a local minimum.

Mira: The results are pretty compelling because they discovered new constitutive models for strain rate effects in alloy steel materials that have compact analytical structures and higher accuracy than what we see in conventional empirical models.

Lev: Higher accuracy is good, but how does that translate to actual performance on real hardware? Does the complexity of the graph structure translate into a slow evaluation time for something like a real-time simulation?

Kai: That’s where it gets interesting; they found that for the deformation of lithium metal, this method identified new laws directly from experimental data with high accuracy.

The paper's summary: Mira: So to summarize, the core idea is expressing equations as directed graphs where nodes are operators and variables and edges show the computational relations between them.

Kai: The goal is to automate the discovery of constitutive laws by letting a graph generation process create free-form symbolic expressions that have undetermined material specific parameters encoded in the edge features.

Lev: So, instead of starting with an equation structure, you start with templates and randomly assemble subgraphs to form candidate graphs. That sounds like a very smart way to prune the search space initially.

Mira: Right, and then you evaluate each candidate graph by computing the mean error across all datasets from multiple sources to make sure the resulting model is generalizable rather than just overfitting one material.

Kai: They found new constitutive laws for strain rate effects in alloy steel that have compact analytical structures and higher accuracy compared to conventional empirical models.

Lev: That’s a key finding; having a compact structure means it should be easier to implement in simulations, and the accuracy gain is what matters most for us.

Mira: And for lithium metal deformation, they discovered a generalized power exponential form for the dynamic increase factor model which achieved a mean squared error of six point nine times ten to the negative four when compared against classical models <ref:2511.09906#pg3>.

Kai: That MSE number sounds very solid; it’s low enough that it suggests the functional form they found is genuinely capturing some underlying physics in that material system.

Lev: But what about strain hardening, which is often more complex than just a dynamic increase factor? They didn't mention if they found similar high-accuracy laws for plasticity.

The paper's improvements: Mira: One major improvement they highlight is that when you combine the independently discovered constitutive models—for instance, combining their strain rate effect model and their strain hardening model—the integrated relation achieves a higher accuracy with an MSE of six hundred forty-six point four and an R squared of zero point nine seven four.

Kai: That’s significant because they reduced the prediction error to nearly half that of the Johnson Cook model for high-strength steels, which is a benchmark we often compare against.

Lev: Reducing the error by half is substantial; that means their integrated approach provides a much more reliable description of true plastic stress as it depends on both strain and strain rate simultaneously.

Mira: They also showed superior adaptability across different strain rate regimes for the high strength steel Q460JSC compared to conventional models.

Lev: Adaptability is crucial because we're testing this on materials that are undergoing extreme conditions, and if a model works well across different rates, it suggests the underlying physics is being captured more robustly.

Kai: For lithium metal specifically, the final discovered equation combines a direct linear dependence on stress with a nonstandard evolution term involving an exponential function of temperature T.

Mira: That specific combination for lithium metal is interesting because it shows how they handled the coupling between strain rate, temperature, and stress in that system.

Lev: So they managed to find a law that works well across all temperature regimes for lithium metal based on those experimental data points. That's hard to get without significant assumptions about the physics being correct everywhere.

Conclusion: Kai: So, to wrap up this paper, the main thing is that they have successfully used a graph-based equation discovery framework to find new constitutive laws for solids with higher accuracy and better structure than traditional empirical models.

Mira: They achieved this by letting the AI explore free-form symbolic expressions constrained by templates and optimizing those expressions against multiple experimental datasets using genetic programming.

Lev: The implication for us is that if we can build a framework like this, we could automate the discovery of material laws for complex problems without needing to start from scratch every time.

Kai: And they showed that integrating different discovered models—like combining strain rate and strain hardening laws—can lead to a more accurate integrated relation, reducing error compared to existing benchmarks like Johnson Cook.

Mira: For lithium metal, they found a specific law involving stress dependence and an exponential temperature term that fits the experimental data with a relative error of only one point eight six percent across all temperatures <ref:2511.09906#pg1>.

Lev: It’s neat that the framework can handle these complex, coupled responses for materials like lithium metal and high strength steels, even if we still have to worry about how fast the graph evaluation runs on real hardware.

Kai: The paper "Beyond empirical models: Discovering new constitutive laws in solids with graph-based equation discovery" shows a path toward scientific machine learning for finding material science laws.

Mira: It’s a way to move past just fitting curves and start building physically informed, generalizable equations directly from data.

Lev: We'll be watching how this graph structure idea evolves, because if we can constrain the graph search better, it could handle tensorial quantities next, which would be a big step for modeling anisotropic behavior.

Hao Xu, Yuntian Chen, *Dongxiao Zhang

Zhejiang Key Laboratory of Industrial Intelligence and Digital Twin · Department of Electrical Engineering, Tsinghua University · Ningbo Institute of Digital Twin · Institute for Advanced Study, Lingnan University

cond-mat.mtrl-sci, cs.LG, physics.app-ph, physics.data-an

Submitted: 2025-11-13

Updated: 2025-11-13

Journal ref: Science Advances, 2026

DOI: 10.1126/sciadv.aec0989

License: http://creativecommons.org/licenses/by-nc-nd/4.0/

Importance score: 87/100

The gist: Constitutive models are fundamental to solid mechanics and materials science, underpinning the quantitative description and prediction of material responses under diverse loading conditions This work…

Key concepts

Graph-based Equation Discovery
This technique represents mathematical equations as directed graphs. Nodes represent variables or operators (like 'add' or 'exp'), and edges show the computational relationships between them. This structure allows the system to search for complex, free-form symbolic expressions that describe material behavior, rather than relying on pre-defined equation structures.
Edge Features
In this framework, edge features are used to store information about the parameters in an equation. Instead of having separate nodes for every parameter, these features directly encode the material-specific coefficients that need to be optimized. This makes the graph representation compact and flexible for discovering laws with undetermined constants.
Genetic Programming
Genetic programming is an optimization strategy used to search through possible equation structures. It works by generating candidate graphs based on predefined templates, evaluating them against experimental data, and then evolving the best candidates through mutation and crossover. This process guides the system toward discovering equations that accurately fit the observed physical responses.
Graph Cross-over
Graph crossover is a mechanism used during evolution to recombine successful parts of two parent graphs. It involves randomly selecting nodes in each graph and swapping their corresponding subgraphs. This allows the system to combine functional motifs from different successful models, helping to create more complex and accurate constitutive laws.

Terminology

Summary

Constitutive models are fundamental to solid mechanics and materials science, underpinning the quantitative description and prediction of material responses under diverse loading conditions This work proposes a graph-based equation discovery framework for the automated discovery of constitutive laws directly from multisource experimental data

Framework Concept

The proposed 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 The graph-based representation offers several advantages over conventional tree-based representations, such as allowing node sharing and flexible edge connectivity for more compact encoding Furthermore, the framework embeds material-specific parameters directly as edge features, avoiding the need for additional parameter nodes

Optimization Strategy

Genetic programming is utilized for optimization through a loop of “generation-evaluation-evolution” The generation process involves introducing graph templates to define structural rules and configurable subgraph patterns Candidate graphs are assembled from randomly generated subgraphs that adhere to these predefined templates, mitigating the risk of generating overly complex structures The evaluation metric for each graph is the mean error computed across all datasets, promoting the discovery of equations with generalizability The L-BFGS optimization algorithm is employed to fit material-specific parameters individually for each material dataset A multi-start optimization strategy is adopted to mitigate sensitivity and retain the solution corresponding to the lowest postoptimization error

Key Discoveries

The framework has discovered new constitutive models for strain-rate effects in alloy steel materials that exhibit compact analytical structures and higher accuracy compared to conventional empirical models For the deformation of lithium metal, the method identified new constitutive laws directly from experimental data with high accuracy Specifically, a generalized power-exponential form was discovered for the dynamic increase factor (DIF) model This discovered model achieved the lowest mean squared error (MSE) of 6.9×10-4 and the highest coefficient of determination (R2) of 0. p. 8

Where the paper says it

9 achieves the lowest mean squared error (MSE) of 6. 9×10-4 and the highest coefficient of determination (R2 ) of 0.

980 when compared against classical DIF constitutive models Similarly, for strain hardening, an exponential-form model was selected as the final equation because it provides superior mathematical smoothness and avoids singularities within the plastic strain domain

Model Integration and Validation

The authors constructed an integrated rate-dependent constitutive relation by combining the independently discovered constitutive models for dynamic increase factor and strain hardening This integrated model achieved a higher accuracy, with an MSE of 646.4 and an R2 of 0.974, reducing the prediction error to nearly half that of the Johnson–Cook (J-C) model The framework demonstrated superior adaptability across different strain-rate regimes for high-strength steel Q460JSC compared to conventional models For lithium metal, the discovered constitutive law showed excellent agreement with experimental data across all temperature regimes, achieving a relative error of only 1.86% The final discovered equation for lithium metal combines a direct linear dependence on stress with a nonstandard evolution term involving an exponential function of temperature T

Limitations and Future Directions

Several limitations remain, including the specification of graph templates which introduces a form of prior structural bias The current implementation is limited to scalar constitutive responses, and extending the framework to accommodate tensorial quantities and anisotropic material behavior remains an open direction for future investigations Further research is needed to balance representational expressiveness with computational efficiency when dealing with complex problems involving multiple variables or coupled physical fields The work contributes to a new paradigm of scientifically grounded machine learning for physical law discovery

Materials and Methods

Each candidate equation is encoded as a directed acyclic graph (DAG), denoted by G = (V, E), where V is the set of nodes representing operators or variables, and E is the set of directed edges representing the computational dependencies between them Node types include Variable nodes for input variables like strain rate epsiloṅ or temperature T, and operator nodes drawn from a predefined set such as add, mul, exp, log, and pow Each edge is associated with an edge feature eij ∈ R that represents either a fixed scalar constant or a learnable undetermined coefficient Ci to be optimized during model evaluation Graph templates are introduced to constrain the symbolic search space by defining syntactic and topological constraints on how equations can be assembled Graph crossover is implemented as a subgraph exchange mechanism between two parent graphs to facilitate recombination of functional motifs

Graph Evaluation

To quantitatively assess the quality of a candidate equation, parameter identification is followed by graph evaluation, which reflects the model’s predictive accuracy with respect to observed data The optimization is performed using the L-BFGS algorithm(51), a quasi-Newton method suitable for smooth objective landscapes and small-to-moderate numbers of parameters The loss function is defined as L(theta) = L(theta) = 1/N ∑ (f(xi; θ) − yi) i=1 to N, where θ = C1 C2 Cn denotes the set of undetermined coefficients encoded in the graph’s edge features The loss is computed as the average loss across all M datasets when data from multiple sources are used, ensuring generalizability

Graph Cross-over and Mutation

Graph crossover is implemented as a subgraph exchange mechanism between two parent graphs where a random node is selected in each parent graph, and the corresponding subgraphs rooted at these nodes are swapped Three distinct mutation strategies are employed: Edge feature perturbation, Subgraph replacement, and Subgraph deletion Edge feature perturbation modifies a randomly selected edge by replacing its associated feature with a new randomly sampled value Subgraph replacement involves selecting a non-initial node and replacing its subgraph with one newly generated from the graph template Subgraph deletion promotes structural simplification by randomly choosing and removing a subgraph, replacing the parent node with a constant term The evolution process incorporates an extinction strategy where all but a small subset of top-performing graphs are eliminated to maintain population diversity

References

G. A. Holzapfel, Nonlinear solid mechanics: a continuum approach for engineering science E. p. 1

Where the paper says it

2 Abstract Constitutive models are fundamental to solid mechanics and materials science, underpinning the quantitative description and prediction of material responses under diverse loading conditions. Traditional phenomenological models, which are derived through empirical fitting, often lack generalizability and rely heavily on expert intuition and predefined functional forms.

A. de Souza Neto, D. Peric, D. R. J. Owen, Computational Methods for Plasticity: Theory and Applications X. p. 1
Where the paper says it

Accordingly, they are typically established through phenomenological approaches, guided by systematic experimentation and theoretical generalization, to characterize nonlinear behaviors across varying conditions(1). The accuracy and generality of constitutive models are critical for the reliability of mechanical analysis, directly influencing both theoretical developments and practical applications in computational mechanics and materials engineering.

Zhou, D. Yu, O Barrera, Mechanics constitutive models for viscoelastic solid materials: Development and a critical review J. p. 1
Where the paper says it

2 Abstract Constitutive models are fundamental to solid mechanics and materials science, underpinning the quantitative description and prediction of material responses under diverse loading conditions. Traditional phenomenological models, which are derived through empirical fitting, often lack generalizability and rely heavily on expert intuition and predefined functional forms.

H Sung, J. H Kim, R. H Wagoner, A plastic constitutive equation incorporating strain, strain-rate, and temperature R Liang, A S Khan, A critical review of experimental results and constitutive models for BCC and FCC metals over a wide range of strain rates and temperatures F J Zerilli, R W Armstrong, Dislocation‐mechanics‐based constitutive relations for material dynamics calculations N R Brodnik, C Muir, N Tulshibagwale, J Rossin, M P Echlin, C M Hamel, S L B Kramer, T M Pollock, J D Kiser, C Smith, S H Daly J N Fuhg, G Anantha Padmanabha, N Bouklas, B Bahmani R Eggersmann, T Kirchdoerfer, S Reese, L Stainier, M Ortiz T Kirchdoerfer, M Ortiz, Data‐driven computing in dynamics H Salahshoor, M Ortiz, Model-free data-driven viscoelasticity in the frequency domain M Peirlinck, K Linka, J A Hurtado, E Kuhl M Evett, T Fernandez, Numeric mutation improves the discovery of numeric constants in genetic programming D C Liu, J Nocedal, On the limited memory BFGS method for large scale optimization M Cranmer, Interpretable machine learning for science with PySR and SymbolicRegression M Flaschel, S Kumar, L De Lorenzis, Automated discovery of generalized standard material models with EUCLID S L Brunton, J N Kutz, Methods for data-driven multiscale model discovery for materials A A Kaptanoglu, B M de Silva, U Fasel, K Kaheman X Liu, Z He, J Ye, L Yan, S Li, Y Tang Study on dynamic mechanical behavior of Q460JSC and HQ600 high strength steel W S LePage, Y Chen, E Kazyak J Wen, Q Zou, Y Wei Physics-driven machine learning model on temperature and time-dependent deformation in lithium metal and its finite element implementation

Author Contributions

H X., and D Z conceived the idea, designed the study, and analyzed the results H X. p. 0

Where the paper says it

3 Ningbo Institute of Digital Twin, Eastern Institute of Technology, Ningbo, Zhejiang 315200, P. China 4 Institute for Advanced Study, Lingnan University, Tuen Mun, Hong Kong * Corresponding authors.

developed the algorithm, performed the computations, and generated the results and figures H X. p. 6
Where the paper says it

The generated graphs are evaluated using experimental datasets collected from the literature across various materials (Fig. Since constitutive laws typically involve material-specific undetermined parameters, the L-BFGS optimization algorithm is employed to fit these parameters individually for each material dataset.

, Y C. and D Z wrote and edited the manuscript D Z supervised the entire project

Declaration of Interests

The authors declare that they have no competing interests

Acknowledgements

This work was supported and partially funded by the National Natural Science Foundation of China (Grant 52288101), the China Postdoctoral Science Foundation (Grant No. 2024M761535), the China National Postdoctoral Program for Innovative Talents (Grant No. p. 0

Where the paper says it

1 Beyond empirical models: Discovering new constitutive laws in solids with graph-based equation discovery Hao Xu1,2, Yuntian Chen1,3,*, and Dongxiao Zhang1,4,* 1 Zhejiang Key Laboratory of Industrial Intelligence and Digital Twin, Eastern Institute of Technology, Ningbo, Zhejiang 315200, China 2 Department of Electrical Engineering, Tsinghua University, Beijing 100084, P. 3 Ningbo Institute of Digital Twin, Eastern Institute of Technology, Ningbo, Zhejiang 315200, P.

BX20250063), and the Natural Science Foundation of Ningbo, China (No. p. 0
Where the paper says it

1 Beyond empirical models: Discovering new constitutive laws in solids with graph-based equation discovery Hao Xu1,2, Yuntian Chen1,3,*, and Dongxiao Zhang1,4,* 1 Zhejiang Key Laboratory of Industrial Intelligence and Digital Twin, Eastern Institute of Technology, Ningbo, Zhejiang 315200, China 2 Department of Electrical Engineering, Tsinghua University, Beijing 100084, P. 3 Ningbo Institute of Digital Twin, Eastern Institute of Technology, Ningbo, Zhejiang 315200, P.

2023J027) This work is supported by the High Performance Computing Centers at Eastern Institute of Technology, Ningbo, and Ningbo Institute of Digital Twin

Reference

G. A. Holzapfel, Nonlinear solid mechanics: a continuum approach for engineering science Kluwer Academic Publishers Dordrecht [Preprint] (2002) E. p. 1

Where the paper says it

2 Abstract Constitutive models are fundamental to solid mechanics and materials science, underpinning the quantitative description and prediction of material responses under diverse loading conditions. Traditional phenomenological models, which are derived through empirical fitting, often lack generalizability and rely heavily on expert intuition and predefined functional forms.

A. de Souza Neto, D Peric, D R J Owen, Computational Methods for Plasticity: Theory and Applications John Wiley & Sons 2011 X Zhou, D Yu, O Barrera, Mechanics constitutive models for viscoelastic solid materials: Development and a critical review Advances in Applied Mechanics 56 189–321 2023 J H Sung, J H Kim, R H Wagoner, A plastic constitutive equation incorporating strain, strain-rate, and temperature Int J Plast 26 1746–1771 2010 R Liang, A S Khan, A critical review of experimental results and constitutive models for BCC and FCC metals over a wide range of strain rates and temperatures Int J Plast 15 963–980 1999 F J Zerilli, R W Armstrong, Dislocation‐mechanics‐based constitutive relations for material dynamics calculations J Appl Phys 61 1816–1825 1987 N R Brodnik, C Muir, N Tulshibagwale, J Rossin, M P Echlin, C M Hamel, S L B Kramer, T M Pollock, J D Kiser, C Smith S H Daly Perspective: Machine learning in experimental solid mechanics J Mech Phys Solids 173 2023 J N Fuhg, G Anantha Padmanabha, N Bouklas, B Bahmani W Sun, N N Vlassis, M Flaschel, P Carrara L De Lorenzis A review on data-driven constitutive laws for solids Archives of Computational Methods in Engineering 1–43 2024 R Eggersmann, T Kirchdoerfer, S Reese, L Stainier, M Ortiz Model-free datadriven inelasticity Comput Methods Appl Mech Eng 350 81–99 2019 T Kirchdoerfer, M Ortiz, Data‐driven computing in dynamics Int J Numer Methods Eng 113 1697–1710 2018 H Salahshoor, M Ortiz, Model-free data-driven viscoelasticity in the frequency domain Comput Methods Appl Mech Eng 403 115657 2023 M Peirlinck, K Linka, J A Hurtado, E Kuhl On automated model discovery and a universal material subroutine for hyperelastic materials Comput Methods Appl Mech Eng 418 116534 2024 M Evett, T Fernandez, Numeric mutation improves the discovery of numeric constants in genetic programming Genetic Programming 98 66–71 1998 D C Liu, J Nocedal, On the limited memory BFGS method for large scale optimization Math Program 45 503–528 1989 M Cranmer, Interpretable machine learning for science with PySR and SymbolicRegression jl arXiv preprint arXiv:2305.01582 2023 M Flaschel, S Kumar, L De Lorenzis Automated discovery of generalized standard material models with EUCLID Comput Methods Appl Mech Eng 405 115867 2023 S L Brunton, J N Kutz, Methods for data-driven multiscale model discovery for materials Journal of Physics: Materials 2 044002 2019 A A Kaptanoglu, B M de Silva, U Fasel, K Kaheman A J Goldschmidt J L Callaham C B Delahunt Z G Nicolaou K Champion J C Loiseau PySINDy: A comprehensive Python package for robust sparse system identification arXiv preprint arXiv:2111.08481 2021 H Xu, H Chang, D Zhang DLGA-PDE: Discovery of PDEs with incomplete candidate library via combination of deep learning and genetic algorithm J Comput Phys 418 109584 2020 M Tang, W Liao, R Kuske, S H Kang WeakIdent: Weak formulation for identifying differential equation using narrow-fit and trimming J Comput Phys 483 112069 2023 Z Li, H Yuan, W Han, Y Hou, H Li, H Ding Z Jiang L Yang Bi-level identification of governing equations for nonlinear physical systems Nat Comput Sci 1–11 2025 W S LePage, Y Chen, E Kazyak K.-H Chen A J Sanchez A Poli E M Arruda M D Thouless N P Dasgupta Lithium Mechanics: Roles of Strain Rate and Temperature and Implications for Lithium Metal Batteries J Electrochem Soc 166 A89–A97 2019 W S LePage, Y Chen, E Kazyak K. p. 1
Where the paper says it

This enables the generation and optimization of free-form symbolic expressions with undetermined material-specific parameters. Through the proposed framework, we have discovered new constitutive models for strain-rate effects in alloy steel materials and the deformation behavior of lithium metal.

p. 1
Where the paper says it

This enables the generation and optimization of free-form symbolic expressions with undetermined material-specific parameters. Through the proposed framework, we have discovered new constitutive models for strain-rate effects in alloy steel materials and the deformation behavior of lithium metal.

-H Chen A J Sanchez A Poli E M Arruda M D Thouless N P Dasgupta Lithium Mechanics: Roles of Strain Rate and Temperature and Implications for Lithium Metal Batteries J Electrochem Soc 166 A89–A97 2019 W S LePage, Y Chen, E Kazyak K.

Green — the paper says it, and the page is printed. Red — no passage carries it, so treat that sentence as unverified. The same check runs on your own text: check a summary against its source, $5.

Improvements for AI systems

  1. Improved AI systems can autonomously discover compact, closed-form constitutive relationships directly from multisource experimental data without manual derivation. This capability overcomes the limitations of human intuition constraining models to simple linear or low-order nonlinear forms.

  2. The improved system can generate and identify free-form constitutive laws with undetermined material-specific parameters, leading to higher accuracy and structural compactness compared to conventional empirical models. This is achieved by using a graph-based representation where edge features encode parametric dependencies.

  3. The framework allows the AI system to integrate data from multiple sources, ensuring that discovered constitutive laws are generalizable and not overfitted to a specific material or condition. This addresses the risk of overfitting under limited or scarce single-source data availability.

  4. The system can construct an integrated rate-dependent constitutive relation that describes true plastic stress as a joint function of true plastic strain and strain rate, providing a comprehensive description across wide loading conditions. This model outperforms conventional integrated models like the Johnson–Cook (J-C) model in accuracy for high-strength steels at high strain rates.

  5. The AI system can develop constitutive laws that capture complex, coupled material responses by proposing modifications to the integrated model's coefficients, such as replacing coefficients with Cs1 - λ1 x DIF and Cs2 - λ2 x DIF.

Abstract

Constitutive models are fundamental to solid mechanics and materials science, underpinning the quantitative description and prediction of material responses under diverse loading conditions. Traditional phenomenological models, which are derived through empirical fitting, often lack generalizability and rely heavily on expert intuition and predefined functional forms. In this work, we propose a graph-based equation discovery framework for the automated discovery of constitutive laws directly from multisource 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 proposed framework, we have discovered new constitutive models for strain-rate effects in alloy steel materials and the deformation behavior of lithium metal. Compared with conventional empirical models, these new models exhibit compact analytical structures and achieve higher accuracy. The proposed graph-based equation discovery framework provides a generalizable and interpretable approach for data-driven scientific modelling, particularly in contexts where traditional empirical formulations are inadequate for representing complex physical phenomena.

Sources

Related papers