Machine learning materials physics: Integrable deep neural networks enable scale bridging by learning free energy functions

Abstract

The free energy of a system is central to many material models. Although free energy data is not generally found directly, its derivatives can be observed or calculated. In this work, we present an Integrable Deep Neural Network (IDNN) that can be trained to derivative data, then analytically integrated to recover an accurate representation of the free energy. The IDNN is demonstrated by training to the chemical potential values of a binary alloy with B2 ordering. The resulting DNN representation of the free energy is used in a phase field simulation and found to predict the appropriate formation of antiphase boundaries in the material. In contrast, a B-spline representation of the same data failed to represent the physics of the system with sufficient fidelity to resolve the antiphase boundaries.

23 pages, 12 figures

References in corpus (3)

• Self-driven lattice-model Monte Carlo simulations of alloy thermodynamic
• Machine learning materials physics: Surrogate optimization and multi-fidelity algorithms predict precipitate morphology in an alternative to phase field dynamics
• Unconditionally stable, second-order accurate schemes for solid state phase transformations driven by mechano-chemical spinodal decomposition

Cited by in corpus (24)

• Integrating Machine Learning and Multiscale Modeling: Perspectives, Challenges, and Opportunities in the Biological, Biomedical, and Behavioral Sciences
• Geometric deep learning for computational mechanics Part I: Anisotropic Hyperelasticity
• Data-driven Tissue Mechanics with Polyconvex Neural Ordinary Differential Equations
• Deep learning of thermodynamics-aware reduced-order models from data
• Machine learning materials physics: Multi-resolution neural networks learn the free energy and nonlinear elastic response of evolving microstructures
• Variational Onsager Neural Networks (VONNs): A thermodynamics-based variational learning strategy for non-equilibrium PDEs
• Gibbs-Duhem-Informed Neural Networks for Binary Activity Coefficient Prediction
• Algorithmically-Consistent Deep Learning Frameworks for Structural Topology Optimization
• Thermodynamics-informed graph neural networks
• Symplectic Neural Networks in Taylor Series Form for Hamiltonian Systems
• Predicting the Mechanical Properties of Biopolymer Gels Using Neural Networks Trained on Discrete Fiber Network Data
• Drawing Phase Diagrams of Random Quantum Systems by Deep Learning the Wave Functions
• Scale bridging materials physics: Active learning workflows and integrable deep neural networks for free energy function representations in alloys
• Bayesian neural networks for weak solution of PDEs with uncertainty quantification
• Multi-variable Integration with a Neural Network
• Neural Control of Discrete Weak Formulations: Galerkin, Least-Squares and Minimal-Residual Methods with Quasi-Optimal Weights
• Faster Bayesian inference with neural network bundles and new results for $f(R)$ models
• Explainable artificial intelligence for mechanics: physics-informing neural networks for constitutive models
• System inference for the spatio-temporal evolution of infectious diseases: Michigan in the time of COVID-19
• Conformal Quantile Regression for Neural Probabilistic Constitutive Modeling
• Li${}_x$CoO${}_2$ phase stability studied by machine learning-enabled scale bridging between electronic structure, statistical mechanics and phase field theories
• Similarity-Based Equational Inference in Physics
• System inference via field inversion for the spatio-temporal progression of infectious diseases: Studies of COVID-19 in Michigan and Mexico
• Nonseparable Symplectic Neural Networks