A Generative Modeling Framework for Inferring Families of Biomechanical Constitutive Laws in Data-Sparse Regimes

Abstract

Quantifying biomechanical properties of the human vasculature could deepen our understanding of cardiovascular diseases. Standard nonlinear regression in constitutive modeling requires considerable high-quality data and an explicit form of the constitutive model as prior knowledge. By contrast, we propose a novel approach that combines generative deep learning with Bayesian inference to efficiently infer families of constitutive relationships in data-sparse regimes. Inspired by the concept of functional priors, we develop a generative adversarial network (GAN) that incorporates a neural operator as the generator and a fully-connected neural network as the discriminator. The generator takes a vector of noise conditioned on measurement data as input and yields the predicted constitutive relationship, which is scrutinized by the discriminator in the following step. We demonstrate that this framework can accurately estimate means and standard deviations of the constitutive relationships of the murine aorta using data collected either from model-generated synthetic data or ex vivo experiments for mice with genetic deficiencies. In addition, the framework learns priors of constitutive models without explicitly knowing their functional form, providing a new model-agnostic approach to learning hidden constitutive behaviors from data.

References in corpus (11)

• Uncertainty Quantification in Scientific Machine Learning: Methods, Metrics, and Comparisons
• A new family of Constitutive Artificial Neural Networks towards automated model discovery
• Bayesian Physics-Informed Neural Networks for real-world nonlinear dynamical systems
• NN-EUCLID: deep-learning hyperelasticity without stress data
• Recent Advances and Applications of Machine Learning in Experimental Solid Mechanics: A Review
• Operator learning for predicting multiscale bubble growth dynamics
• Interfacing Finite Elements with Deep Neural Operators for Fast Multiscale Modeling of Mechanics Problems
• Physics-Informed Neural Networks for Nonhomogeneous Material Identification in Elasticity Imaging
• NeuralUQ: A comprehensive library for uncertainty quantification in neural differential equations and operators
• G2Φnet: Relating Genotype and Biomechanical Phenotype of Tissues with Deep Learning
• Blending Neural Operators and Relaxation Methods in PDE Numerical Solvers

Cited by in corpus (1)

• Fast meta-solvers for 3D complex-shape scatterers using neural operators trained on a non-scattering problem