TAEN: A Model-Constrained Tikhonov Autoencoder Network for Forward and Inverse Problems

Abstract

Efficient real-time solvers for forward and inverse problems are essential in engineering and science applications. Machine learning surrogate models have emerged as promising alternatives to traditional methods, offering substantially reduced computational time. Nevertheless, these models typically demand extensive training datasets to achieve robust generalization across diverse scenarios. While physics-based approaches can partially mitigate this data dependency and ensure physics-interpretable solutions, addressing scarce data regimes remains a challenge. Both purely data-driven and physics-based machine learning approaches demonstrate severe overfitting issues when trained with insufficient data. We propose a novel Tikhonov autoencoder model-constrained framework, called TAE, capable of learning both forward and inverse surrogate models using a single arbitrary observation sample. We develop comprehensive theoretical foundations including forward and inverse inference error bounds for the proposed approach for linear cases. For comparative analysis, we derive equivalent formulations for pure data-driven and model-constrained approach counterparts. At the heart of our approach is a data randomization strategy, which functions as a generative mechanism for exploring the training data space, enabling effective training of both forward and inverse surrogate models from a single observation, while regularizing the learning process. We validate our approach through extensive numerical experiments on two challenging inverse problems: 2D heat conductivity inversion and initial condition reconstruction for time-dependent 2D Navier-Stokes equations. Results demonstrate that TAE achieves accuracy comparable to traditional Tikhonov solvers and numerical forward solvers for both inverse and forward problems, respectively, while delivering orders of magnitude computational speedups.

References in corpus (16)

• DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators
• Training deep neural networks for the inverse design of nanophotonic structures
• MoDL: Model Based Deep Learning Architecture for Inverse Problems
• Gradient-enhanced physics-informed neural networks for forward and inverse PDE problems
• Physics-informed neural networks for inverse problems in nano-optics and metamaterials
• Transformers for Modeling Physical Systems
• Multi-level Convolutional Autoencoder Networks for Parametric Prediction of Spatio-temporal Dynamics
• Long-time predictive modeling of nonlinear dynamical systems using neural networks
• Implicit Full Waveform Inversion with Deep Neural Representation
• Solving inverse-PDE problems with physics-aware neural networks
• Adversarial Regularizers in Inverse Problems
• Accelerating MCMC with active subspaces
• Model Order Reduction based on Runge-Kutta Neural Network
• Derivative-Informed Neural Operator: An Efficient Framework for High-Dimensional Parametric Derivative Learning
• Two new calibration techniques of lumped-parameter mathematical models for the cardiovascular system
• A Model-Constrained Tangent Slope Learning Approach for Dynamical Systems