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

• URL: http://arxiv.org/abs/2412.07010v2
• Date: Mon, 30 Dec 2024 03:52:19 GMT
• Title: TAEN: A Model-Constrained Tikhonov Autoencoder Network for Forward and Inverse Problems
• Authors: Hai V. Nguyen, Tan Bui-Thanh, Clint Dawson,
• Abstract summary: 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. These models typically demand extensive training datasets to achieve robust generalization across diverse scenarios. 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.
• Score: 0.6144680854063939
• License:
• 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.

Related papers

• Bayesian Model Parameter Learning in Linear Inverse Problems with Application in EEG Focal Source Imaging [49.1574468325115]
  Inverse problems can be described as limited-data problems in which the signal of interest cannot be observed directly. We studied a linear inverse problem that included an unknown non-linear model parameter. We utilized a Bayesian model-based learning approach that allowed signal recovery and subsequently estimation of the model parameter.
  arXiv  Detail & Related papers  (2025-01-07T18:14:24Z)
• On conditional diffusion models for PDE simulations [53.01911265639582]
  We study score-based diffusion models for forecasting and assimilation of sparse observations. We propose an autoregressive sampling approach that significantly improves performance in forecasting. We also propose a new training strategy for conditional score-based models that achieves stable performance over a range of history lengths.
  arXiv  Detail & Related papers  (2024-10-21T18:31:04Z)
• Solving Inverse Problems with Model Mismatch using Untrained Neural Networks within Model-based Architectures [14.551812310439004]
  We introduce an untrained forward model residual block within the model-based architecture to match the data consistency in the measurement domain for each instance. Our approach offers a unified solution that is less parameter-sensitive, requires no additional data, and enables simultaneous fitting of the forward model and reconstruction in a single pass.
  arXiv  Detail & Related papers  (2024-03-07T19:02:13Z)
• Learning-based adaption of robotic friction models [48.453527255659296]
  We introduce a novel approach to adapt an existing friction model to new dynamics using as little data as possible. Our proposed estimator outperforms the conventional model-based approach and the base neural network significantly. Our method does not rely on data with external load during training, eliminating the need for external torque sensors.
  arXiv  Detail & Related papers  (2023-10-25T14:50:15Z)
• Discovering Interpretable Physical Models using Symbolic Regression and Discrete Exterior Calculus [55.2480439325792]
  We propose a framework that combines Symbolic Regression (SR) and Discrete Exterior Calculus (DEC) for the automated discovery of physical models. DEC provides building blocks for the discrete analogue of field theories, which are beyond the state-of-the-art applications of SR to physical problems. We prove the effectiveness of our methodology by re-discovering three models of Continuum Physics from synthetic experimental data.
  arXiv  Detail & Related papers  (2023-10-10T13:23:05Z)
• Towards a Better Theoretical Understanding of Independent Subnetwork Training [56.24689348875711]
  We take a closer theoretical look at Independent Subnetwork Training (IST) IST is a recently proposed and highly effective technique for solving the aforementioned problems. We identify fundamental differences between IST and alternative approaches, such as distributed methods with compressed communication.
  arXiv  Detail & Related papers  (2023-06-28T18:14:22Z)
• Self-Validated Physics-Embedding Network: A General Framework for Inverse Modelling [2.449329947677678]
  Self-Embedding Physics-Embedding Network (SVPEN) is a general neural network framework for inverse modeling. The embedded physical forward model ensures that any solution that successfully passes its validation is physically reasonable. More than ten case studies in two highly nonlinear and entirely distinct applications are presented.
  arXiv  Detail & Related papers  (2022-10-12T10:31:36Z)
• HyperImpute: Generalized Iterative Imputation with Automatic Model Selection [77.86861638371926]
  We propose a generalized iterative imputation framework for adaptively and automatically configuring column-wise models. We provide a concrete implementation with out-of-the-box learners, simulators, and interfaces.
  arXiv  Detail & Related papers  (2022-06-15T19:10:35Z)
• Learning new physics efficiently with nonparametric methods [11.970219534238444]
  We present a machine learning approach for model-independent new physics searches. The corresponding algorithm is powered by recent large-scale implementations of kernel methods. We show that our approach has dramatic advantages compared to neural network implementations in terms of training times and computational resources.
  arXiv  Detail & Related papers  (2022-04-05T16:17:59Z)
• Improved Surrogate Modeling of Fluid Dynamics with Physics-Informed Neural Networks [0.0]
  PINNs have recently shown great promise as a way of incorporating physics-based domain knowledge, including fundamental governing equations, into neural network models. Here, we explore the use of this modeling methodology to surrogate modeling of a fluid dynamical system. We show that the inclusion of a physics-based regularization term can substantially improve the equivalent data-driven surrogate model.
  arXiv  Detail & Related papers  (2021-05-05T02:23:20Z)
• Physics Informed Deep Learning for Transport in Porous Media. Buckley Leverett Problem [0.0]
  We present a new hybrid physics-based machine-learning approach to reservoir modeling. The methodology relies on a series of deep adversarial neural network architecture with physics-based regularization. The proposed methodology is a simple and elegant way to instill physical knowledge to machine-learning algorithms.
  arXiv  Detail & Related papers  (2020-01-15T08:20:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.