Discretization of parameter identification in PDEs using Neural Networks
arXiv:2108.10618 · doi:10.1088/1361-6420/ac9c25
Abstract
We consider the ill-posed inverse problem of identifying a nonlinearity in a time-dependent PDE model. The nonlinearity is approximated by a neural network, and needs to be determined alongside other unknown physical parameters and the unknown state. Hence, it is not possible to construct input-output data pairs to perform a supervised training process. Proposing an all-at-once approach, we bypass the need for training data and recover all the unknowns simultaneously. In the general case, the approximation via a neural network can be realized as a discretization scheme, and the training with noisy data can be viewed as an ill-posed inverse problem. Therefore, we study discretization of regularization in terms of Tikhonov and projected Landweber methods for discretization of inverse problems, and prove convergence when the discretization error (network approximation error) and the noise level tend to zero.
References in corpus (13)
- Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
- PDE-Net: Learning PDEs from Data
- Deep Network Approximation for Smooth Functions
- A penalty method for PDE-constrained optimization in inverse problems
- Higher-order total variation approaches and generalisations
- All-at-once versus reduced iterative methods for time dependent inverse problems
- Data driven regularization by projection
- Discretization of variational regularization in Banach spaces
- Goal oriented adaptivity in the IRGNM for parameter identification in PDEs II: all-at once formulations
- Landweber-Kaczmarz for parameter identification in time-dependent inverse problems: All-at-once versus Reduced version
- Learning-informed parameter identification in nonlinear time-dependent PDEs
- Inverse problems on low-dimensional manifolds
- Optimization with learning-informed differential equation constraints and its applications