Neural Inverse Operators for Solving PDE Inverse Problems

arXiv2301.11167MaRDI QIDQ6424477FDOQ6424477

Authors: Roberto Molinaro, Yunan Yang, Björn Engquist, Siddhartha Mishra 

Publication date: 26 January 2023

Abstract: A large class of inverse problems for PDEs are only well-defined as mappings from operators to functions. Existing operator learning frameworks map functions to functions and need to be modified to learn inverse maps from data. We propose a novel architecture termed Neural Inverse Operators (NIOs) to solve these PDE inverse problems. Motivated by the underlying mathematical structure, NIO is based on a suitable composition of DeepONets and FNOs to approximate mappings from operators to functions. A variety of experiments are presented to demonstrate that NIOs significantly outperform baselines and solve PDE inverse problems robustly, accurately and are several orders of magnitude faster than existing direct and PDE-constrained optimization methods.

This page was built for publication: Neural Inverse Operators for Solving PDE Inverse Problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6424477)