PETAL: Physics Emulation Through Averaged Linearizations for Solving Inverse Problems

TL;DR

This paper introduces PETAL, a physics-informed surrogate model for inverse problems that embeds linearizations of the forward model to improve accuracy and efficiency in signal recovery, demonstrated on ocean acoustic tomography.

Contribution

Proposes a physics-embedded learned weighted average model that incorporates linearizations to enhance inverse problem solving accuracy.

Findings

Improved signal recovery accuracy in ocean acoustic tomography.

Physics-based linearizations enhance gradient information during inversion.

Demonstrated effectiveness in ocean sound speed profile estimation.

Abstract

Inverse problems describe the task of recovering an underlying signal of interest given observables. Typically, the observables are related via some non-linear forward model applied to the underlying unknown signal. Inverting the non-linear forward model can be computationally expensive, as it often involves computing and inverting a linearization at a series of estimates. Rather than inverting the physics-based model, we instead train a surrogate forward model (emulator) and leverage modern auto-grad libraries to solve for the input within a classical optimization framework. Current methods to train emulators are done in a black box supervised machine learning fashion and fail to take advantage of any existing knowledge of the forward model. In this article, we propose a simple learned weighted average model that embeds linearizations of the forward model around various reference points into the model itself, explicitly incorporating known physics. Grounding the learned model with physics based linearizations improves the forward modeling accuracy and provides richer physics based gradient information during the inversion process leading to more accurate signal recovery. We demonstrate the efficacy on an ocean acoustic tomography (OAT) example that aims to recover ocean sound speed profile (SSP) variations from acoustic observations (e.g. eigenray arrival times) within simulation of ocean dynamics in the Gulf of Mexico.