Physics-informed neural network for predicting unmeasured ocean acoustic pressure field

Abstract

This study employs a physics-informed neural network in an ocean waveguide to predict the unmeasured acoustic pressure field, leveraging partially measured data. The method addresses a scenario where an acoustic source transmits signals across different ranges and is measured by multiple receivers. The acoustic pressure field in ocean waveguides exhibits rapid spatial variations over kilometer-range scales. The fully connected neural networks encounter challenges when approximating high-frequency functions, known as spectral bias. To mitigate this problem, the measured pressure field is transformed into a low-frequency function for training the neural network. We propose two methods sharing the same neural network architecture but utilizing different information. The first method uses a complex value of the pressure field (i.e., both magnitude and phase), while the second method uses only magnitude. We validate the proposed methods using simulations and experimental data from the SWellEx-96 environment. Results demonstrate that the first method exhibits superior performance with sparse data, while the second method works better in real-world scenarios.