Work

Inferring Underwater Topography with Finite Volume Neural Networks

Year: 2025

Type: conference-paper

Abstract: Partial differential equations (PDEs) find applications across various scientific and engineering fields.There is a growing trend for integrating physics-aware machine learning models to solve PDEs.Among them, the Finite Volume Neural Network (FINN) has proven to be efficient in uncovering latent structures in data.This study explores the capabilities of FINN in the investigation of shallow-water equations, which simulate wave dynamics in coastal regions.Specifically, we investigate the efficacy of FINN in reconstructing underwater topography.We find that FINN excels at inferring topography solely from wave dynamics, stressing the importance of application-specific inductive bias in neural network architectures.

Source: European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN)

DOI: 10.14428/esann/2025.es2025-12

Authors: Cosku Horuz, Matthias Karlbauer, Timothy Praditia, Sergey Oladyshkin, Wolfgang Nowak, Sebastian Otte

Institutions: University of Lübeck, University of Tübingen, University of Stuttgart

Language: English

Topic: Model Reduction and Neural Networks

Subfield: Statistical and Nonlinear Physics

Field: Physics and Astronomy

Domain: Physical Sciences

Open Access status: bronze

OpenAlex ID: W4409479718

FWCI:

Cites:

Cited by:

Related to: 10