Predicting beach profiles with machine learning from offshore wave reflection spectra - BRGM - Bureau de recherches géologiques et minières
Journal Articles Environmental Modelling and Software Year : 2025

Predicting beach profiles with machine learning from offshore wave reflection spectra

Abstract

Tracking and forecasting changes in coastal morphology is vital for development, risk reduction, and overall coastal management. One challenge of current coastal research and engineering is to find a method able to accurately assess the bathymetry profile along the coast and key parameters such as slope and sandbars. Traditional bathymetry measurements are obtained through echo-sounding, which is time-consuming, hazardous and costly. Using a variety of simulated cases, we test the potential of machine learning and in particular Neural Networks to reconstruct the coastal bathymetry profile from offshore sensed waves, based on shore-based wave reflection. Features such as foreshore slope, curvature, sandbars amplitude and positions can be captured.
Fichier principal
Vignette du fichier
1-s2.0-S1364815224002822-main.pdf (3.12 Mo) Télécharger le fichier
Origin Publication funded by an institution
Licence

Dates and versions

hal-04717243 , version 1 (01-10-2024)

Licence

Identifiers

Cite

Elsa Disdier, Rafael Almar, Rachid Benshila, Mahmoud Al Najar, Romain Chassagne, et al.. Predicting beach profiles with machine learning from offshore wave reflection spectra. Environmental Modelling and Software, 2025, 183, pp.106221. ⟨10.1016/j.envsoft.2024.106221⟩. ⟨hal-04717243⟩
81 View
15 Download

Altmetric

Share

More