Efficient Deep Learning Surrogate Method for Predicting the Transport of Particle Patches in Coastal Environments

45 Pages Posted: 2 May 2024

See all articles by Jeancarlo M. Fajardo-Urbina

Jeancarlo M. Fajardo-Urbina

affiliation not provided to SSRN

Yang Liu

Netherlands eScience Center

Sonja Georgievska

Netherlands eScience Center

Ulf Gräwe

affiliation not provided to SSRN

Herman J.H. Clercx

affiliation not provided to SSRN

Theo Gerkema

affiliation not provided to SSRN

Matias Duran-Matute

affiliation not provided to SSRN

Abstract

Several coastal regions require operational forecast systems for predicting the transport of pollutants released during marine accidents. In response to this need, surrogate models offer cost-effective solutions. Here, we propose a surrogate modeling method for predicting the transport of particle patches in coastal environments. These patches are collections of passive particles equivalent to Eulerian tracers but can be extended to other particulates. By only using relevant forcing, we train a deep learning model (DLM) to predict the displacement (advection) and spread (dispersion) of particle patches after one tidal period. These quantities are then coupled into a simplified Lagrangian model to obtain predictions for larger times. Predictions with our methodology, successfully applied in the Dutch Wadden Sea, are fast. The trained DLM provides predictions in a few seconds, and our simplified Lagrangian model is one to two orders of magnitude faster than a traditional Lagrangian model fed with currents.

Keywords: Deep learning surrogate modeling, Lagrangian pollution modeling, Lagrangian advection and dispersion, Coastal systems, Dutch Wadden Sea

Suggested Citation

Fajardo-Urbina, Jeancarlo M. and Liu, Yang and Georgievska, Sonja and Gräwe, Ulf and Clercx, Herman J.H. and Gerkema, Theo and Duran-Matute, Matias, Efficient Deep Learning Surrogate Method for Predicting the Transport of Particle Patches in Coastal Environments. Available at SSRN: https://ssrn.com/abstract=4815334 or http://dx.doi.org/10.2139/ssrn.4815334

Jeancarlo M. Fajardo-Urbina

affiliation not provided to SSRN ( email )

No Address Available

Yang Liu

Netherlands eScience Center ( email )

Netherlands

Sonja Georgievska

Netherlands eScience Center ( email )

Netherlands

Ulf Gräwe

affiliation not provided to SSRN ( email )

No Address Available

Herman J.H. Clercx

affiliation not provided to SSRN ( email )

No Address Available

Theo Gerkema

affiliation not provided to SSRN ( email )

No Address Available

Matias Duran-Matute (Contact Author)

affiliation not provided to SSRN ( email )

No Address Available

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
46
Abstract Views
163
PlumX Metrics