Exploring deep learning capabilities for surge predictions in coastal areas

Abstract To improve coastal adaptation and management, it is critical to better understand and predict the characteristics of sea levels. Here, we explore the capabilities of artificial intelligence, from four deep learning methods to predict the surge component of sea-level variability based on loc...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Timothy Tiggeloven, Anaïs Couasnon, Chiem van Straaten, Sanne Muis, Philip J. Ward
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/0ed3964985f849d4808e3ae38d7d2888
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:0ed3964985f849d4808e3ae38d7d2888
record_format dspace
spelling oai:doaj.org-article:0ed3964985f849d4808e3ae38d7d28882021-12-02T18:53:18ZExploring deep learning capabilities for surge predictions in coastal areas10.1038/s41598-021-96674-02045-2322https://doaj.org/article/0ed3964985f849d4808e3ae38d7d28882021-08-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-96674-0https://doaj.org/toc/2045-2322Abstract To improve coastal adaptation and management, it is critical to better understand and predict the characteristics of sea levels. Here, we explore the capabilities of artificial intelligence, from four deep learning methods to predict the surge component of sea-level variability based on local atmospheric conditions. We use an Artificial Neural Networks, Convolutional Neural Network, Long Short-Term Memory layer (LSTM) and a combination of the latter two (ConvLSTM), to construct ensembles of Neural Network (NN) models at 736 tide stations globally. The NN models show similar patterns of performance, with much higher skill in the mid-latitudes. Using our global model settings, the LSTM generally outperforms the other NN models. Furthermore, for 15 stations we assess the influence of adding complexity more predictor variables. This generally improves model performance but leads to substantial increases in computation time. The improvement in performance remains insufficient to fully capture observed dynamics in some regions. For example, in the tropics only modelling surges is insufficient to capture intra-annual sea level variability. While we focus on minimising mean absolute error for the full time series, the NN models presented here could be adapted for use in forecasting extreme sea levels or emergency response.Timothy TiggelovenAnaïs CouasnonChiem van StraatenSanne MuisPhilip J. WardNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-15 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Timothy Tiggeloven
Anaïs Couasnon
Chiem van Straaten
Sanne Muis
Philip J. Ward
Exploring deep learning capabilities for surge predictions in coastal areas
description Abstract To improve coastal adaptation and management, it is critical to better understand and predict the characteristics of sea levels. Here, we explore the capabilities of artificial intelligence, from four deep learning methods to predict the surge component of sea-level variability based on local atmospheric conditions. We use an Artificial Neural Networks, Convolutional Neural Network, Long Short-Term Memory layer (LSTM) and a combination of the latter two (ConvLSTM), to construct ensembles of Neural Network (NN) models at 736 tide stations globally. The NN models show similar patterns of performance, with much higher skill in the mid-latitudes. Using our global model settings, the LSTM generally outperforms the other NN models. Furthermore, for 15 stations we assess the influence of adding complexity more predictor variables. This generally improves model performance but leads to substantial increases in computation time. The improvement in performance remains insufficient to fully capture observed dynamics in some regions. For example, in the tropics only modelling surges is insufficient to capture intra-annual sea level variability. While we focus on minimising mean absolute error for the full time series, the NN models presented here could be adapted for use in forecasting extreme sea levels or emergency response.
format article
author Timothy Tiggeloven
Anaïs Couasnon
Chiem van Straaten
Sanne Muis
Philip J. Ward
author_facet Timothy Tiggeloven
Anaïs Couasnon
Chiem van Straaten
Sanne Muis
Philip J. Ward
author_sort Timothy Tiggeloven
title Exploring deep learning capabilities for surge predictions in coastal areas
title_short Exploring deep learning capabilities for surge predictions in coastal areas
title_full Exploring deep learning capabilities for surge predictions in coastal areas
title_fullStr Exploring deep learning capabilities for surge predictions in coastal areas
title_full_unstemmed Exploring deep learning capabilities for surge predictions in coastal areas
title_sort exploring deep learning capabilities for surge predictions in coastal areas
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/0ed3964985f849d4808e3ae38d7d2888
work_keys_str_mv AT timothytiggeloven exploringdeeplearningcapabilitiesforsurgepredictionsincoastalareas
AT anaiscouasnon exploringdeeplearningcapabilitiesforsurgepredictionsincoastalareas
AT chiemvanstraaten exploringdeeplearningcapabilitiesforsurgepredictionsincoastalareas
AT sannemuis exploringdeeplearningcapabilitiesforsurgepredictionsincoastalareas
AT philipjward exploringdeeplearningcapabilitiesforsurgepredictionsincoastalareas
_version_ 1718377308846292992