The intensification of extreme events, storm surges and coastal flooding in a climate change scenario increasingly influences human processes, especially in coastal areas where sea-based activities are concentrated. Predicting sea level near the coasts, with a high accuracy and in a reasonable amount of time, becomes a strategic task. Despite the developments of complex numerical codes for high-resolution ocean modeling, the task of making forecasts in areas at the intersection between land and sea remains challenging. In this respect, the use of machine learning techniques can represent an interesting alternative to be investigated and evaluated by numerical modelers. This article presents the application of the Long-Short Term Memory (LSTM) neural network to the problem of short-term sea level forecasting in the Southern Adriatic Northern Ionian (SANI) domain in the Mediterranean sea. The proposed multi-model architecture based on LSTM networks has been trained to predict mean sea levels three days ahead, for different coastal locations. Predictions were compared with the observation data collected through the tide-gauge devices as well as with the forecasts produced by the Southern Adriatic Northern Ionian Forecasting System (SANIFS) developed at the Euro-Mediterranean Center on Climate Change (CMCC), which provides short-term daily updated forecasts in the Mediterranean basin. Experimental results demonstrate that the multi-model architecture is able to bridge information far in time and to produce predictions with a much higher accuracy than SANIFS forecasts.

A multi-model architecture based on Long Short-Term Memory neural networks for multi-step sea level forecasting / Accarino, G.; Chiarelli, M.; Fiore, S.; Federico, I.; Causio, S.; Coppini, G.; Aloisio, G.. - In: FUTURE GENERATION COMPUTER SYSTEMS. - ISSN 0167-739X. - 124:(2021), pp. 1-9. [10.1016/j.future.2021.05.008]

A multi-model architecture based on Long Short-Term Memory neural networks for multi-step sea level forecasting

Fiore S.;
2021-01-01

Abstract

The intensification of extreme events, storm surges and coastal flooding in a climate change scenario increasingly influences human processes, especially in coastal areas where sea-based activities are concentrated. Predicting sea level near the coasts, with a high accuracy and in a reasonable amount of time, becomes a strategic task. Despite the developments of complex numerical codes for high-resolution ocean modeling, the task of making forecasts in areas at the intersection between land and sea remains challenging. In this respect, the use of machine learning techniques can represent an interesting alternative to be investigated and evaluated by numerical modelers. This article presents the application of the Long-Short Term Memory (LSTM) neural network to the problem of short-term sea level forecasting in the Southern Adriatic Northern Ionian (SANI) domain in the Mediterranean sea. The proposed multi-model architecture based on LSTM networks has been trained to predict mean sea levels three days ahead, for different coastal locations. Predictions were compared with the observation data collected through the tide-gauge devices as well as with the forecasts produced by the Southern Adriatic Northern Ionian Forecasting System (SANIFS) developed at the Euro-Mediterranean Center on Climate Change (CMCC), which provides short-term daily updated forecasts in the Mediterranean basin. Experimental results demonstrate that the multi-model architecture is able to bridge information far in time and to produce predictions with a much higher accuracy than SANIFS forecasts.
2021
Accarino, G.; Chiarelli, M.; Fiore, S.; Federico, I.; Causio, S.; Coppini, G.; Aloisio, G.
A multi-model architecture based on Long Short-Term Memory neural networks for multi-step sea level forecasting / Accarino, G.; Chiarelli, M.; Fiore, S.; Federico, I.; Causio, S.; Coppini, G.; Aloisio, G.. - In: FUTURE GENERATION COMPUTER SYSTEMS. - ISSN 0167-739X. - 124:(2021), pp. 1-9. [10.1016/j.future.2021.05.008]
File in questo prodotto:
File Dimensione Formato  
1-s2.0-S0167739X21001588-main.pdf

Solo gestori archivio

Descrizione: Articolo principale
Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 2.74 MB
Formato Adobe PDF
2.74 MB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/324938
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 12
  • ???jsp.display-item.citation.isi??? 9
social impact