Storm Surge Forecast Using an Encoder–Decoder Recurrent Neural Network Model
This study presents an encoder–decoder neural network model to forecast storm surges on the US North Atlantic Coast. The proposed multivariate time-series forecast model consists of two long short-term memory (LSTM) models. The first LSTM model encodes the input sequence, including storm position, c...
Published in: | Journal of Marine Science and Engineering |
---|---|
Main Authors: | , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
MDPI AG
2022
|
Subjects: | |
Online Access: | https://doi.org/10.3390/jmse10121980 https://doaj.org/article/9dbee1e229634ff39102c863a76aa16c |
id |
ftdoajarticles:oai:doaj.org/article:9dbee1e229634ff39102c863a76aa16c |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:9dbee1e229634ff39102c863a76aa16c 2023-05-15T17:31:05+02:00 Storm Surge Forecast Using an Encoder–Decoder Recurrent Neural Network Model Zhangping Wei Hai Cong Nguyen 2022-12-01T00:00:00Z https://doi.org/10.3390/jmse10121980 https://doaj.org/article/9dbee1e229634ff39102c863a76aa16c EN eng MDPI AG https://www.mdpi.com/2077-1312/10/12/1980 https://doaj.org/toc/2077-1312 doi:10.3390/jmse10121980 2077-1312 https://doaj.org/article/9dbee1e229634ff39102c863a76aa16c Journal of Marine Science and Engineering, Vol 10, Iss 1980, p 1980 (2022) storm surge Atlantic hurricanes multivariate forecast recurrent neural network encoder–decoder model long short-term memory model Naval architecture. Shipbuilding. Marine engineering VM1-989 Oceanography GC1-1581 article 2022 ftdoajarticles https://doi.org/10.3390/jmse10121980 2022-12-30T19:31:24Z This study presents an encoder–decoder neural network model to forecast storm surges on the US North Atlantic Coast. The proposed multivariate time-series forecast model consists of two long short-term memory (LSTM) models. The first LSTM model encodes the input sequence, including storm position, central pressure, and the radius of the maximum winds to an internal state. The second LSTM model decodes the internal state to forecast the storm surge water level and velocity. The neural network model was developed based on a storm surge dataset generated by the North Atlantic Comprehensive Coastal Study using a physics-based storm surge model. The neural network model was trained to predict storm surges at three forecast lead times ranging from 3 h to 12 h by learning the correlation between the past storm conditions and future storm hazards. The results show that the computationally efficient neural network model can forecast a storm in a fraction of one second. The neural network model not only forecasts peak surges, but also predicts the time-series profile of a storm. Furthermore, the model is highly versatile, and it can forecast storm surges generated by different sizes and strengths of bypassing and landfalling storms. Overall, this work demonstrates the success of data-driven approaches to improve coastal hazard research. Article in Journal/Newspaper North Atlantic Directory of Open Access Journals: DOAJ Articles Journal of Marine Science and Engineering 10 12 1980 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
storm surge Atlantic hurricanes multivariate forecast recurrent neural network encoder–decoder model long short-term memory model Naval architecture. Shipbuilding. Marine engineering VM1-989 Oceanography GC1-1581 |
spellingShingle |
storm surge Atlantic hurricanes multivariate forecast recurrent neural network encoder–decoder model long short-term memory model Naval architecture. Shipbuilding. Marine engineering VM1-989 Oceanography GC1-1581 Zhangping Wei Hai Cong Nguyen Storm Surge Forecast Using an Encoder–Decoder Recurrent Neural Network Model |
topic_facet |
storm surge Atlantic hurricanes multivariate forecast recurrent neural network encoder–decoder model long short-term memory model Naval architecture. Shipbuilding. Marine engineering VM1-989 Oceanography GC1-1581 |
description |
This study presents an encoder–decoder neural network model to forecast storm surges on the US North Atlantic Coast. The proposed multivariate time-series forecast model consists of two long short-term memory (LSTM) models. The first LSTM model encodes the input sequence, including storm position, central pressure, and the radius of the maximum winds to an internal state. The second LSTM model decodes the internal state to forecast the storm surge water level and velocity. The neural network model was developed based on a storm surge dataset generated by the North Atlantic Comprehensive Coastal Study using a physics-based storm surge model. The neural network model was trained to predict storm surges at three forecast lead times ranging from 3 h to 12 h by learning the correlation between the past storm conditions and future storm hazards. The results show that the computationally efficient neural network model can forecast a storm in a fraction of one second. The neural network model not only forecasts peak surges, but also predicts the time-series profile of a storm. Furthermore, the model is highly versatile, and it can forecast storm surges generated by different sizes and strengths of bypassing and landfalling storms. Overall, this work demonstrates the success of data-driven approaches to improve coastal hazard research. |
format |
Article in Journal/Newspaper |
author |
Zhangping Wei Hai Cong Nguyen |
author_facet |
Zhangping Wei Hai Cong Nguyen |
author_sort |
Zhangping Wei |
title |
Storm Surge Forecast Using an Encoder–Decoder Recurrent Neural Network Model |
title_short |
Storm Surge Forecast Using an Encoder–Decoder Recurrent Neural Network Model |
title_full |
Storm Surge Forecast Using an Encoder–Decoder Recurrent Neural Network Model |
title_fullStr |
Storm Surge Forecast Using an Encoder–Decoder Recurrent Neural Network Model |
title_full_unstemmed |
Storm Surge Forecast Using an Encoder–Decoder Recurrent Neural Network Model |
title_sort |
storm surge forecast using an encoder–decoder recurrent neural network model |
publisher |
MDPI AG |
publishDate |
2022 |
url |
https://doi.org/10.3390/jmse10121980 https://doaj.org/article/9dbee1e229634ff39102c863a76aa16c |
genre |
North Atlantic |
genre_facet |
North Atlantic |
op_source |
Journal of Marine Science and Engineering, Vol 10, Iss 1980, p 1980 (2022) |
op_relation |
https://www.mdpi.com/2077-1312/10/12/1980 https://doaj.org/toc/2077-1312 doi:10.3390/jmse10121980 2077-1312 https://doaj.org/article/9dbee1e229634ff39102c863a76aa16c |
op_doi |
https://doi.org/10.3390/jmse10121980 |
container_title |
Journal of Marine Science and Engineering |
container_volume |
10 |
container_issue |
12 |
container_start_page |
1980 |
_version_ |
1766128398316339200 |