An efficient artificial intelligence model for prediction of tropical storm surge
Process-based models have been widely used for storm surge predictions, but their high computational demand is a major drawback in some applications such as rapid forecasting. Few efforts have been made to employ previous databases of synthetic/real storms and provide more efficient surge prediction...
Published in: | Natural Hazards |
---|---|
Main Authors: | , , , , |
Format: | Text |
Language: | unknown |
Published: |
DigitalCommons@URI
2016
|
Subjects: | |
Online Access: | https://digitalcommons.uri.edu/oce_facpubs/234 https://doi.org/10.1007/s11069-016-2193-4 |
id |
ftunivrhodeislan:oai:digitalcommons.uri.edu:oce_facpubs-1233 |
---|---|
record_format |
openpolar |
spelling |
ftunivrhodeislan:oai:digitalcommons.uri.edu:oce_facpubs-1233 2024-09-15T18:24:08+00:00 An efficient artificial intelligence model for prediction of tropical storm surge Hashemi, M. Reza Spaulding, Malcolm L. Shaw, Alex Farhadi, Hamed Lewis, Matt 2016-05-01T07:00:00Z https://digitalcommons.uri.edu/oce_facpubs/234 https://doi.org/10.1007/s11069-016-2193-4 unknown DigitalCommons@URI https://digitalcommons.uri.edu/oce_facpubs/234 doi:10.1007/s11069-016-2193-4 https://doi.org/10.1007/s11069-016-2193-4 Ocean Engineering Faculty Publications Artificial neural networks Hurricane NACCS Rhode Island Storm surge text 2016 ftunivrhodeislan https://doi.org/10.1007/s11069-016-2193-4 2024-08-21T00:09:34Z Process-based models have been widely used for storm surge predictions, but their high computational demand is a major drawback in some applications such as rapid forecasting. Few efforts have been made to employ previous databases of synthetic/real storms and provide more efficient surge predictions (e.g. using storm similarity of an individual storm to those in the database). Here, we develop an alternative efficient and robust artificial intelligent model, which predicts the peak storm surge using the tropical storm parameters: central pressure, radius to maximum winds, forward velocity, and storm track. The US Army Corp of Engineers, North Atlantic Comprehensive Coastal Study, has recently performed numerical simulations of 1050 synthetic tropical storms, which statistically represent tropical storms, using a coupled high resolution wave–surge modeling system for the east coast of the US, from Cape Hatteras to the Canadian border. This study has provided an unprecedented dataset which can be used to train artificial intelligence models for surge prediction in those areas. While numerical simulation of a storm surge at this scale and resolution (over 6 million elements scaling from 20 m to more than 100 km) is extremely expensive, the artificial intelligence takes the advantage of the previous simulations, and effectively learns the relationship between storm parameters representing storm forcing and surge. The artificial neural network method which was used for this study, was shown to outperform support vector machine for extreme storms. ANN model, which is based on a neurobiological analogy, can be conveniently developed, retrained by new data, and is nonparametric. The AI model, which was developed for Rhode Island, was validated using a set of randomly selected synthetic storms as well as real tropical storms in this region. The model performance was found satisfactory with root-mean-square error of <35 cm for observed and synthetic storms. It was also shown that it is not possible to develop a ... Text North Atlantic University of Rhode Island: DigitalCommons@URI Natural Hazards 82 1 471 491 |
institution |
Open Polar |
collection |
University of Rhode Island: DigitalCommons@URI |
op_collection_id |
ftunivrhodeislan |
language |
unknown |
topic |
Artificial neural networks Hurricane NACCS Rhode Island Storm surge |
spellingShingle |
Artificial neural networks Hurricane NACCS Rhode Island Storm surge Hashemi, M. Reza Spaulding, Malcolm L. Shaw, Alex Farhadi, Hamed Lewis, Matt An efficient artificial intelligence model for prediction of tropical storm surge |
topic_facet |
Artificial neural networks Hurricane NACCS Rhode Island Storm surge |
description |
Process-based models have been widely used for storm surge predictions, but their high computational demand is a major drawback in some applications such as rapid forecasting. Few efforts have been made to employ previous databases of synthetic/real storms and provide more efficient surge predictions (e.g. using storm similarity of an individual storm to those in the database). Here, we develop an alternative efficient and robust artificial intelligent model, which predicts the peak storm surge using the tropical storm parameters: central pressure, radius to maximum winds, forward velocity, and storm track. The US Army Corp of Engineers, North Atlantic Comprehensive Coastal Study, has recently performed numerical simulations of 1050 synthetic tropical storms, which statistically represent tropical storms, using a coupled high resolution wave–surge modeling system for the east coast of the US, from Cape Hatteras to the Canadian border. This study has provided an unprecedented dataset which can be used to train artificial intelligence models for surge prediction in those areas. While numerical simulation of a storm surge at this scale and resolution (over 6 million elements scaling from 20 m to more than 100 km) is extremely expensive, the artificial intelligence takes the advantage of the previous simulations, and effectively learns the relationship between storm parameters representing storm forcing and surge. The artificial neural network method which was used for this study, was shown to outperform support vector machine for extreme storms. ANN model, which is based on a neurobiological analogy, can be conveniently developed, retrained by new data, and is nonparametric. The AI model, which was developed for Rhode Island, was validated using a set of randomly selected synthetic storms as well as real tropical storms in this region. The model performance was found satisfactory with root-mean-square error of <35 cm for observed and synthetic storms. It was also shown that it is not possible to develop a ... |
format |
Text |
author |
Hashemi, M. Reza Spaulding, Malcolm L. Shaw, Alex Farhadi, Hamed Lewis, Matt |
author_facet |
Hashemi, M. Reza Spaulding, Malcolm L. Shaw, Alex Farhadi, Hamed Lewis, Matt |
author_sort |
Hashemi, M. Reza |
title |
An efficient artificial intelligence model for prediction of tropical storm surge |
title_short |
An efficient artificial intelligence model for prediction of tropical storm surge |
title_full |
An efficient artificial intelligence model for prediction of tropical storm surge |
title_fullStr |
An efficient artificial intelligence model for prediction of tropical storm surge |
title_full_unstemmed |
An efficient artificial intelligence model for prediction of tropical storm surge |
title_sort |
efficient artificial intelligence model for prediction of tropical storm surge |
publisher |
DigitalCommons@URI |
publishDate |
2016 |
url |
https://digitalcommons.uri.edu/oce_facpubs/234 https://doi.org/10.1007/s11069-016-2193-4 |
genre |
North Atlantic |
genre_facet |
North Atlantic |
op_source |
Ocean Engineering Faculty Publications |
op_relation |
https://digitalcommons.uri.edu/oce_facpubs/234 doi:10.1007/s11069-016-2193-4 https://doi.org/10.1007/s11069-016-2193-4 |
op_doi |
https://doi.org/10.1007/s11069-016-2193-4 |
container_title |
Natural Hazards |
container_volume |
82 |
container_issue |
1 |
container_start_page |
471 |
op_container_end_page |
491 |
_version_ |
1810464452399595520 |