Predicting the Evolution of Extreme Water Levels With Long Short‐Term Memory Station‐Based Approximated Models and Transfer Learning Techniques

Abstract Extreme water levels (EWLs) resulting from cyclones pose significant flood hazards and risks to coastal communities and interconnected ecosystems. To date, physically based models have enabled accurate prediction of EWLs despite their inherent high computational cost. However, the applicabi...

Full description

Saved in:
Bibliographic Details
Main Authors: Samuel Daramola, David F. Muñoz, Paul Muñoz, Siddharth Saksena, Jennifer Irish
Format: Article
Language:English
Published: Wiley 2025-03-01
Series:Water Resources Research
Subjects:
Online Access:https://doi.org/10.1029/2024WR039054
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849422713762873344
author Samuel Daramola
David F. Muñoz
Paul Muñoz
Siddharth Saksena
Jennifer Irish
author_facet Samuel Daramola
David F. Muñoz
Paul Muñoz
Siddharth Saksena
Jennifer Irish
author_sort Samuel Daramola
collection DOAJ
description Abstract Extreme water levels (EWLs) resulting from cyclones pose significant flood hazards and risks to coastal communities and interconnected ecosystems. To date, physically based models have enabled accurate prediction of EWLs despite their inherent high computational cost. However, the applicability of these models is limited to data‐rich sites with diverse characteristics. The dependence on high quality spatiotemporal data, which is often computationally expensive, hinders the applicability of these models to regions of either limited or data‐scarce conditions. To address this challenge, we present a Long Short‐Term Memory (LSTM) network framework to predict the evolution of EWLs beyond site‐specific training stations. The framework, named LSTM‐Station Approximated Models (LSTM‐SAM), consists of a collection of bidirectional LSTM models enhanced with a custom attention mechanism layer embedded in the architecture. LSTM‐SAM incorporates a transfer learning approach applicable to target (tide‐gage) stations along the U.S. Atlantic Coast. Importantly, LSTM‐SAM helps analyze: (a) the underlying limitations associated with transfer learning, (b) evaluate EWL predictions beyond training domains, and (c) capture the evolution of EWL caused by tropical and extratropical cyclones. The framework demonstrates satisfactory performance with “transferable” models achieving Kling‐Gupta Efficiency (KGE), Nash‐Sutcliffe Efficiency (NSE), and Root‐Mean Square Error (RMSE) ranging from 0.78 to 0.92, 0.90 to 0.97, and 0.09–0.18 m at the target stations, respectively. We show that LSTM‐SAM can accurately predict not only EWLs but also their evolution over time, that is, onset, peak, and dissipation, which could assist in operational flood forecasting in regions with limited resources to set up physically based models.
format Article
id doaj-art-d02e27716f1b4eb48a8d8f99529c090f
institution Kabale University
issn 0043-1397
1944-7973
language English
publishDate 2025-03-01
publisher Wiley
record_format Article
series Water Resources Research
spelling doaj-art-d02e27716f1b4eb48a8d8f99529c090f2025-08-20T03:30:57ZengWileyWater Resources Research0043-13971944-79732025-03-01613n/an/a10.1029/2024WR039054Predicting the Evolution of Extreme Water Levels With Long Short‐Term Memory Station‐Based Approximated Models and Transfer Learning TechniquesSamuel Daramola0David F. Muñoz1Paul Muñoz2Siddharth Saksena3Jennifer Irish4Department of Civil and Environmental Engineering Virginia Tech Blacksburg VA USADepartment of Civil and Environmental Engineering Virginia Tech Blacksburg VA USADepartment of Water and Climate Vrije Universiteit Brussel (VUB) Brussels VA USADepartment of Civil and Environmental Engineering Virginia Tech Blacksburg VA USADepartment of Civil and Environmental Engineering Virginia Tech Blacksburg VA USAAbstract Extreme water levels (EWLs) resulting from cyclones pose significant flood hazards and risks to coastal communities and interconnected ecosystems. To date, physically based models have enabled accurate prediction of EWLs despite their inherent high computational cost. However, the applicability of these models is limited to data‐rich sites with diverse characteristics. The dependence on high quality spatiotemporal data, which is often computationally expensive, hinders the applicability of these models to regions of either limited or data‐scarce conditions. To address this challenge, we present a Long Short‐Term Memory (LSTM) network framework to predict the evolution of EWLs beyond site‐specific training stations. The framework, named LSTM‐Station Approximated Models (LSTM‐SAM), consists of a collection of bidirectional LSTM models enhanced with a custom attention mechanism layer embedded in the architecture. LSTM‐SAM incorporates a transfer learning approach applicable to target (tide‐gage) stations along the U.S. Atlantic Coast. Importantly, LSTM‐SAM helps analyze: (a) the underlying limitations associated with transfer learning, (b) evaluate EWL predictions beyond training domains, and (c) capture the evolution of EWL caused by tropical and extratropical cyclones. The framework demonstrates satisfactory performance with “transferable” models achieving Kling‐Gupta Efficiency (KGE), Nash‐Sutcliffe Efficiency (NSE), and Root‐Mean Square Error (RMSE) ranging from 0.78 to 0.92, 0.90 to 0.97, and 0.09–0.18 m at the target stations, respectively. We show that LSTM‐SAM can accurately predict not only EWLs but also their evolution over time, that is, onset, peak, and dissipation, which could assist in operational flood forecasting in regions with limited resources to set up physically based models.https://doi.org/10.1029/2024WR039054long short‐term memory networkstransfer learningextreme water levelcyclonesattention layer
spellingShingle Samuel Daramola
David F. Muñoz
Paul Muñoz
Siddharth Saksena
Jennifer Irish
Predicting the Evolution of Extreme Water Levels With Long Short‐Term Memory Station‐Based Approximated Models and Transfer Learning Techniques
Water Resources Research
long short‐term memory networks
transfer learning
extreme water level
cyclones
attention layer
title Predicting the Evolution of Extreme Water Levels With Long Short‐Term Memory Station‐Based Approximated Models and Transfer Learning Techniques
title_full Predicting the Evolution of Extreme Water Levels With Long Short‐Term Memory Station‐Based Approximated Models and Transfer Learning Techniques
title_fullStr Predicting the Evolution of Extreme Water Levels With Long Short‐Term Memory Station‐Based Approximated Models and Transfer Learning Techniques
title_full_unstemmed Predicting the Evolution of Extreme Water Levels With Long Short‐Term Memory Station‐Based Approximated Models and Transfer Learning Techniques
title_short Predicting the Evolution of Extreme Water Levels With Long Short‐Term Memory Station‐Based Approximated Models and Transfer Learning Techniques
title_sort predicting the evolution of extreme water levels with long short term memory station based approximated models and transfer learning techniques
topic long short‐term memory networks
transfer learning
extreme water level
cyclones
attention layer
url https://doi.org/10.1029/2024WR039054
work_keys_str_mv AT samueldaramola predictingtheevolutionofextremewaterlevelswithlongshorttermmemorystationbasedapproximatedmodelsandtransferlearningtechniques
AT davidfmunoz predictingtheevolutionofextremewaterlevelswithlongshorttermmemorystationbasedapproximatedmodelsandtransferlearningtechniques
AT paulmunoz predictingtheevolutionofextremewaterlevelswithlongshorttermmemorystationbasedapproximatedmodelsandtransferlearningtechniques
AT siddharthsaksena predictingtheevolutionofextremewaterlevelswithlongshorttermmemorystationbasedapproximatedmodelsandtransferlearningtechniques
AT jenniferirish predictingtheevolutionofextremewaterlevelswithlongshorttermmemorystationbasedapproximatedmodelsandtransferlearningtechniques