Predicting Morphological Changes Along a Macrotidal Coastline Using a Two‐Stage Machine Learning Model

Abstract Understanding and predicting coastal change is of the foremost importance to protect coastal communities and coastal assets. This study analyzes field data from 125 locations along the Morecambe coastline, consisting of beach transects collected twice a year for more than a decade (2007–202...

Full description

Saved in:
Bibliographic Details
Main Authors: Pavitra Kumar, Nicoletta Leonardi
Format: Article
Language:English
Published: Wiley 2025-04-01
Series:Water Resources Research
Subjects:
Online Access:https://doi.org/10.1029/2024WR037523
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849687674917486592
author Pavitra Kumar
Nicoletta Leonardi
author_facet Pavitra Kumar
Nicoletta Leonardi
author_sort Pavitra Kumar
collection DOAJ
description Abstract Understanding and predicting coastal change is of the foremost importance to protect coastal communities and coastal assets. This study analyzes field data from 125 locations along the Morecambe coastline, consisting of beach transects collected twice a year for more than a decade (2007–2022). Wave data at these 125 locations were simulated using the hydrodynamic Delft3D model, with full coupling of the Delft3D FLOW and WAVE modules. To model the sediment volume changes observed along the Morecambe coastline, this study proposes a two‐stage machine learning model that incorporates beach behavior classification and deep learning techniques to predict changes in sediment volumes along coastal environments. The first stage of the model, developed using a random forest classifier, classifies beach behavior into four categories: eroding, accreting, stable, or undergoing short‐term fluctuations. The second stage of the model developed using LSTM and sequence‐to‐sequence models, uses the output of the first stage to predict the change in sediment volume after erosion/accretion. The random forest classifier achieves testing accuracy of 0.74. LSTM model achieved a testing regression of 0.92 for one‐step‐ahead (6 months) predictions of change in sediment volume time series, while sequence‐to‐sequence model achieved the testing regression of 0.96 for three‐time‐ahead (1.5 years) predictions and 0.88 for ten‐time‐step‐ahead (5 years) prediction.
format Article
id doaj-art-8dee63598e59480ebb7cdcead3e7bc79
institution DOAJ
issn 0043-1397
1944-7973
language English
publishDate 2025-04-01
publisher Wiley
record_format Article
series Water Resources Research
spelling doaj-art-8dee63598e59480ebb7cdcead3e7bc792025-08-20T03:22:16ZengWileyWater Resources Research0043-13971944-79732025-04-01614n/an/a10.1029/2024WR037523Predicting Morphological Changes Along a Macrotidal Coastline Using a Two‐Stage Machine Learning ModelPavitra Kumar0Nicoletta Leonardi1Department of Geography and Planning School of Environmental Sciences University of Liverpool Liverpool UKDepartment of Geography and Planning School of Environmental Sciences University of Liverpool Liverpool UKAbstract Understanding and predicting coastal change is of the foremost importance to protect coastal communities and coastal assets. This study analyzes field data from 125 locations along the Morecambe coastline, consisting of beach transects collected twice a year for more than a decade (2007–2022). Wave data at these 125 locations were simulated using the hydrodynamic Delft3D model, with full coupling of the Delft3D FLOW and WAVE modules. To model the sediment volume changes observed along the Morecambe coastline, this study proposes a two‐stage machine learning model that incorporates beach behavior classification and deep learning techniques to predict changes in sediment volumes along coastal environments. The first stage of the model, developed using a random forest classifier, classifies beach behavior into four categories: eroding, accreting, stable, or undergoing short‐term fluctuations. The second stage of the model developed using LSTM and sequence‐to‐sequence models, uses the output of the first stage to predict the change in sediment volume after erosion/accretion. The random forest classifier achieves testing accuracy of 0.74. LSTM model achieved a testing regression of 0.92 for one‐step‐ahead (6 months) predictions of change in sediment volume time series, while sequence‐to‐sequence model achieved the testing regression of 0.96 for three‐time‐ahead (1.5 years) predictions and 0.88 for ten‐time‐step‐ahead (5 years) prediction.https://doi.org/10.1029/2024WR037523sediment volumemorecambe baytwo‐stage modelingrandom forestLSTMsequence‐to‐sequence
spellingShingle Pavitra Kumar
Nicoletta Leonardi
Predicting Morphological Changes Along a Macrotidal Coastline Using a Two‐Stage Machine Learning Model
Water Resources Research
sediment volume
morecambe bay
two‐stage modeling
random forest
LSTM
sequence‐to‐sequence
title Predicting Morphological Changes Along a Macrotidal Coastline Using a Two‐Stage Machine Learning Model
title_full Predicting Morphological Changes Along a Macrotidal Coastline Using a Two‐Stage Machine Learning Model
title_fullStr Predicting Morphological Changes Along a Macrotidal Coastline Using a Two‐Stage Machine Learning Model
title_full_unstemmed Predicting Morphological Changes Along a Macrotidal Coastline Using a Two‐Stage Machine Learning Model
title_short Predicting Morphological Changes Along a Macrotidal Coastline Using a Two‐Stage Machine Learning Model
title_sort predicting morphological changes along a macrotidal coastline using a two stage machine learning model
topic sediment volume
morecambe bay
two‐stage modeling
random forest
LSTM
sequence‐to‐sequence
url https://doi.org/10.1029/2024WR037523
work_keys_str_mv AT pavitrakumar predictingmorphologicalchangesalongamacrotidalcoastlineusingatwostagemachinelearningmodel
AT nicolettaleonardi predictingmorphologicalchangesalongamacrotidalcoastlineusingatwostagemachinelearningmodel