Predicting coastal wave conditions: A simple machine learning approach
Allbwn ymchwil: Cyfraniad at gyfnodolyn › Erthygl › adolygiad gan gymheiriaid
StandardStandard
Yn: Applied Ocean Research, Cyfrol 153, 104282, 01.12.2024.
Allbwn ymchwil: Cyfraniad at gyfnodolyn › Erthygl › adolygiad gan gymheiriaid
HarvardHarvard
APA
CBE
MLA
VancouverVancouver
Author
RIS
TY - JOUR
T1 - Predicting coastal wave conditions: A simple machine learning approach
AU - Roome, Edward
AU - Christie, David
AU - Neill, Simon
PY - 2024/12/1
Y1 - 2024/12/1
N2 - Accurate and reliable nearshore wave predictions are highly valuable for a range of marine activities, including coastal engineering and maritime transport. However, in nearshore locations, predicting wave properties is challenging due to complex shallow water processes, requiring local wave models. This article develops an alternative data-driven framework to predict wave parameters (e.g. significant wave height) through the extension of wave buoy datasets using a trained Gaussian process regression (GPR — a supervised machine learning method). We present an easy-to-implement workflow, where the extensive range of input parameters (from ECMWF’s (1) ERA5 reanalysis and (2) IFS forecast global wave model, resolution) drives the development of GPR models. At five contrasting locations around the United Kingdom’s coastline, the GPR models produce wave predictions (forecast and hindcast) with low bias scores and strong correlations with observations. When compared to the global (ERA5 reanalysis) and a benchmark shelf-scale (Atlantic-European North West Shelf reanalysis; AENWS, resolution) model, the GPR hindcasts reduced significant wave height () root-mean-squared error (RMSE) from 0.46 m (ERA5) and 0.21 m (AENWS) to 0.16 m (GPR). For the average zero-crossing wave period () RMSE reduced from 1.46 s (ERA5) and 1.15 s (AENWS) to 0.58 s (GPR). Because our approach uses publicly available global data, it can be implemented at any historic or active buoy location. We provide proof of concept for an online forecast and hindcast tool which has the potential to improve accessibility to coastal wave predictions for many marine stakeholders.
AB - Accurate and reliable nearshore wave predictions are highly valuable for a range of marine activities, including coastal engineering and maritime transport. However, in nearshore locations, predicting wave properties is challenging due to complex shallow water processes, requiring local wave models. This article develops an alternative data-driven framework to predict wave parameters (e.g. significant wave height) through the extension of wave buoy datasets using a trained Gaussian process regression (GPR — a supervised machine learning method). We present an easy-to-implement workflow, where the extensive range of input parameters (from ECMWF’s (1) ERA5 reanalysis and (2) IFS forecast global wave model, resolution) drives the development of GPR models. At five contrasting locations around the United Kingdom’s coastline, the GPR models produce wave predictions (forecast and hindcast) with low bias scores and strong correlations with observations. When compared to the global (ERA5 reanalysis) and a benchmark shelf-scale (Atlantic-European North West Shelf reanalysis; AENWS, resolution) model, the GPR hindcasts reduced significant wave height () root-mean-squared error (RMSE) from 0.46 m (ERA5) and 0.21 m (AENWS) to 0.16 m (GPR). For the average zero-crossing wave period () RMSE reduced from 1.46 s (ERA5) and 1.15 s (AENWS) to 0.58 s (GPR). Because our approach uses publicly available global data, it can be implemented at any historic or active buoy location. We provide proof of concept for an online forecast and hindcast tool which has the potential to improve accessibility to coastal wave predictions for many marine stakeholders.
KW - Artificial intelligence
KW - Machine learning
KW - Coastal wave prediction
KW - Wave buoy
U2 - 10.1016/j.apor.2024.104282
DO - 10.1016/j.apor.2024.104282
M3 - Article
VL - 153
JO - Applied Ocean Research
JF - Applied Ocean Research
SN - 0141-1187
M1 - 104282
ER -