Morphodynamic predictions based on Machine Learning. Performance and limits for pocket beaches near the Bilbao port
Predicting the morphodynamic behaviour of pocket beaches exposed to energetic waves and meso-tidal ranges—particularly under strong seasonal variability and the influence of climate change—requires a robust characterization of coastal morphodynamics across a wide range of temporal and spatial scales...
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-07-01
|
| Series: | Frontiers in Environmental Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fenvs.2025.1600473/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849715454530027520 |
|---|---|
| author | Manuel Viñes Agustín Sánchez-Arcilla Irati Epelde César Mösso Javier Franco Joaquim Sospedra Aritz Abalia Pedro Líria Manel Grifoll Alberto Ojanguren Mario Hernáez Manuel González Agustín Sánchez-Arcilla |
| author_facet | Manuel Viñes Agustín Sánchez-Arcilla Irati Epelde César Mösso Javier Franco Joaquim Sospedra Aritz Abalia Pedro Líria Manel Grifoll Alberto Ojanguren Mario Hernáez Manuel González Agustín Sánchez-Arcilla |
| author_sort | Manuel Viñes |
| collection | DOAJ |
| description | Predicting the morphodynamic behaviour of pocket beaches exposed to energetic waves and meso-tidal ranges—particularly under strong seasonal variability and the influence of climate change—requires a robust characterization of coastal morphodynamics across a wide range of temporal and spatial scales. This study introduces a data-driven modelling approach using Machine Learning (ML), specifically the Gradient Boosting Regressor (GBR), a powerful ensemble technique capable of iteratively improving predictions from limited datasets. The GBR model is applied to forecast beach evolution in complex coastal settings, where physical understanding is limited, specifically targeting a set of pocket beaches in the Bay of Biscay (North Atlantic). The methodology combines wave time series and morphodynamic variables obtained through videometry stations (KOSTASystem technology). This ML framework is then implemented to improve the current understanding of hydro-morphological interactions and establish criteria to enhance the reliability of erosion and flood predictions. The obtained predictions can steer the design and implementation of protection measures to increase beach resilience under climate change drivers, such as sea-level rise and wave storminess, leading to improved adaptation strategies. This approach, which also demonstrates the advantages of ML over conventional statistics, is developed from a set of extreme meteo-oceanographic events acting on pocket beaches adjacent to and within the Nervión estuary and Bilbao port. The application of conventional statistics and ML techniques to this dataset begins with an extreme analysis of offshore wave data, from which a set of 32 wave storms has been propagated towards the coast using the Simulated WAves Nearshore (SWAN) model. This dataset serves to evaluate predictive formulations derived from statistical and ML tools, based on monthly values, which filter out short-term variability and focus on medium- to long-term (annual to decadal) beach behaviour—scales that are critical for sustainable coastal management. Results demonstrate that ML-based predictions using GBR outperform traditional statistical methods, where validation metrics confirm the improved predictive accuracy, with R2 values exceeding 0.7 in several cases, without any evidence of overfitting. These predictions contribute to understanding hydro-morphological interactions and support the design of adaptive beach protection strategies. |
| format | Article |
| id | doaj-art-c85a51bdd828491889d23c29ff8339ea |
| institution | DOAJ |
| issn | 2296-665X |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Environmental Science |
| spelling | doaj-art-c85a51bdd828491889d23c29ff8339ea2025-08-20T03:13:22ZengFrontiers Media S.A.Frontiers in Environmental Science2296-665X2025-07-011310.3389/fenvs.2025.16004731600473Morphodynamic predictions based on Machine Learning. Performance and limits for pocket beaches near the Bilbao portManuel Viñes0Agustín Sánchez-Arcilla1Irati Epelde2César Mösso3Javier Franco4Joaquim Sospedra5Aritz Abalia6Pedro Líria7Manel Grifoll8Alberto Ojanguren9Mario Hernáez10Manuel González11Agustín Sánchez-Arcilla12Universitat Politècnica de Catalunya – BarcelonaTech (UPC), Laboratori d’Enginyeria Marítima (LIM), Barcelona, SpainUniversitat Politècnica de Catalunya – BarcelonaTech (UPC), Laboratori d’Enginyeria Marítima (LIM), Barcelona, SpainAZTI Marine Research, Basque Research and Technology Alliance (BRTA), Gipuzkoa, SpainUniversitat Politècnica de Catalunya – BarcelonaTech (UPC), Laboratori d’Enginyeria Marítima (LIM), Barcelona, SpainAZTI Marine Research, Basque Research and Technology Alliance (BRTA), Gipuzkoa, SpainUniversitat Politècnica de Catalunya – BarcelonaTech (UPC), Laboratori d’Enginyeria Marítima (LIM), Barcelona, SpainAZTI Marine Research, Basque Research and Technology Alliance (BRTA), Gipuzkoa, SpainAZTI Marine Research, Basque Research and Technology Alliance (BRTA), Gipuzkoa, SpainUniversitat Politècnica de Catalunya – BarcelonaTech (UPC), Laboratori d’Enginyeria Marítima (LIM), Barcelona, SpainDepartamento de Salud, Seguridad y Medio Ambiente de la Autoridad, Autoridad Portuaria de Bilbao, APB, Santurtzi, SpainDepartamento de Planificación, Proyectos y Construccíón, Autoridad Portuaria de Bilbao, APB, Santurtzi, SpainAZTI Marine Research, Basque Research and Technology Alliance (BRTA), Gipuzkoa, SpainUniversitat Politècnica de Catalunya – BarcelonaTech (UPC), Laboratori d’Enginyeria Marítima (LIM), Barcelona, SpainPredicting the morphodynamic behaviour of pocket beaches exposed to energetic waves and meso-tidal ranges—particularly under strong seasonal variability and the influence of climate change—requires a robust characterization of coastal morphodynamics across a wide range of temporal and spatial scales. This study introduces a data-driven modelling approach using Machine Learning (ML), specifically the Gradient Boosting Regressor (GBR), a powerful ensemble technique capable of iteratively improving predictions from limited datasets. The GBR model is applied to forecast beach evolution in complex coastal settings, where physical understanding is limited, specifically targeting a set of pocket beaches in the Bay of Biscay (North Atlantic). The methodology combines wave time series and morphodynamic variables obtained through videometry stations (KOSTASystem technology). This ML framework is then implemented to improve the current understanding of hydro-morphological interactions and establish criteria to enhance the reliability of erosion and flood predictions. The obtained predictions can steer the design and implementation of protection measures to increase beach resilience under climate change drivers, such as sea-level rise and wave storminess, leading to improved adaptation strategies. This approach, which also demonstrates the advantages of ML over conventional statistics, is developed from a set of extreme meteo-oceanographic events acting on pocket beaches adjacent to and within the Nervión estuary and Bilbao port. The application of conventional statistics and ML techniques to this dataset begins with an extreme analysis of offshore wave data, from which a set of 32 wave storms has been propagated towards the coast using the Simulated WAves Nearshore (SWAN) model. This dataset serves to evaluate predictive formulations derived from statistical and ML tools, based on monthly values, which filter out short-term variability and focus on medium- to long-term (annual to decadal) beach behaviour—scales that are critical for sustainable coastal management. Results demonstrate that ML-based predictions using GBR outperform traditional statistical methods, where validation metrics confirm the improved predictive accuracy, with R2 values exceeding 0.7 in several cases, without any evidence of overfitting. These predictions contribute to understanding hydro-morphological interactions and support the design of adaptive beach protection strategies.https://www.frontiersin.org/articles/10.3389/fenvs.2025.1600473/fullMachine LearningGradient Boosting Regressorkey hydro- and morphodynamic variablescross-correlationspredictive formulations |
| spellingShingle | Manuel Viñes Agustín Sánchez-Arcilla Irati Epelde César Mösso Javier Franco Joaquim Sospedra Aritz Abalia Pedro Líria Manel Grifoll Alberto Ojanguren Mario Hernáez Manuel González Agustín Sánchez-Arcilla Morphodynamic predictions based on Machine Learning. Performance and limits for pocket beaches near the Bilbao port Frontiers in Environmental Science Machine Learning Gradient Boosting Regressor key hydro- and morphodynamic variables cross-correlations predictive formulations |
| title | Morphodynamic predictions based on Machine Learning. Performance and limits for pocket beaches near the Bilbao port |
| title_full | Morphodynamic predictions based on Machine Learning. Performance and limits for pocket beaches near the Bilbao port |
| title_fullStr | Morphodynamic predictions based on Machine Learning. Performance and limits for pocket beaches near the Bilbao port |
| title_full_unstemmed | Morphodynamic predictions based on Machine Learning. Performance and limits for pocket beaches near the Bilbao port |
| title_short | Morphodynamic predictions based on Machine Learning. Performance and limits for pocket beaches near the Bilbao port |
| title_sort | morphodynamic predictions based on machine learning performance and limits for pocket beaches near the bilbao port |
| topic | Machine Learning Gradient Boosting Regressor key hydro- and morphodynamic variables cross-correlations predictive formulations |
| url | https://www.frontiersin.org/articles/10.3389/fenvs.2025.1600473/full |
| work_keys_str_mv | AT manuelvines morphodynamicpredictionsbasedonmachinelearningperformanceandlimitsforpocketbeachesnearthebilbaoport AT agustinsanchezarcilla morphodynamicpredictionsbasedonmachinelearningperformanceandlimitsforpocketbeachesnearthebilbaoport AT iratiepelde morphodynamicpredictionsbasedonmachinelearningperformanceandlimitsforpocketbeachesnearthebilbaoport AT cesarmosso morphodynamicpredictionsbasedonmachinelearningperformanceandlimitsforpocketbeachesnearthebilbaoport AT javierfranco morphodynamicpredictionsbasedonmachinelearningperformanceandlimitsforpocketbeachesnearthebilbaoport AT joaquimsospedra morphodynamicpredictionsbasedonmachinelearningperformanceandlimitsforpocketbeachesnearthebilbaoport AT aritzabalia morphodynamicpredictionsbasedonmachinelearningperformanceandlimitsforpocketbeachesnearthebilbaoport AT pedroliria morphodynamicpredictionsbasedonmachinelearningperformanceandlimitsforpocketbeachesnearthebilbaoport AT manelgrifoll morphodynamicpredictionsbasedonmachinelearningperformanceandlimitsforpocketbeachesnearthebilbaoport AT albertoojanguren morphodynamicpredictionsbasedonmachinelearningperformanceandlimitsforpocketbeachesnearthebilbaoport AT mariohernaez morphodynamicpredictionsbasedonmachinelearningperformanceandlimitsforpocketbeachesnearthebilbaoport AT manuelgonzalez morphodynamicpredictionsbasedonmachinelearningperformanceandlimitsforpocketbeachesnearthebilbaoport AT agustinsanchezarcilla morphodynamicpredictionsbasedonmachinelearningperformanceandlimitsforpocketbeachesnearthebilbaoport |