Machine Learning Beach Attendance Forecast Modelling from Automatic Video-Derived Counting

Accurate predictions of beach user numbers are important for coastal management, resource allocation, and minimising safety risks, especially when considering surf-zone hazards. The present work applies an XGBoost model to predict beach attendance from automatically video-derived data, incorporating...

Full description

Saved in:
Bibliographic Details
Main Authors: Bruno Castelle, David Carayon, Jeoffrey Dehez, Sylvain Liquet, Vincent Marieu, Nadia Sénéchal, Sandrine Lyser, Jean-Philippe Savy, Stéphanie Barneix
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Journal of Marine Science and Engineering
Subjects:
Online Access:https://www.mdpi.com/2077-1312/13/6/1181
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850167360389906432
author Bruno Castelle
David Carayon
Jeoffrey Dehez
Sylvain Liquet
Vincent Marieu
Nadia Sénéchal
Sandrine Lyser
Jean-Philippe Savy
Stéphanie Barneix
author_facet Bruno Castelle
David Carayon
Jeoffrey Dehez
Sylvain Liquet
Vincent Marieu
Nadia Sénéchal
Sandrine Lyser
Jean-Philippe Savy
Stéphanie Barneix
author_sort Bruno Castelle
collection DOAJ
description Accurate predictions of beach user numbers are important for coastal management, resource allocation, and minimising safety risks, especially when considering surf-zone hazards. The present work applies an XGBoost model to predict beach attendance from automatically video-derived data, incorporating input variables such as weather, waves, tide, and time (e.g., day hour, weekday). This approach is applied to data collected from Biscarrosse Beach during the summer of 2023, where beach attendance varied significantly (from 0 to 2031 individuals). Results indicate that the optimal XGBoost model achieved high predictive accuracy, with a coefficient of determination (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula>) of 0.97 and an RMSE of 70.4 users, using daily mean weather data, tide and time as input variables, i.e., disregarding wave data. The model skilfully captures both day-to-day and hourly variability in attendance, with time of day (hour) and daily mean air temperature being the most influential variables. An XGBoost model using only daily mean temperature and hour of the day even shows good predictive accuracy (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula> = 0.90). The study emphasises the importance of daily mean weather data over instantaneous measurements, as beach users tend to plan visits based on forecasts. This model offers reliable, computationally inexpensive, and high-frequency (e.g., every 10 min) beach user predictions which, combined with existing surf-zone hazard forecast models, can be used to anticipate life risk at the beach.
format Article
id doaj-art-1feb1856730e496dab68ea500854db2e
institution OA Journals
issn 2077-1312
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Journal of Marine Science and Engineering
spelling doaj-art-1feb1856730e496dab68ea500854db2e2025-08-20T02:21:13ZengMDPI AGJournal of Marine Science and Engineering2077-13122025-06-01136118110.3390/jmse13061181Machine Learning Beach Attendance Forecast Modelling from Automatic Video-Derived CountingBruno Castelle0David Carayon1Jeoffrey Dehez2Sylvain Liquet3Vincent Marieu4Nadia Sénéchal5Sandrine Lyser6Jean-Philippe Savy7Stéphanie Barneix8Univ. Bordeaux, CNRS, Bordeaux INP, EPOC, UMR 5805, 33615 Pessac, FranceINRAE Nouvelle Aquitaine, Cestas-Gazinet, 33140 Villenave-d’Ornon, FranceINRAE Nouvelle Aquitaine, Cestas-Gazinet, 33140 Villenave-d’Ornon, FranceMétéo-France, 31055 Toulouse, FranceUniv. Bordeaux, CNRS, Bordeaux INP, EPOC, UMR 5805, 33615 Pessac, FranceUniv. Bordeaux, CNRS, Bordeaux INP, EPOC, UMR 5805, 33615 Pessac, FranceINRAE Nouvelle Aquitaine, Cestas-Gazinet, 33140 Villenave-d’Ornon, FranceSMGBL, 40660 Messanges, FranceSMGBL, 40660 Messanges, FranceAccurate predictions of beach user numbers are important for coastal management, resource allocation, and minimising safety risks, especially when considering surf-zone hazards. The present work applies an XGBoost model to predict beach attendance from automatically video-derived data, incorporating input variables such as weather, waves, tide, and time (e.g., day hour, weekday). This approach is applied to data collected from Biscarrosse Beach during the summer of 2023, where beach attendance varied significantly (from 0 to 2031 individuals). Results indicate that the optimal XGBoost model achieved high predictive accuracy, with a coefficient of determination (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula>) of 0.97 and an RMSE of 70.4 users, using daily mean weather data, tide and time as input variables, i.e., disregarding wave data. The model skilfully captures both day-to-day and hourly variability in attendance, with time of day (hour) and daily mean air temperature being the most influential variables. An XGBoost model using only daily mean temperature and hour of the day even shows good predictive accuracy (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula> = 0.90). The study emphasises the importance of daily mean weather data over instantaneous measurements, as beach users tend to plan visits based on forecasts. This model offers reliable, computationally inexpensive, and high-frequency (e.g., every 10 min) beach user predictions which, combined with existing surf-zone hazard forecast models, can be used to anticipate life risk at the beach.https://www.mdpi.com/2077-1312/13/6/1181beach attendance forecastingXGBoost modellingvideo-derived beach user dataweather and tidal influencescoastal safety management
spellingShingle Bruno Castelle
David Carayon
Jeoffrey Dehez
Sylvain Liquet
Vincent Marieu
Nadia Sénéchal
Sandrine Lyser
Jean-Philippe Savy
Stéphanie Barneix
Machine Learning Beach Attendance Forecast Modelling from Automatic Video-Derived Counting
Journal of Marine Science and Engineering
beach attendance forecasting
XGBoost modelling
video-derived beach user data
weather and tidal influences
coastal safety management
title Machine Learning Beach Attendance Forecast Modelling from Automatic Video-Derived Counting
title_full Machine Learning Beach Attendance Forecast Modelling from Automatic Video-Derived Counting
title_fullStr Machine Learning Beach Attendance Forecast Modelling from Automatic Video-Derived Counting
title_full_unstemmed Machine Learning Beach Attendance Forecast Modelling from Automatic Video-Derived Counting
title_short Machine Learning Beach Attendance Forecast Modelling from Automatic Video-Derived Counting
title_sort machine learning beach attendance forecast modelling from automatic video derived counting
topic beach attendance forecasting
XGBoost modelling
video-derived beach user data
weather and tidal influences
coastal safety management
url https://www.mdpi.com/2077-1312/13/6/1181
work_keys_str_mv AT brunocastelle machinelearningbeachattendanceforecastmodellingfromautomaticvideoderivedcounting
AT davidcarayon machinelearningbeachattendanceforecastmodellingfromautomaticvideoderivedcounting
AT jeoffreydehez machinelearningbeachattendanceforecastmodellingfromautomaticvideoderivedcounting
AT sylvainliquet machinelearningbeachattendanceforecastmodellingfromautomaticvideoderivedcounting
AT vincentmarieu machinelearningbeachattendanceforecastmodellingfromautomaticvideoderivedcounting
AT nadiasenechal machinelearningbeachattendanceforecastmodellingfromautomaticvideoderivedcounting
AT sandrinelyser machinelearningbeachattendanceforecastmodellingfromautomaticvideoderivedcounting
AT jeanphilippesavy machinelearningbeachattendanceforecastmodellingfromautomaticvideoderivedcounting
AT stephaniebarneix machinelearningbeachattendanceforecastmodellingfromautomaticvideoderivedcounting