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 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 (R2) 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 (R2 = 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.
(Journal of Marine Science and Engineering. vol. 13, n° 2077-1312, pp. 1181, 08/04/2026)
EPOC, EPHE, PSL, UB, INSU - CNRS, CNRS, UR ETTIS, INRAE, UR EABX, INRAE, EPOC, SMGBL
New records of the jellyfish Rhizostoma luteum (Scyphozoa: Rhizostomeae) in the Bay of Biscay, and update of its distribution area
The authors report new observations of the giant jellyfish Rhizostoma luteum based on field observations and photographic databases from citizen sciences from 2017 to 2023. These observations indicate the presence of this species in the south of the Bay of Biscay, where it has been observed on several occasions and at different locations, suggesting a regular presence in the area. These observations represent the most northerly reports for the North-East Atlantic and the first on the French coast. An update of its distribution has highlighted the presence of the species as far south as South Africa in the South-East Atlantic.
(Cahiers de Biologie Marine. vol. 66, n° 0007-9723, pp. 5-9, 08/04/2026)
EPOC, EPHE, PSL, UB, INSU - CNRS, CNRS, LERAR, COAST, IFREMER, IRSTEA, LERPAC, COAST, IFREMER
Use of solute concentration gradients in the benthic boundary layer to highlight sediment source-sink dynamics: a non-invasive \textitin situ study
Oxygen, nutrients, and pollutants fluxes at the sediment-water interface are involved in the water quality and ecological status of shallow coastal environments. The short-term variabilities of these fluxes, in response to hydrodynamic and benthic biogeochemical processes in the field, make it difficult to assess the net balance of these fluxes. Here we evaluate the ability of using concentration gradients in the benthic boundary layer to better understand temporal variations in these fluxes. Three shallow Mediterranean coastal lagoons (Berre, Thau and Prévost lagoons), affected by deoxygenation events and depicting contrasting water quality status, were investigated. A Benthic Oxygen Gradient Observatory System (BOGOS) was set-up and deployed for two weeks in each lagoon to obtain continuous oxygen gradient time-series. In addition, concentration gradients of nutrients (Si, NH4+, PO43−) and trace elements (Fe, Mn, Co, As, Cu, Mo, MeHg) were obtained using a specifically dedicated benthic water sampler (SUSANE) deployed under contrasting oxygenation conditions (oxic, hypoxic, anoxic, euxinic) and diurnal cycles (day and night). The results enabled us firstly to better define the limits of applying the gradient method in shallow coastal areas, considering environmental conditions (water stratification, intense water mixing, low flux intensity) as well as technical limitations (concentration uncertainty). This approach then allowed to accurately capture contrasted benthic oxygen dynamics: diurnal cycles in sediments colonized by macrophytes in Prévost and Thau lagoons, and a dominant high oxygen demand in bare sediments in Berre lagoon. Benthic solute gradients in Berre lagoon indicated release of nutrients from the sediment under normoxic conditions after a long-term anoxic event, as well as release of dissolved Mn, Fe, As and Co under anoxic conditions. Under euxinic conditions, gradients reversed for most trace elements that were trapped in sediment due to (co)precipitation with sulfide minerals, while nutrient gradients indicated continuing sizeable releases to the water column. The benthic concentration gradient approach can thus be seen as a promising approach in assessing the dynamics of benthic fluxes at an appropriate time scale in highly dynamic shallow coastal lagoons. This effort should be completed by vertical turbulent diffusivity measurements, to obtain time series of turbulent fluxes of various solutes.
(Estuarine, Coastal and Shelf Science. vol. 323, n° 0272-7714, pp. 109432, 08/04/2026)
CHROME, UNIMES, EPOC, EPHE, PSL, UB, INSU - CNRS, CNRS, UAG, INSU - CNRS, UM, CNRS, CEREGE, IRD, AMU, CdF (institution), INSU - CNRS, CNRS, INRAE, UMR Marbec - Station Sète, UMR MARBEC, IRD, IFREMER, CNRS, UM, MIO, IRD, AMU, INSU - CNRS, UTLN, CNRS, LCE, AMU, INC-CNRS, CNRS, HSM, IRD, INSU - CNRS, CNRS, UM, CCEM, IFREMER
Characterization of barchanoid dune systems on the Cap Ferret spit (Aquitaine)
The Cap Ferret spit (Atlantic coast, France) is defined by barchanoid dune systems formed by a large input of sand remobilized by aeolian dynamics. GPR investigations have revealed distinct internal architectures within the barchanoid dunes, mainly characterized by eastward-dipping reflectors and complex structures illustrating sand remobilization. These structures highlight a progressive evolution in dune morphology, from west to east, i) low topographic and interconnected dunes without specific morphology (proto-barchans), ii) interconnected dunes with crescent-shaped morphology (barchanoid ridge) and iii) isolated dunes with a well-defined crescent-shaped morphology (isolated barchans). This study investigates these distinct stages of development, linking internal stratigraphy and geomorphological evolution, and provides insights on the dynamics of coastal barchanoid dune formation and migration.
(. vol. 84, pp. 1-4, 08/04/2026)
BRGM, EPOC, EPHE, PSL, UB, INSU - CNRS, CNRS
History of the Sedimentary Regimes of the Aquitaine Margin (Bay of Biscay, France) at the Outlet of its Main Tributaries During the Last Millennium: A Mirror of the North Atlantic and European Climates
(08/04/2026)
EPOC, EPHE, PSL, UB, INSU - CNRS, CNRS, GEO-OCEAN, UBS, IFREMER, INSU - CNRS, UBO EPE, CNRS
Main conclusions and perspectives from the collective scientific assessment of the effects of plant protection products on biodiversity and ecosystem services along the land–sea continuum in France and French overseas territories
Preservation of biodiversity and ecosystem services is critical for sustainable development and human well-being. However, an unprecedented erosion of biodiversity is observed and the use of plant protection products (PPP) has been identified as one of its main causes. In this context, at the request of the French Ministries responsible for the Environment, for Agriculture and for Research, a panel of 46 scientific experts ran a nearly 2-year-long (2020-2022) collective scientific assessment (CSA) of international scientific knowledge relating to the impacts of PPP on biodiversity and ecosystem services. The scope of this CSA covered the terrestrial, atmospheric, freshwater, and marine environments (with the exception of groundwater) in their continuity from the site of PPP application to the ocean, in France and French overseas territories, based on international knowledge produced on or transposable to this type of context (climate, PPP used, biodiversity present, etc.). Here, we provide a brief summary of the CSA's main conclusions, which were drawn from about 4500 international publications. Our analysis finds that PPP contaminate all environmental matrices, including biota, and cause direct and indirect ecotoxicological effects that unequivocally contribute to the decline of certain biological groups and alter certain ecosystem functions and services. Levers for action to limit PPP-driven pollution and effects on environmental compartments include local measures from plot to landscape scales and regulatory improvements. However, there are still significant gaps in knowledge regarding environmental contamination by PPPs and its effect on biodiversity and ecosystem functions and services. Perspectives and research needs are proposed to address these gaps.
(Environmental Science and Pollution Research. vol. 32, n° 0944-1344, pp. 2757–2772, 08/04/2026)
RiverLy, INRAE, ECOSYS, INRAE, IFREMER, ISA, UNS, CNRS, INRAE, UniCA, LMGE, CNRS, UCA, UMR BAGAP, ESA, INRAE, Institut Agro, LPED, IRD, AMU, INERIS, EMMAH, AU, INRAE, VAS, ICE, VAS, CRIOBE, UPVD, EPHE, PSL, CNRS, SEBIO, INERIS, URCA, ULH, NU, URCA, CNRS, CNELIAS, AU, AMU, MMSH, AMU, CNRS, CNRS, LBBE, UCBL, VAS, CNRS, LBBE, UCBL, VAS, CNRS, INRAE, Institut Agro, UBE, LCE, CNRS, UFC, UBFC, UMR SAVE, UB, Bordeaux Sciences Agro, INRAE, DECOD, IFREMER, INRAE, Institut Agro, Institut Agro, OFB Service Santé Agri, OFB - DRAS, OFB, GREDEG, UNS, CNRS, UniCA, ENSFEA, LEREPS, UT Capitole, Comue de Toulouse, UT2J, Comue de Toulouse, ENSFEA, EPOC, EPHE, PSL, UB, INSU - CNRS, CNRS, UMR Eco&Sols, Cirad, IRD, INRAE, Institut Agro, IODE, UR, CNRS, UPR HORTSYS, Cirad, Cirad-PERSYST, Cirad, UMR MARBEC, IRD, IFREMER, CNRS, UM, AMURE, IRD, IFREMER, UBO EPE, CNRS, UR EABX, INRAE, IMBE, AU, AMU, CNRS, UdG, PHYTOX, IFREMER, CUFR, URAFPA, UL, INRAE, UR HYCAR, INRAE, DEPE, INRAE
Manila clam (Ruditapes philippinarum) in France: Fishing activity, governance and present knowledge challenges regarding its biology and ecology
Originally introduced to France in the 1970s for aquaculture purposes, the clam Ruditapes philippinarum (Adam and Reeve, 1850) has thrived in favourable conditions across numerous sites along the Bay of Biscay, English Channel and Mediterranean coasts forming neo-naturalized populations. It is harvested by both recreational and professional fishers, with an estimated production ratio of 2.4 for both activities combined. Total French commercial fishing production is roughly estimated at around 2000 to 3000 tons per year. This activity is managed by three types of regulation at different scales: European (Minimum Conservation Reference Size - MCRS), national (licenses), and regional. Regional instruments govern fishing practices by setting spatial and temporal access rules to fishing grounds (also referred to as deposits), prohibiting certain gear types at the local scale, determining the minimum size of clam fishing (above MCRS) and setting fishing quotas. Not all of them are implemented everywhere; most often, they are based on stock assessment results and specific research programs, which are not available in every location. This article first provides a review of available information on current Manila clam production in France, and its regulation. Second, it offers an overview of recent knowledge mobilized for management purposes. This overview covers biological and ecological processes (i.e. population dynamics, reproduction and spawning, habitats considerations, biotic interactions and infectious diseases), and enables us to identify future research prospects of interest.
(Estuarine, Coastal and Shelf Science. vol. 317, n° 0272-7714, pp. 109206, 08/04/2026)
LERAR, COAST, IFREMER, LMAP, UPPA, CNRS, EPOC, EPHE, PSL, UB, INSU - CNRS, CNRS, UMR MARBEC, IRD, IFREMER, CNRS, UM, ASIM, IFREMER, DECOD, IFREMER, INRAE, Institut Agro, Institut Agro, SBR, SU, CNRS, AD2M, SU, CNRS, SBR, SU, CNRS, LOV, INSU - CNRS, SU, CNRS, IMEV, INSU - CNRS, SU, CNRS, M2C, UNICAEN, NU, INSU - CNRS, UNIROUEN, NU, CNRS, SMEL, LEMAR, IRD, IFREMER, UBO EPE, CNRS, UR ETTIS, INRAE
Tidal Pumping, Alkalinity Production and Export: An Overlooked Carbon Sequestration Process in Salt Marshes
(08/04/2026)
EPOC, EPHE, PSL, UB, INSU - CNRS, CNRS
Differentiating estuarine dissolved organic matter composition by unsupervised and supervised machine learning
Differentiating the composition of Dissolved Organic Matter (DOM) in estuaries is a major environmental concern, as the DOM characteristics are closely linked to biogeochemical and ecological considerations (e.g. water properties and trophic cycling). However, tracing the spatiotemporal variations of estuarine DOM is challenging due to multiple sources and complex transformation processes. Here, we investigate the dynamics of estuarine DOM by analyzing the optical properties of DOM through UV-Visible absorbance and fluorescence spectroscopy, while also capturing the variability of DOM using machine learning algorithms and explainable artificial intelligence. To this aim, we collected sub-surface water samples (n = 249) from a human-impacted estuary with intense industrialization and urbanization in France (Seine Estuary) across distinct land use characteristics in contrasting hydrological conditions. We then applied unsupervised and supervised machine learning techniques to analyze the optical properties of DOM, which were determined by UV-Visible absorbance and Excitation-Emission Matrix (EEM) fluorescence spectroscopy combined with parallel factor analysis (PAR-AFAC). Our results show that unsupervised machine learning (K-means clustering) captures the spatial variabilities of DOM, identifying three distinct estuarine zones based on pronounced spatial variations of several DOM optical parameters. Supervised machine learning (Light Gradient Boosted Machine, LightGBM) further validates the rationality of the defined zonation. Subsequently, explainable artificial intelligence based on SHapley Additive exPlanations (SHAP) analysis shows that DOM in each zone has specific characteristics. Our model indicates that DOM in the Seine Estuary is primarily influenced by high molecular weight materials and autochthonous contributions in the upper estuary (Zone I). The dominant contribution to DOM in the mid-estuary (Zone II) comes from autochthonous and aromatic material as well as transformation and (photo)degradation products. Lower estuary (Zone III) is mainly characterized by aromatic DOM (subject to photodegradation), low molecular weight compounds, autochthonous DOM, as well as transformation and (photo)degradation products. Overall, this study presents a workflow for differentiating the composition of DOM, tracing the variability and dynamics of DOM along the land-to-sea continuum, and elucidating the involved processes. The approach developed in the Seine Estuary has significant implications for environmental management and can be adapted to other land-sea continuums.
(Water Research. vol. 284, n° 0043-1354, pp. 123900, 08/04/2026)
METIS, EPHE, PSL, INSU - CNRS, SU, CNRS, EPOC, EPHE, PSL, UB, INSU - CNRS, CNRS
Semi-empirical forecast modelling of rip-current and shore-break wave hazards
Sandy beaches are highly attractive but also potentially dangerous environments for those entering the water as they can be exposed to physical hazards in the surf zone. The most severe and widespread natural bathing hazards on beaches are rip currents and shore-break waves, which form under different wave, tide, and morphological conditions. This paper introduces two new, simple semiempirical rip-current and shore-break wave hazard forecast models. These physics-informed models, which depend on a limited number of free parameters, can be used to compute the time evolution of the rip-current flow speed V and shore-break wave energy E sb . These models are applied to a high-energy mesotidal-macrotidal beach, La Lette Blanche, in southwest France, where intense rip-currents and shore-break wave hazards co-exist. Hourly lifeguardperceived hazards collected during patrolling hours (from 11:00 a.m. to 07:00 p.m. LT (UTC+2)) during July and August of 2022 are used to calibrate the two models. These data are also used to transform V and E sb into a five-level scale from 0 (no hazard) to 4 (hazard maximised). The model accurately predicts rip-current and shore-break wave hazard levels, including their modulation by tide elevation and incident wave conditions, opening new perspectives for forecasting multiple surf-zone hazards on sandy beaches. In addition, daily-mean hazard forecasts demonstrate even greater predictive skill, which is important for conveying straightforward messages to the general public and lifeguard managers. The approach presented here only requires a limited number of beach morphology metrics and allows for the prediction of surf-zone hazards on beaches where wave and tide forecasts are available.
(Natural Hazards and Earth System Sciences. vol. 25, n° 1561-8633, pp. 2379–2397, 08/04/2026)
EPOC, EPHE, PSL, UB, INSU - CNRS, CNRS, UR ETTIS, INRAE, SMGBL, UR EABX, INRAE