Using machine learning to predict drownings in surf beaches of southwest France
Background: Southwest France golden-sand beaches are very popular destination for bathing and other sea activities in summer. However, they are also potentially dangerous environments with increased risk of accidents in unsupervised areas, especially during the off-peak season, due to strong rip-current and shorebreak waves. Predicting and quantifying these accidents is of major importance for public communication and emergency services management. Previous work on beach risk prediction was conducted along a specific section of the coast (Gironde), using data from 2011-2017 to train a model and further predict drowning incidents based on sea and weather forecasts, which has led to the development of an alert system based on a logistic regression model used by local decision makers [1]. Methods: In this study, we further improve this model by using new statistical methods related to machine learning, a larger dataset (2011-2022) and by including spatialization in order to propose a modelling framework that could be generalized to other coasts. We estimated drowning risk as a combination of hazard (ocean conditions) and exposure (beachgoer crowd). Several machine learning models were trained and compared using 3-day weather and sea forecasts from 2011 to 2022 as predictors along with an emergency calls database used as an outcome on the same time frame. The training set covered 188 drowning events over 1988 days while the test set covered 81 events over 663 days. Results: Our results show this new modeling framework is able to predict days with the highest risk of drowning events with improved accuracy on the Gironde coast: AUC = 0.9 (95% CI 0.89 to 0.91), PPV = 0.49 (95%CI 0.41 to 0.55) and NPV = 0.96 (95%CI 0.95 to 0.99). Conclusions: This supports the development of a new alert system that will provide useful information to decision makers. However, “all models are wrong, but some are useful” [2]. While this model could still be improved, with further feature engineering and improved data for rescues, this work also addresses the issue of identifying the right criteria to define what would actually be the “best” model depending on risk management policies set by decision makers.
(05/12/2023)
UR ETTIS, INRAE, EPOC, EPHE, PSL, UB, INSU - CNRS, CNRS, INSERM, CHU Bordeaux
Influence d’une structure anticlinale dans les modalités d’échanges et de recharge d’un système multicouche : l’exemple du système aquifère du Cénomanien dans le Sud de la Gironde (France)
(Géologues, n° 0016-7916, pp. p 17-22, 04/12/2023)
EPOC, EPHE, PSL, UB, INSU - CNRS, CNRS, SMEGREG, BRGM
Projet Phytosol Résidus de pesticides dans les sols français : présence, risques et persistance
À la différence de ce qui est fait pour les milieux aquatiques et l'atmosphère, la surveillance de la contamination des sols par les pesticides n'existe pas à l'échelle du territoire. Or, des travaux récents de chercheurs INRAE, en collaboration avec l'université de Bordeaux, montrent qu'un grand nombre de substances, en quantité importante, y persistent sous forme de résidus. Des résultats parus dans la revue Environmental Science & Technology.
(04/12/2023)
Info&Sols, INRAE, EPOC, EPHE, PSL, UB, INSU - CNRS, CNRS, UMR ISPA, Bordeaux Sciences Agro, INRAE, LAS, INRAE
Investigating beachgoer's perceptions of coastal bathing risks in South-West France
Research has suggested that experts differ from laypeople in their risk judgement. This hypothesis converges with a result often demonstrated in studies of beachgoers, who are shown to be generally unfamiliar with rips and underestimate the associated risks. However, no study has attempted to explicitly compare the perceptions made by beachgoers with those made by lifeguards, who are considered to be the experts in this field. In this presentation, we investigate the difference in risk perceptions by laypeople and lifeguards at a beach located in one of the most dangerous coastlines of France
(04/12/2023)
UR ETTIS, INRAE, EPOC, EPHE, PSL, UB, INSU - CNRS, CNRS, SMGBL, UB
Initialization shock in the ocean circulation reduces skill in decadal predictions of the North Atlantic subpolar gyre
Due to large northward heat transport, the Atlantic meridional overturning circulation (AMOC) strongly affects the climate of various regions. Its internal variability has been shown to be predictable decades ahead within climate models, providing the hope that synchronizing ocean circulation with observations can improve decadal predictions, notably of the North Atlantic subpolar gyre (SPG). Climate predictions require a starting point which is a reconstruction of the past climate. This is usually performed with data assimilation methods that blend available observations and climate model states together. There is no unique method to derive the initial conditions. Moreover, this can be performed using full-field observations or their anomalies superimposed on the model's climatology to avoid strong drifts in predictions. How critical ocean circulation drifts are for prediction skill has not been assessed yet. We analyze this possible connection using the dataset of 12 decadal prediction systems from the World Meteorological Organization Lead Centre for Annual-to-Decadal Climate Prediction. We find a variety of initial AMOC errors within the predictions related to a dynamically imbalanced ocean states leading to strongly displaced or multiple maxima in the overturning structures. This likely results in a blend of what is known as model drift and initial shock. We identify that the AMOC initialization influences the quality of the SPG predictions. When predictions show a large initial error in their AMOC, they usually have low skill for predicting internal variability of the SPG for a time horizon of 6-10 years. Full-field initialized predictions with low AMOC drift show better SPG skill than those with a large AMOC drift. Nevertheless, while the anomaly-initialized predictions do not experience large drifts, they show low SPG skill when skill also present in historical runs is removed using a residual correlation metric. Thus, reducing initial shock and model biases for the ocean circulation in prediction systems might help to improve their prediction for the SPG beyond 5 years. Climate predictions could also benefit from quality-check procedure for assimilation/initialization because currently the research groups only reveal the problems in initialization once the set of predictions has been completed, which is an expensive effort.
(Frontiers in Climate. vol. 5, n° 2624-9553, 04/12/2023)
EPOC, EPHE, PSL, UB, INSU - CNRS, CNRS, MOHC, UHH, CEN, UHH, GFI / BiU, UiB, UCAS, CAS, UCAR, GFDL, NOAA, CMCC, MPI-M, BSC-CNS, DMI, CCCma, ECCC, JAMSTEC, MRI, JMA
Archives sédimentaires : reconstruire les trajectoires temporelles des contaminants
(pp. Dans Baratelli, F., Thiebault, T. (eds), Dynamique des contaminants à l'échelle du bassin versant de la Seine, PIREN-Seine, Rapport de synthèse phase VIII, Volume 9, 2023, pp. 4-34, 01/12/2023)
METIS, EPHE, PSL, INSU - CNRS, SU, CNRS, EPHE, PSL, LSCE, UVSQ, INSU - CNRS, CNRS, DRF (CEA), CEA, EPOC, EPHE, PSL, UB, INSU - CNRS, CNRS, GERS-LEE, GéHCO, UT, GEDI, LSCE, UVSQ, INSU - CNRS, CNRS, DRF (CEA), CEA
Microscopic charcoals in ocean sediments off Africa track past fire intensity from the continent
Abstract Fires in Africa account for more than half of global fire-carbon emissions but the long-term evolution of fire activity and its link to global climate change remains elusive. Paleofire records provide descriptive information about fire changes through time, going beyond the range of satellite observations, although fire regime characteristics are challenging to reconstruct. To address this conceptual gap, we report here the abundance and morphometric data for a large set of microscopic charcoal samples ( n = 128) recovered from surface ocean sediments offshore Africa. We show that in subtropical Southern Africa, large and intense fires prevailing in open savanna-grassland ecosystems produce a high abundance of small and elongated microcharcoal particles. In contrast, in the forest ecosystems of equatorial and tropical regions of western and central Africa, low-intensity fires dominate, producing low amounts of squared microcharcoal particles. Microcharcoal concentration and morphotype in marine sediment records off Africa are thus indicative of fire regime characteristics. Applied to down-core marine charcoal records, these findings reveal that at orbital time-scale intense and large, open grassland-savanna fires occurred during wet periods in the sub-tropical areas. A strong contribution of fire carbon emissions during periods of precession and summer insolation maxima in the geological record is thus expected.
(Communications Earth & Environment. vol. 4, n° 2662-4435, pp. 133, 01/12/2023)
USV, EPOC, EPHE, PSL, UB, INSU - CNRS, CNRS, CEFE, UPVM, EPHE, PSL, CNRS, IRD [Occitanie], INRAE, Institut Agro, UM, IMBE, AU, AMU, CNRS, GEO-OCEAN, UBS, IFREMER, INSU - CNRS, UBO EPE, CNRS, MARUM
Is part-night lighting a suitable mitigation strategy to limit Artificial Light at Night effects on the biological rhythm at the behavioral and molecular scales of the oyster Crassostrea gigas?
(Science of the Total Environment. vol. 905, n° 0048-9697, pp. 167052, 01/12/2023)
EPOC, EPHE, PSL, UB, INSU - CNRS, CNRS
Les bassins carbonifères-permiens du sud du Bassin parisien et du nord du Massif central
Les bassins carbonifères-permiens du nord du Massif central sont connus historiquement en raison de leurs ressources carbonées (charbon, huiles bitumineuses), raison pour laquelle ils ont été largement étudiés jusque dans les années 1980, avec notamment la fin de l’exploration en France.
(Géochronique. vol. 168, n° 0292-8477, pp. 41-49, 01/12/2023)
BRGM, EPOC, EPHE, PSL, UB, INSU - CNRS, CNRS, GR, UR, INSU - CNRS, CNRS, BGS, UB, CNRS
Relative contribution of canopy and soil effects between plants with different metal tolerance along a metal pollution gradient
(Science of the Total Environment. vol. 904, n° 0048-9697, pp. 166905, 01/12/2023)
EPOC, EPHE, PSL, UB, INSU - CNRS, CNRS