Résumé : Les fourmis sont des organismes cibles appropriés pour les études environnementales. Au cours de notre étude, nous nous sommes focalisés sur les fourmis de la litière via l'application de deux méthodes de récolte complémentaires selon le protocole all (ants of leaf litter). Dans les forêts naturelles de Guyane française, l'hétérogénéité environnementale et les perturbations structurent les communautés de fourmis de la litière en influençant la richesse, la diversité, l'abondance et la densité en espèces ainsi que les compositions taxonomique et fonctionnelle. Chaque type de formation végétale possède une communauté spécifique. La fragmentation et la conversion des forêts en plantations ont entrainé une altération plus ou moins profonde des communautés; cette variabilité est fonction du type d’agriculture et des espèces d'essences cultivées. Bien que l'altération des communautés se soit révélée maximale dans la plupart des monocultures, les plantations de cacaoyers ont un potentiel de conservation réel. Enfin, dans un contexte ou il est urgent de simplifier l'intégration des arthropodes dans les études de conservation, de contrôle et de suivi de la santé des écosystèmes terrestres, la méthode des réseaux de neurones est apparue comme un outil puissant pour mettre en évidence et analyser les patrons des communautés de fourmis.
Ants are reliable and relevant target organisms for environmental surveys. In our study, we focused on litter-dwelling ants through the use of two complementary sampling methods that were implemented according to the ants of leaf litter (all) protocol. In pristine forests of french guiana, leaf-litter ant communities are structured by environmental heterogeneity and natural perturbations - which influence species richness, diversity, abundance and density, as well as taxonomic and functional composition. This results in habitat-specific communities for each vegetal formation. Forest fragmentation and conversion into monocultures have led to a more or less deep alteration of the ant communities; this variability depends on the type of agricultural system and cultivated tree species. Although the intensity of community alteration peaked in tree monocultures, cocoa plantation exhibited a real potential for native species conservation. Finally, in the current context where simplifying the integration of arthropods into conservation programs as well as into surveys designed to monitor and manage the environment is critical, the use of neural networks appears to be a powerful tool for reliably highlighting and analyzing ant communities patterns.

http://www.theses.fr/2011AGUY0475/document

Éditeur(s) : HAL CCSD
Résumé : International audience
Modelling techniques for river hydrologic forecasting systems have taken advantage of machine learning methods especially for flood prediction. But current solutions, mostly based on artificial neural networks do not always meet end users requirements on the readability and the understandability of predictive models. In this paper, we present a new version of our original solution based on the concept of aggregate variables in order to predict flash flood events from observed water level and/or rain measurements, particularly in the context of caribbean watersheds in which flash flood are much uncertain. We combine aggregate variables in juries. Juries of aggregate variables are trained and tested using a typical 10-fold cross validation scheme. Best juries are searched through an evolutionary approach that is optimized. Different parameters are set up like aggregation periods and jury sizes to prove the efficiency of the proposed approach compared to classical solutions.
Congress on Evolutionary Computation (CEC) 2013
Cancun, Mexico

hal-00847582
https://hal.archives-ouvertes.fr/hal-00847582
DOI : 10.1109/CEC.2013.6557656

Éditeur(s) : HAL CCSD
Résumé : International audience
We instrumented a realistic car simulator to extract low level data related to the driver's use of the vehicle controls. After proceeding these data, we generated features that were fed to a Multi-Layer Perceptron (MLP) and Support Vector Machines (SVM). Our goal was determine if the driver's Blood Alcohol Content (BAC) was over $0.4g.l^{-1}$ or not, and even estimate the BAC value. Our device process the vehicle's controls data and then outputs the user BAC. We discuss the results of the prototype using the MLP and SVM algorithms in both single-user and multi-user context for detection of drunk drivers and estimation of the BAC value. The prototype performed better with single user base than with multi-user, and provided comparable results with MLP and SVM.
ESANN 2013 proccedings,European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
Bruges, Belgium

hal-00850138
https://hal.archives-ouvertes.fr/hal-00850138

Éditeur(s) : HAL CCSD MDPI
Résumé : International audience
Satellite precipitation products are a means of estimating rainfall, particularly in areas that are sparsely equipped with rain gauges. The Guiana Shield is a region vulnerable to high water episodes. Flood risk is enhanced by the concentration of population living along the main rivers. A good understanding of the regional hydro-climatic regime, as well as an accurate estimation of precipitation is therefore of great importance. Unfortunately, there are very few rain gauges available in the region. The objective of the study is then to compare satellite rainfall estimation products in order to complement the information available in situ and to perform a regional analysis of four operational precipitation estimates, by partitioning the whole area under study into a homogeneous hydro-climatic region. In this study, four satellite products have been tested, TRMM TMPA (Tropical Rainfall Measuring Mission Multisatellite Precipitation Analysis) V7 (Version 7) and RT (real time), CMORPH (Climate Prediction Center (CPC) MORPHing technique) and PERSIANN (Precipitation Estimation from Remotely-Sensed Information using Artificial Neural Network), for daily rain gauge data. Product performance is evaluated at daily and monthly scales based on various intensities and hydro-climatic regimes from 1 January 2001 to 30 December 2012 and using quantitative statistical criteria (coefficient correlation, bias, relative bias and root mean square error) and quantitative error metrics (probability of detection for rainy days and for no-rain days and the false alarm ratio). Over the entire study period, all products underestimate precipitation. The results obtained in terms of the hydro-climate show that for areas with intense convective precipitation, TMPA V7 shows a better performance than other products, especially in the estimation of extreme precipitation events. In regions along the Amazon, the use of PERSIANN is better. Finally, in the driest areas, TMPA V7 and PERSIANN show the same performance.
ISSN: 2072-4292

meteo-01304579
https://hal-meteofrance.archives-ouvertes.fr/meteo-01304579
https://hal-meteofrance.archives-ouvertes.fr/meteo-01304579/document
https://hal-meteofrance.archives-ouvertes.fr/meteo-01304579/file/remotesensing-07-15831.pdf
DOI : 10.3390/rs71215831

Éditeur(s) : HAL CCSD Elsevier
Résumé : International audience
In this paper, we propose a benchmarking of supervised machine learning techniques (neural networks, Gaussian processes and support vector machines) in order to forecast the Global Horizontal solar Irradiance (GHI). We also include in this benchmark a simple linear autoregressive (AR) model as well as two naive models based on persistence of the GHI and persistence of the clear sky index (denoted herein scaled persistence model). The models are calibrated and validatedwith data from three French islands: Corsica (41.91°N; 8.73°E), Guadeloupe (16.26°N; 61.51°W) and Reunion (21.34°S ; 55.49°E). The main findings of this work are, that for hour ahead solar forecasting,the machine learning techniques slightly improve the performances exhibited by the linear AR and the scaled persistence model. However, the improvement appears to be more pronounced in case of unstable sky conditions.These nonlinear techniques start to outperform their simple counterparts for forecasting horizons greater than one hour.
ISSN: 0038-092X

Droits : info:eu-repo/semantics/OpenAccess
hal-01099211
https://hal.archives-ouvertes.fr/hal-01099211
https://hal.archives-ouvertes.fr/hal-01099211/document
https://hal.archives-ouvertes.fr/hal-01099211/file/Manuscript_Lauretetal_Rev_unmarked.pdf