bascule de visibilité Search & Display Options

Tout Sélectionner    Désélectionner
 |   | 
Détails
   print
  Enregistrements Liens
Auteur (down) Villon, S.; Mouillot, D.; Chaumont, M.; Darling, E.S.; Subsol, G.; Claverie, T.; Villeger, S. doi  openurl
  Titre A Deep learning method for accurate and fast identification of coral reef fishes in underwater images Type Article scientifique
  Année 2018 Publication Revue Abrégée Ecol. Inform.  
  Volume 48 Numéro Pages 238-244  
  Mots-Clés Automated identification; Convolutional neural network; density; Machine learning; Marine fishes; neural-networks; system; temperate; Underwater pictures; video stations; visual census; vulnerability  
  Résumé Identifying and counting fish individuals on photos and videos is a crucial task to cost-effectively monitor marine biodiversity, yet it remains difficult and time-consuming. In this paper, we present a method to assist the identification of fish species on underwater images, and we compare our model performances to human ability in terms of speed and accuracy. We first tested the performance of a convolutional neural network (CNN) trained with different photographic databases while accounting for different post-processing decision rules to identify 20 fish species. Finally, we compared the performance of species identification of our best CNN model with that of humans on a test database of 1197 fish images representing nine species. The best CNN was the one trained with 900,000 images including (i) whole fish bodies, (ii) partial fish bodies and (iii) the environment (e.g. reef bottom or water). The rate of correct identification was 94.9%, greater than the rate of correct identification by humans (89.3%). The CNN was also able to identify fish individuals partially hidden behind corals or behind other fish and was more effective than humans to identify fish on smallest or blurry images while humans were better to identify fish individuals in unusual positions (e.g. twisted body). On average, each identification by our best CNN using a common hardware took 0.06 s. Deep Learning methods can thus perform efficient fish identification on underwater images and offer promises to build-up new video-based protocols for monitoring fish biodiversity cheaply and effectively.  
  Adresse  
  Auteur institutionnel Thèse  
  Editeur Lieu de Publication Éditeur  
  Langue English Langue du Résumé Titre Original  
  Éditeur de collection Titre de collection Titre de collection Abrégé  
  Volume de collection Numéro de collection Edition  
  ISSN 1574-9541 ISBN Médium  
  Région Expédition Conférence  
  Notes Approuvé pas de  
  Numéro d'Appel MARBEC @ isabelle.vidal-ayouba @ collection 2475  
Lien permanent pour cet enregistrement
 

 
Auteur (down) Teixido, N.; Gambi, M.C.; Parravacini, V.; Kroeker, K.; Micheli, F.; Villeger, S.; Ballesteros, E. doi  openurl
  Titre Functional biodiversity loss along natural CO2 gradients Type Article scientifique
  Année 2018 Publication Revue Abrégée Nat. Commun.  
  Volume 9 Numéro Pages 5149  
  Mots-Clés carbon; community; consequences; diversity; fish; impact; ocean acidification; redundancy; reveals; vulnerability  
  Résumé The effects of environmental change on biodiversity are still poorly understood. In particular, the consequences of shifts in species composition for marine ecosystem function are largely unknown. Here we assess the loss of functional diversity, i.e. the range of species biological traits, in benthic marine communities exposed to ocean acidification (OA) by using natural CO2 vent systems. We found that functional richness is greatly reduced with acidification, and that functional loss is more pronounced than the corresponding decrease in taxonomic diversity. In acidified conditions, most organisms accounted for a few functional entities (i.e. unique combination of functional traits), resulting in low functional redundancy. These results suggest that functional richness is not buffered by functional redundancy under OA, even in highly diverse assemblages, such as rocky benthic communities.  
  Adresse  
  Auteur institutionnel Thèse  
  Editeur Lieu de Publication Éditeur  
  Langue English Langue du Résumé Titre Original  
  Éditeur de collection Titre de collection Titre de collection Abrégé  
  Volume de collection Numéro de collection Edition  
  ISSN 2041-1723 ISBN Médium  
  Région Expédition Conférence  
  Notes Approuvé pas de  
  Numéro d'Appel MARBEC @ isabelle.vidal-ayouba @ collection 2477  
Lien permanent pour cet enregistrement
 

 
Auteur (down) Su, G.; Villeger, S.; Brosse, S. doi  openurl
  Titre Morphological diversity of freshwater fishes differs between realms, but morphologically extreme species are widespread Type Article scientifique
  Année 2019 Publication Revue Abrégée Glob. Ecol. Biogeogr.  
  Volume 28 Numéro 2 Pages 211-221  
  Mots-Clés diet; ecology; patterns; vulnerability; richness; freshwater fish; functional diversity; extinction risk; traits; biogeographical realms; functional redundancy; functional vulnerability; mismatch; morphological traits; morphologically extreme species; rivers  
  Résumé Aim The aim was to analyse the morphological diversity of the world freshwater fish fauna. We tested to which extent the distributions of morphological traits are supported by extreme morphologies and how those extreme morphologies are distributed among realms and affect the functional vulnerability. We also analysed the contribution of between- and within-order morphological variability to the morphological differences between realms. Major taxa studied Freshwater fish. Location Global. Time period 1960s-2010s. Methods We used a global database of freshwater fishes from the six realms. Ten morphological traits were measured on 9,150 species, that is, 75% of the ca. 13,000 freshwater fish species. A principal components analysis was conducted to combine the 10 traits into a multidimensional space. We used Kolmogorov-Smirnov tests to compare the difference in morphological diversity between the six realms and between and within the major fish orders. We then identified the morphologically extreme species and quantified their contributions to the morphological range to assess the functional vulnerability and redundancy of fish faunas in the six biogeographical realms for freshwater ecosystems. Results We report a strong morphological variability among freshwater fishes of the world, with significant morphological differences among realm fish faunas, caused by an interplay between taxonomic composition of the realm faunas and morphological differences within orders among the realms. Morphologically extreme species accounted for a large percentage of the filling of the global morphological space and are distributed throughout the world. Main conclusions Fish morphological diversity is largely supported by a few species with extreme trait combinations, indicating that functional vulnerability exists throughout the world. Our results suggest that more attention should be paid to these morphologically extreme species and that they should be protected to ensure the sustainability of functions they support.  
  Adresse  
  Auteur institutionnel Thèse  
  Editeur Lieu de Publication Éditeur  
  Langue English Langue du Résumé Titre Original  
  Éditeur de collection Titre de collection Titre de collection Abrégé  
  Volume de collection Numéro de collection Edition  
  ISSN 1466-822x ISBN Médium  
  Région Expédition Conférence  
  Notes Approuvé pas de  
  Numéro d'Appel MARBEC @ isabelle.vidal-ayouba @ collection 2528  
Lien permanent pour cet enregistrement
 

 
Auteur (down) Parravicini, V.; Villeger, S.; McClanahan, T.R.; Arias-Gonzalez, J.E.; Bellwood, D.R.; Belmaker, J.; Chabanet, P.; Floeter, S.R.; Friedlander, A.M.; Guilhaumon, F.; Vigliola, L.; Kulbicki, M.; Mouillot, D. url  doi
openurl 
  Titre Global mismatch between species richness and vulnerability of reef fish assemblages Type Article scientifique
  Année 2014 Publication Revue Abrégée Ecology Letters  
  Volume 17 Numéro 9 Pages 1101-1110  
  Mots-Clés Vulnerability; biodiversity; biodiversity loss; conservation; coral-reefs; extinction; fisheries; functional diversity; hotspots; macroecology; marine; patterns; protected areas; risk assessment; sensitivity  
  Résumé The impact of anthropogenic activity on ecosystems has highlighted the need to move beyond the biogeographical delineation of species richness patterns to understanding the vulnerability of species assemblages, including the functional components that are linked to the processes they support. We developed a decision theory framework to quantitatively assess the global taxonomic and functional vulnerability of fish assemblages on tropical reefs using a combination of sensitivity to species loss, exposure to threats and extent of protection. Fish assemblages with high taxonomic and functional sensitivity are often exposed to threats but are largely missed by the global network of marine protected areas. We found that areas of high species richness spatially mismatch areas of high taxonomic and functional vulnerability. Nevertheless, there is strong spatial match between taxonomic and functional vulnerabilities suggesting a potential win-win conservation-ecosystem service strategy if more protection is set in these locations.  
  Adresse  
  Auteur institutionnel Thèse  
  Editeur Lieu de Publication Éditeur  
  Langue English Langue du Résumé Titre Original  
  Éditeur de collection Titre de collection Titre de collection Abrégé  
  Volume de collection Numéro de collection Edition  
  ISSN 1461-023x ISBN Médium  
  Région Expédition Conférence  
  Notes Approuvé pas de  
  Numéro d'Appel MARBEC @ isabelle.vidal-ayouba @ collection 630  
Lien permanent pour cet enregistrement
 

 
Auteur (down) Olivier, D.; Loiseau, N.; Petatan-Ramirez, D.; Trujillo Milian, O.; Suarez-Castillo, A.N.; Torre, J.; Munguia-Vega, A.; Reyes-Bonilla, H. doi  openurl
  Titre Functional-biogeography of the reef fishes of the islands of the Gulf of California: Integrating functional divergence into marine conservation Type Article scientifique
  Année 2018 Publication Revue Abrégée Glob. Ecol. Conserv.  
  Volume 16 Numéro Pages e00506  
  Mots-Clés biodiversity; communities; diversity; species richness; Biodiversity; vulnerability; framework; ecosystem function; redundancy; Functional traits; Biologically important area; Marine protected area; regionalization; rocky reefs; Sea of Cortez; Tropical Eastern Pacific  
  Résumé The Gulf of California (GC) is a semi-closed sea in the Tropical Eastern Pacific and is recognised as a highly diverse marine ecosystem. Despite this status, this region is still poorly studied in comparison to other marine hotspots. To start filling this gap, we attempt to provide a global overview of reef-fish diversity around the numerous islands of the region. We evaluated species richness, the abundance and biomass, and the functional diversity of the fish assemblages for the major islands of the GC. We first highlight that the southwestern part of the central GC is the hotspot of reef-fishes diversity within the GC, in terms of species richness, functional diversity, and fish abundance. We then found out an important functional divergence between fish assemblages of northern and southern regions. The fish biomass of each region is dominated by different species, characterised by different ecological traits (the opposite of functional convergence). This functional divergence may be explained by an important oceanographic heterogeneity along the latitudinal axis of the GC. The northern part shows larger climate fluctuations while the southern part is more tropical and climatically stable. Such functional divergence is a biodiversity facet to take into account when determining the sites to focus conservation action. In the GC, this criterion allows the importance of some sites to be highlighted to preserve the legacy of the reef-fishes, despite their lower diversity levels. (C) 2018 The Authors. Published by Elsevier B.V.  
  Adresse  
  Auteur institutionnel Thèse  
  Editeur Lieu de Publication Éditeur  
  Langue English Langue du Résumé Titre Original  
  Éditeur de collection Titre de collection Titre de collection Abrégé  
  Volume de collection Numéro de collection Edition  
  ISSN 2351-9894 ISBN Médium  
  Région Expédition Conférence  
  Notes Approuvé pas de  
  Numéro d'Appel MARBEC @ alain.herve @ collection 2481  
Lien permanent pour cet enregistrement
Tout Sélectionner    Désélectionner
 |   | 
Détails
   print

Save Citations:
Export Records: