%0 Book Section
%9 OS CH : Chapitres d'ouvrages scientifiques
%A Mangeas, Morgan
%A Iovan, Corina
%A Vigliola, Laurent
%T L'intelligence artificielle au secours de la biodiversité
%B Biodiversité au Sud : recherches pour un monde durable
%C Marseille
%D 2020
%E Agnèse, Jean-François
%E Dangles, Olivier
%E Rodary, Estienne
%E Verdier, Valérie
%E Sabrié, Marie-Lise
%E Mourier, Thomas
%E Lavagne, Corinne
%E Thivent, V.
%L fdi:010080825
%G FRE
%I IRD
%@ 978-2-7099-2850-2
%K GESTION DE L'ENVIRONNEMENT ; CONSERVATION DE LA NATURE ; DIVERSITE SPECIFIQUE ; COLLECTE DE DONNEES ; INTELLIGENCE ARTIFICIELLE
%K BIODIVERSITE ; RECHERCHE PLURIDISCIPLINAIRE ; FOUILLE DE DONNEES ; ENTREPOT DE DONNEES
%K ZONE TROPICALE
%P 20-21
%U http://www.documentation.ird.fr/hor/fdi:010080825
%> http://horizon.documentation.ird.fr/exl-doc/pleins_textes/divers21-01/010080825.pdf
%W Horizon (IRD)
%$ 021ENVECO ; 082ECOSYS ; 122INTAR

%0 Journal Article
%9 ACL : Articles dans des revues avec comité de lecture répertoriées par l'AERES
%A Ampou, E. E.
%A Ouillon, Sylvain
%A Iovan, Corina
%A Andréfouët, Serge
%T Change detection of Bunaken Island coral reefs using 15 years of very high resolution satellite images : a kaleidoscope of habitat trajectories
%B Indonesia seas management
%D 2018
%L fdi:010073616
%G ENG
%J Marine Pollution Bulletin
%@ 0025-326X
%K Indonesia ; INDESO ; Remote sensing ; Reef flat ; Marine habitat ; Resilience
%K INDONESIE
%K BUNAKEN ILE
%M ISI:000438323100009
%N No spécial
%P 83-95
%R 10.1016/j.marpolbul.2017.10.067
%U http://www.documentation.ird.fr/hor/fdi:010073616
%> http://www.documentation.ird.fr/intranet/publi/2018/07/010073616.pdf
%V 131 Part B
%W Horizon (IRD)
%X In Bunaken Island (Indonesia), a time-series of very high resolution (2-4 m) satellite imagery was used to draw the long-term dynamics of shallow reef flat habitats from 2001 to 2015. Lack of historical georeferenced ground-truth data oriented the analysis towards a scenario-approach based on the monitoring of selected unambiguously-changing habitat polygons characterized in situ in 2014 and 2015. Eight representative scenarios (coral colonization, coral loss, coral stability, and sand colonization by seagrass) were identified. All occurred simultaneously in close vicinity, precluding the identification of a single general cause of changes that could have affected the whole reef. Likely, very fine differences in reef topography, exposure to wind/wave and sea level variations were responsible for the variety of trajectories. While trajectories of reef habitats is a way to measure resilience and coral recovery, here, the 15-year time-series was too short to be able to conclude on the resilience of Bunaken reefs.
%$ 036 ; 126

%0 Journal Article
%9 ACL : Articles dans des revues avec comité de lecture répertoriées par l'AERES
%A Derville, S.
%A Torres, L. G.
%A Iovan, Corina
%A Garrigue, Claire
%T Finding the right fit : comparative cetacean distribution models using multiple data sources and statistical approaches
%D 2018
%L fdi:010074154
%G ENG
%J Diversity and Distributions
%@ 1366-9516
%K citizen science ; generalized regression ; humpback whales ; machine learning ; species distribution models ; support vector machines
%K NOUVELLE CALEDONIE ; PACIFIQUE
%M ISI:000448070600012
%N 11
%P 1657-1673
%R 10.1111/ddi.12782
%U http://www.documentation.ird.fr/hor/fdi:010074154
%> http://www.documentation.ird.fr/intranet/publi/2018/11/010074154.pdf
%V 24
%W Horizon (IRD)
%X Aim: Accurate predictions of cetacean distributions are essential to their conservation but are limited by statistical challenges and a paucity of data. This study aimed at comparing the capacity of various statistical algorithms to deal with biases commonly found in nonsystematic cetacean surveys and to evaluate the potential for citizen science data to improve habitat modelling and predictions. An endangered population of humpback whales (Megaptera novaeangliae) in their breeding ground was used as a case study. Location: New Caledonia, Oceania. Methods: Five statistical algorithms were used to model the habitat preferences of humpback whales from 1,360 sightings collected over 14 years of nonsystematic research surveys. Three different background sampling approaches were tested when developing models from 625 crowdsourced sightings to assess methods accounting for citizen science spatial sampling bias. Model evaluation was conducted through cross-validation and prediction to an independent satellite tracking dataset. Results: Algorithms differed in complexity of the environmental relationships modelled, ecological interpretability and transferability. While parameter tuning had a great effect on model performances, GLMs generally had low predictive performance, SVMs were particularly hard to interpret, and BRTs had high descriptive power but showed signs of overfitting. MAXENT and especially GAMs provided a valuable complexity trade-off, accurate predictions and were ecologically intelligible. Models showed that humpback whales favoured cool (22-23 degrees C) and shallow waters (0-100 m deep) in coastal as well as offshore areas. Citizen science models converged with research survey models, specifically when accounting for spatial sampling bias. Main conclusions: Marine megafauna distribution models present specific challenges that may be addressed through integrative evaluation, independent testing and appropriately tuned statistical algorithms. Specifically, controlling overfitting is a priority when predicting cetacean distributions for large-scale conservation perspectives. Citizen science data appear to be a powerful tool to describe cetacean habitat.
%$ 020 ; 036

%0 Book Section
%9 OS CH : Chapitres d'ouvrages scientifiques
%A Iovan, Corina
%A Ampou, E.
%A Andrefouët, Serge
%A Ouillon, Sylvain
%A Gaspar, P.
%T Change detection of coral reef habitats from multi-temporal and multi-source satellite imagery in Bunaken, Indonesia
%B Multitemp 2015
%D 2015
%L fdi:010067244
%G ENG
%I IEEE
%@ 978-1-4673-7119-3
%K INDONESIE ; MER DE CORAIL
%K BUNAKEN ILE
%P 4
%R 10.1109/Multi-Temp.2015.7245758
%U http://www.documentation.ird.fr/hor/fdi:010067244
%> http://www.documentation.ird.fr/intranet/publi/depot/2016-07-18/010067244.pdf
%W Horizon (IRD)
%X This paper presents a framework for change detection of coral reef habitats in muti-temporal and multi-spectral satellite imagery acquired by multiple sensors. Our specific goal is to analyze the evolution coral reef habitats from images acquired over a period of twelve years. Our study area is located in the centre of the Coral Triangle, a hotspot of biodiversity in the Bunaken Island, Indonesia. In-situ data is used in a supervised classification approach to build classification models for eleven habitat types. Radiometric calibration is pairwise performed between each image in the data set and the reference one, and habitat models built on the reference image are used to classify the entire time series. Results obtained are discussed and the influential factors are put forward.
%B International Workshop on the Analysis of Multitemporal Remote Sensing Images
%8 2015/07/22-24
%$ 126 ; 036

%0 Book Section
%9 OS CH : Chapitres d'ouvrages scientifiques
%A Qin, Y.
%A Ferraz, A.
%A Mallet, C.
%A Iovan, Corina
%T Individual tree segmentation over large areas using airborne LiDAR point cloud and very high resolution optical imagery
%B Multitemp 2015
%D 2015
%L fdi:010067245
%G ENG
%I IEEE
%@ 978-1-4673-7119-3
%K FRANCE
%P 800-803
%U http://www.documentation.ird.fr/hor/fdi:010067245
%> http://www.documentation.ird.fr/intranet/publi/depot/2016-07-18/010067245.pdf
%W Horizon (IRD)
%X Timely and accurate measuremen ts of forest parameters are critical for ecosystem studies, sustainable forest resources management, monitoring and planning. This paper presents a processing chain for individual tree segmentation over large areas with airborne LiDAR 3D point cloud and very high resolution (VHR) optical imagery. The proposed processing chain consists of fo rest stand level delineation with optical imagery, individual tree segmentation with Canopy Height Model (CHM) derived from LiDAR point cloud, rough characterization of trees at forest stand level, and point clustering of individual tree with an Adaptive Mean Shift 3D (AMS3D) algorithm. The processing chain is developed with the expectation of supporting operational forest inventory at individual tree level. Experiment is conducted using LiDAR data acquired in Ventoux region, France. Results suggest that the proposed processing chain can be successfully adopted for individual tree characterization over large areas with different forest stands.
%B International Workshop on the Analysis of Multitemporal Remote Sensing Images
%8 2015/07/22-24
%$ 126 ; 082