Centre de documentation
scientifique

Decision tree-based machine learning models for above-ground biomass estimation using multi-source remote sensing data and object-based image analysis / Haifa Tamiminia in Geocarto international, vol 38 n° inconnu ([01/01/2023])  

Public [article]  inGeocarto international > vol 38 n° inconnu [01/01/2023] Titre : Decision tree-based machine learning models for above-ground biomass estimation using multi-source remote sensing data and object-based image analysis Type de document : Article/Communication Auteurs : Haifa Tamiminia, Auteur ; Bahram Salehi, Auteur ; Masoud Mahdianpari, Auteur ; et al., Auteur Année de publication : 2023 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image mixte [Termes IGN] analyse d'image orientée objet [Termes IGN] biomasse aérienne [Termes IGN] boosting adapté [Termes IGN] classification par forêts d'arbres décisionnels [Termes IGN] classification pixellaire [Termes IGN] données d'entrainement (apprentissage automatique) [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] Extreme Gradient Machine [Termes IGN] image ALOS-PALSAR [Termes IGN] image Landsat [Termes IGN] image Sentinel-MSI [Termes IGN] image Sentinel-SAR [Termes IGN] New York (Etats-Unis ; état) [Termes IGN] réserve naturelle Résumé : (auteur) Forest above-ground biomass (AGB) estimation provides valuable information about the carbon cycle. Thus, the overall goal of this paper is to present an approach to enhance the accuracy of the AGB estimation. The main objectives are to: 1) investigate the performance of remote sensing data sources, including airborne light detection and ranging (LiDAR), optical, SAR, and their combination to improve the AGB predictions, 2) examine the capability of tree-based machine learning models, and 3) compare the performance of pixel-based and object-based image analysis (OBIA). To investigate the performance of machine learning models, multiple tree-based algorithms were fitted to predictors derived from airborne LiDAR data, Landsat, Sentinel-2, Sentinel-1, and PALSAR-2/PALSAR SAR data collected within New York’s Adirondack Park. Combining remote sensing data from multiple sources improved the model accuracy (RMSE: 52.14 Mg ha−1 and R2: 0.49). There was no significant difference among gradient boosting machine (GBM), random forest (RF), and extreme gradient boosting (XGBoost) models. In addition, pixel-based and object-based models were compared using the airborne LiDAR-derived AGB raster as a training/testing sample. The OBIA provided the best results with the RMSE of 33.77 Mg ha−1 and R2 of 0.81 for the combination of optical and SAR data in the GBM model. Numéro de notice : A2022-331 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article DOI : 10.1080/10106049.2022.2071475 Date de publication en ligne : 27/04/2022 En ligne : https://doi.org/10.1080/10106049.2022.2071475 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100607 [article]

Tracking annual dynamics of mangrove forests in mangrove National Nature Reserves of China based on time series Sentinel-2 imagery during 2016–2020 / Rong Zhang in International journal of applied Earth observation and geoinformation, vol 112 (August 2022)  

Public [article]  inInternational journal of applied Earth observation and geoinformation > vol 112 (August 2022) . - n° 102918 Titre : Tracking annual dynamics of mangrove forests in mangrove National Nature Reserves of China based on time series Sentinel-2 imagery during 2016–2020 Type de document : Article/Communication Auteurs : Rong Zhang, Auteur ; Mingming Jia, Auteur ; Zongming Wang, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 102918 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] algorithme de Otsu [Termes IGN] analyse d'image orientée objet [Termes IGN] analyse diachronique [Termes IGN] Chine [Termes IGN] dynamique de la végétation [Termes IGN] image Sentinel-MSI [Termes IGN] mangrove [Termes IGN] réserve naturelle Résumé : (auteur) Mangrove National Nature Reserves (MNNRs) play an extraordinarily significant role in conserving mangrove forests and their habitats. In China, one-fourth of the total mangrove forests were located in MNNRs. Understanding annual spatial distributions and conversions of these mangrove forests are important for precision conservation and rehabilitation efforts. However, to date, annual land cover maps of China’s MNNRs are still unavailable. Here, we proposed a rapid and robust approach to produce annual maps of each MNNRs for the time period of 2016–2020 based on 10-m resolution Sentinel-2 imagery. The proposed approach was developed using object-based image analysis, Otsu and Random Forest algorithm. Results showed that 1) during 2016–2020, areal extents of mangrove forest in all the MNNRs continuously increased from 5912 ha to 6128 ha; 2) obvious increase were found in Zhanjiang Mangrove National Nature Reserve where mangrove forest increased by 127 ha, accounted for 59% of national total increases; 3) newly grown mangrove forests were mainly converted from tidal flats and aquaculture ponds. Our annual maps of China’s MNNRs could provide a basis for managing mangrove ecosystems and supporting the implementation of Sustainable Development Goals related to coastal development. Numéro de notice : A2022-583 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.jag.2022.102918 En ligne : https://doi.org/10.1016/j.jag.2022.102918 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101348 [article]

Use of remotely sensed data to estimate tree species diversity as an indicator of biodiversity in Blouberg Nature Reserve, South Africa / Mangana Rampheri in Geocarto international, vol 37 n° 2 ([15/01/2022])  

Public [article]  inGeocarto international > vol 37 n° 2 [15/01/2022] . - pp 526 - 542 Titre : Use of remotely sensed data to estimate tree species diversity as an indicator of biodiversity in Blouberg Nature Reserve, South Africa Type de document : Article/Communication Auteurs : Mangana Rampheri, Auteur ; Timothy Dube, Auteur ; Inos Dhau, Auteur Année de publication : 2022 Article en page(s) : pp 526 - 542 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] Afrique du sud (état) [Termes IGN] arbre (flore) [Termes IGN] bande spectrale [Termes IGN] biodiversité végétale [Termes IGN] conservation de la flore [Termes IGN] détection de changement [Termes IGN] espèce végétale [Termes IGN] image Landsat-OLI [Termes IGN] image Landsat-TM [Termes IGN] indice de végétation [Termes IGN] régression [Termes IGN] réserve naturelle Résumé : (auteur) We use remotely sensed data to estimate species diversity in Blouberg Nature Reserve (BNR) in the Limpopo province, South Africa to understand the state of biodiversity since communities’ involvement in conservation initiatives. To achieve this objective, Landsat series data collected before and after community involvement in biodiversity conservation were used in conjunction with selected diversity indices i.e., Shannon-Wiener Index (H’) and Simpson Index (D). Thirty 15 m × 15 m field plots were selected and all trees within each plot were identified, with the help of Botanists. Further, we applied regression analysis to determine the relationship between satellite derived tree species diversity and field observations. The results of the study demonstrated a significant (p  Numéro de notice : A2022-052 Affiliation des auteurs : non IGN Thématique : BIODIVERSITE/FORET/IMAGERIE Nature : Article DOI : 10.1080/10106049.2020.1723717 Date de publication en ligne : 16/04/2020 En ligne : https://doi.org/10.1080/10106049.2020.1723717 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99443 [article]

Building fuzzy areal geographical objects from point sets / Jifa Guo in Transactions in GIS, vol 25 n° 6 (December 2021)  

Public [article]  inTransactions in GIS > vol 25 n° 6 (December 2021) . - pp 3067 - 3087 Titre : Building fuzzy areal geographical objects from point sets Type de document : Article/Communication Auteurs : Jifa Guo, Auteur ; Shihong Du, Auteur Année de publication : 2021 Article en page(s) : pp 3067 - 3087 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes IGN] analyse comparative [Termes IGN] habitat animal [Termes IGN] habitat d'espèce [Termes IGN] objet flou [Termes IGN] objet géographique zonal [Termes IGN] réserve naturelle Résumé : (Auteur) Representations of fuzzy geographic objects and analyses of their spatial relationships have received considerable attention in the GIS and spatial database domains over the past 30 years. However, building fuzzy geographical objects from real data is still a challenge. Simple fuzzy areal object models are too restrictive for many applications, and general fuzzy areal models may not be restrictive enough; as a result, the extent of fuzzy regions that satisfy the relevant conditions may be too large to affect the location description and spatial analysis. A condition by which the number of cores is not greater than one is added for the general object model, and an operable method for constructing fuzzy objects from the point set is proposed. Two peak and pass sets are determined for the membership surface by the fuzzy morphometric analysis method. The first set is used to initially divide the footprint of the fuzzy surface into smaller subfootprints, and the second set is used to merge insignificant fuzzy objects with their nearest significant fuzzy objects; thus, unreasonable division is avoided. Cross-validation is adopted to evaluate the generated fuzzy objects. An experiment is provided to verify the effectiveness of the proposed method. Numéro de notice : A2021-933 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1111/tgis.12808 Date de publication en ligne : 10/10/2021 En ligne : https://doi.org/10.1111/tgis.12808 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99454 [article]

Cloud-native seascape mapping of Mozambique’s Quirimbas National Park with Sentinel-2 / Dimitris Poursanidis in Remote sensing in ecology and conservation, vol 7 n° 2 (June 2021)  

Public [article]  inRemote sensing in ecology and conservation > vol 7 n° 2 (June 2021) . - pp 275 - 291 Titre : Cloud-native seascape mapping of Mozambique’s Quirimbas National Park with Sentinel-2 Type de document : Article/Communication Auteurs : Dimitris Poursanidis, Auteur ; Dimosthenis Traganos, Auteur ; Luisa Teixeira, Auteur ; Aurélie Shapiro, Auteur ; Lara Muaves, Auteur Année de publication : 2021 Article en page(s) : pp 275 - 291 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] analyse des mélanges spectraux [Termes IGN] classification et arbre de régression [Termes IGN] classification par forêts d'arbres décisionnels [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] écosystème [Termes IGN] Google Earth Engine [Termes IGN] habitat (nature) [Termes IGN] image Sentinel-MSI [Termes IGN] Mozambique [Termes IGN] récif corallien [Termes IGN] réserve naturelle [Termes IGN] surveillance écologique Résumé : (auteur) The lack of detailed spatial information on coastal resources, notably shallow water coral reefs and associated benthic habitats, impedes our ability to protect and manage them in the face of global climate change and anthropogenic impacts. Here, we develop a semi-automated workflow in the cloud that uses freely available Sentinel-2 data from the European Space Agency (ESA) Copernicus programme to derive information on near-shore coral reef habitats in the Quirimbas National Park (QNP), a recently declared biosphere reserve in northern Mozambique. We use an end-to-end cloud-based framework within the Google Earth Engine cloud geospatial platform to process imagery from raw pixels to cloud-free composites which are corrected for glint and surface artefacts, water column and derived estimated depth and then classified into four benthic habitats. Using independent training and validation data, we apply three supervised classification algorithms: random forests (RF), support vector machine (SVM) and classification and regression trees (CART). Our results show that random forests are the most accurate supervised algorithm with over 82% overall accuracy. We mapped over 105 000 ha of shallow water habitat inside the protected area, of which 18% are dominated by coral and hardbottom; 27.5% are seagrass and submerged aquatic vegetation and another 23.4% are soft and sandy substrates, and the remaining area is optically deep water. We employ satellite-derived bathymetry to assess slope, bathymetric position, rugosity and underwater topography of these habitats. Finally, a spectral unmixing model provides further sub-pixel–level information of habitats with the potential to monitor changes over time. This effort provides the first, consistent and repeatable and also scalable coastal information system for an east African tropical marine protected area, which hosts shallow-water ecosystems which are of great significance to local communities and building resilience towards climate change. Numéro de notice : A2021-733 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1002/rse2.187 Date de publication en ligne : 29/11/2020 En ligne : https://doi.org/10.1002/rse2.187 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98679 [article]

Drought propagation and its impact on groundwater hydrology of wetlands: a case study on the Doode Bemde nature reserve (Belgium) / Buruk Kitachew Wossenyeleh in Natural Hazards and Earth System Sciences, vol 21 n° 1 (January 2021)  

Permalink

Mapping and characterizing animals’ places of interest in forest environment / Laurence Jolivet (2021)  

Permalink

Les synergies de la télédétection optique par drone et satellite / Emilien Alvarez-Vanhard (2021)  

Permalink

Analyse de la déforestation dans la périphérie ouest de la réserve de biosphère du Dja au Cameroun, à partir d'une série multi-annuelle d'images Landsat / Eric Wilson Tegno Nguekam in Revue Française de Photogrammétrie et de Télédétection, n° 222 (novembre 2020)  

Permalink

Applying multi-temporal Landsat satellite data and Markov-cellular automata to predict forest cover change and forest degradation of sundarban reserve forest, Bangladesh / Mohammad Emran Hasan in Forests, vol 11 n° 9 (September 2020)  

Permalink

Evaluating techniques for mapping island vegetation from unmanned aerial vehicle (UAV) images: Pixel classification, visual interpretation and machine learning approaches / S.M. Hamylton in International journal of applied Earth observation and geoinformation, vol 89 (July 2020)  

Permalink

Visualizing when, where, and how fires happen in U.S. parks and protected areas / Nicole C. Inglis in ISPRS International journal of geo-information, vol 9 n° 5 (May 2020)  

Permalink

La Réserve biologique intégrale du Mont-Ventoux, un espace d’étude des écosystèmes forestiers hors sylviculture / Jérémy Terracol in Naturae, n° 5 ([29/03/2017])  

Permalink

Inventaires : les bryophytes de la Réserve naturelle régionale des étangs de Mépieu / Frédéric Gourges in Lo Parvi, n° 24 (2016) 

Permalink

Effects of landscape design of forest reserves on Saproxylic beetle diversity / Christophe Bouget in Conservation biology, vol 30 n° 1 (February 2016)  

Permalink