Centre dedocumentation
scientifique

From local to global: A transfer learning-based approach for mapping poplar plantations at national scale using Sentinel-2 / Yousra Hamrouni in ISPRS Journal of photogrammetry and remote sensing, vol 171 (January 2021)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 171 (January 2021) . - pp 76 - 100 Titre : From local to global: A transfer learning-based approach for mapping poplar plantations at national scale using Sentinel-2 Type de document : Article/Communication Auteurs : Yousra Hamrouni, Auteur ; Eric Paillassa, Auteur ; Véronique Chéret, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 76 - 100 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes descripteurs IGN] apprentissage automatique [Termes descripteurs IGN] base de données forestières [Termes descripteurs IGN] carte de la végétation [Termes descripteurs IGN] classification par forêts aléatoires [Termes descripteurs IGN] couvert forestier [Termes descripteurs IGN] échantillonnage [Termes descripteurs IGN] France (administrative) [Termes descripteurs IGN] image Sentinel-MSI [Termes descripteurs IGN] mise à jour de base de données [Termes descripteurs IGN] populus (genre) [Termes descripteurs IGN] série temporelle Résumé : (auteur) Reliable estimates of poplar plantations area are not available at the French national scale due to the unsuitability and low update rate of existing forest databases for this short-rotation species. While supervised classification methods have been shown to be highly accurate in mapping forest cover from remotely sensed images, their performance depends to a great extent on the labelled samples used to build the models. In addition to their high acquisition cost, such samples are often scarce and not fully representative of the variability in class distributions. Consequently, when classification models are applied to large areas with high intra-class variance, they generally yield poor accuracies because of data shift issues. In this paper, we propose the use of active learning to efficiently adapt a classifier trained on a source image to spatially distinct target images with minimal labelling effort and without sacrificing the classification performance. The adaptation consists in actively adding to the initial local model new relevant training samples from other areas in a cascade that iteratively improves the generalisation capabilities of the classifier leading to a global model tailored to these different areas. This active selection relies on uncertainty sampling to directly focus on the most informative pixels for which the algorithm is the least certain of their class labels. Experiments conducted on Sentinel-2 time series revealed their high capacity to identify poplar plantations at a local scale with an average F-score ranging from 89.5% to 99.3%. For large area adaptation, the results showed that when the same number of training samples was used, active learning outperformed random sampling by up to 5% of the overall accuracy and up to 12% of the class F-score. Additionally, and depending on the class considered, the random sampling model required up to 50% more samples to achieve the same performance of an active learning-based model. Moreover, the results demonstrate the suitability of the derived global model to accurately map poplar plantations among other tree species with overall accuracy values up to 14% higher than those obtained with local models. The proposed approach paves the way for a national scale mapping in an operational context. Numéro de notice : A2021-013 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2020.10.018 date de publication en ligne : 20/11/2020 En ligne : https://doi.org/10.1016/j.isprsjprs.2020.10.018 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96417 [article]

Improving aboveground biomass estimates by taking into account density variations between tree components / Antoine Billard in Annals of Forest Science [en ligne], vol 77 n° 4 (December 2020)  

Public [article]  inAnnals of Forest Science [en ligne] > vol 77 n° 4 (December 2020) . - n° 103 Titre : Improving aboveground biomass estimates by taking into account density variations between tree components Type de document : Article/Communication Auteurs : Antoine Billard, Auteur ; Rodolphe Bauer, Auteur ; Frédéric Mothe, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : n° 103 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes descripteurs IGN] allométrie [Termes descripteurs IGN] base de données forestières [Termes descripteurs IGN] biomasse aérienne [Termes descripteurs IGN] bois de chauffage [Termes descripteurs IGN] branche (arbre) [Termes descripteurs IGN] diamètre à hauteur de poitrine [Termes descripteurs IGN] écorce [Termes descripteurs IGN] hauteur des arbres [Termes descripteurs IGN] résineux [Termes descripteurs IGN] tomographie radar [Termes descripteurs IGN] volume en bois [Vedettes matières IGN] Inventaire forestier Résumé : (auteur) Key message: Strong density differences were observed between stem wood at 1.30 m and other tree components (stem wood, stem bark, knots, branch stumps and branches). The difference, up to 40% depending on the component, should be taken into account when estimating the biomass available for industrial uses, mainly fuelwood and wood for chemistry. Context: Basic density is a major variable in the calculation of tree biomass. However, it is usually measured on stem wood only and at breast height. Aims: The objectives of this study were to compare basic density of stem wood at 1.30 m with other tree components and assess the impact of differences on biomass. Methods: Three softwood species were studied: Abies alba Mill., Picea abies (L.) H. Karst., Pseudotsuga menziesii (Mirb.) Franco. X-Ray computed tomography was used to measure density. Results: Large differences were observed between components. Basic density of components was little influenced by tree size and stand density. Overall, bark, knot and branch biomasses were highly underestimated by using basic density measured at 1.30 m. Conclusion: Using available wood density databases mainly based on breast height measurements would lead to important biases (up to more than 40%) on biomass estimates for some tree components. Further work is necessary to complete available databases. Numéro de notice : A2020-714 Affiliation des auteurs : non IGN Thématique : FORET Nature : Article DOI : 10.1007/s13595-020-00999-1 date de publication en ligne : 26/10/2020 En ligne : https://doi.org/10.1007/s13595-020-00999-1 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96282 [article]

Classifying physiographic regimes on terrain and hydrologic factors for adaptive generalization of stream networks / Lauwrence V. Stanislawski in International journal of cartography, Vol 6 n° 1 (March 2020)  

Public [article]  inInternational journal of cartography > Vol 6 n° 1 (March 2020) . - pp 4 - 21 Titre : Classifying physiographic regimes on terrain and hydrologic factors for adaptive generalization of stream networks Type de document : Article/Communication Auteurs : Lauwrence V. Stanislawski, Auteur ; Michael P. Finn, Auteur ; Barbara P. Buttenfield, Auteur Année de publication : 2020 Article en page(s) : pp 4 - 21 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes descripteurs IGN] algorithme de généralisation [Termes descripteurs IGN] altitude [Termes descripteurs IGN] base de données hydrographiques [Termes descripteurs IGN] cartographie des flux [Termes descripteurs IGN] classification dirigée [Termes descripteurs IGN] classification par maximum de vraisemblance [Termes descripteurs IGN] cours d'eau [Termes descripteurs IGN] drainage [Termes descripteurs IGN] Etats-Unis [Termes descripteurs IGN] pente [Termes descripteurs IGN] perméabilité du sol [Termes descripteurs IGN] représentation multiple [Termes descripteurs IGN] réseau hydrographique [Termes descripteurs IGN] ruissellement [Termes descripteurs IGN] segmentation [Termes descripteurs IGN] traitement automatique de données [Vedettes matières IGN] Généralisation Résumé : (auteur) Automated generalization software must accommodate multi-scale representations of hydrographic networks across a variety of geographic landscapes, because scale-related hydrography differences are known to vary in different physical conditions. While generalization algorithms have been tailored to specific regions and landscape conditions by several researchers in recent years, the selection and characterization of regional conditions have not been formally defined nor statistically validated. This paper undertakes a systematic classification of landscape types in the conterminous United States to spatially subset the country into workable units, in preparation for systematic tailoring of generalization workflows that preserve hydrographic characteristics. The classification is based upon elevation, standard deviation of elevation, slope, runoff, drainage and bedrock density, soil and bedrock permeability, area of inland surface water, infiltration-excess of overland flow, and a base flow index. A seven class solution shows low misclassification rates except in areas of high landscape diversity such as the Appalachians, Rocky Mountains, and Western coastal regions. Numéro de notice : A2020-070 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/23729333.2018.1443759 date de publication en ligne : 20/03/2018 En ligne : https://doi.org/10.1080/23729333.2018.1443759 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94632 [article]

Mapping dead forest cover using a deep convolutional neural network and digital aerial photography / Jean-Daniel Sylvain in ISPRS Journal of photogrammetry and remote sensing, vol 156 (October 2019)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 156 (October 2019) . - pp 14 - 26 Titre : Mapping dead forest cover using a deep convolutional neural network and digital aerial photography Type de document : Article/Communication Auteurs : Jean-Daniel Sylvain, Auteur ; Guillaume Drolet, Auteur ; Nicolas Brown, Auteur Année de publication : 2019 Article en page(s) : pp 14 - 26 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] arbre mort [Termes descripteurs IGN] base de données forestières [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] couvert forestier [Termes descripteurs IGN] feuillu [Termes descripteurs IGN] forêt boréale [Termes descripteurs IGN] image aérienne [Termes descripteurs IGN] orthoimage [Termes descripteurs IGN] peuplement mélangé [Termes descripteurs IGN] pinophyta [Termes descripteurs IGN] Québec (Canada) [Termes descripteurs IGN] santé des forêts Résumé : (Auteur) Tree mortality is an important forest ecosystem variable having uses in many applications such as forest health assessment, modelling stand dynamics and productivity, or planning wood harvesting operations. Because tree mortality is a spatially and temporally erratic process, rates and spatial patterns of tree mortality are difficult to estimate with traditional inventory methods. Remote sensing imagery has the potential to detect tree mortality at spatial scales required for accurately characterizing this process (e.g., landscape, region). Many efforts have been made in this sense, mostly using pixel- or object-based methods. In this study, we explored the potential of deep Convolutional Neural Networks (CNNs) to detect and map tree health status and functional type over entire regions. To do this, we built a database of around 290,000 photo-interpreted trees that served to extract and label image windows from 20 cm-resolution digital aerial images, for use in CNN training and evaluation. In this process, we also evaluated the effect of window size and spectral channel selection on classification accuracy, and we assessed if multiple realizations of a CNN, generated using different weight initializations, can be aggregated to provide more robust predictions. Finally, we extended our model with 5 additional classes to account for the diversity of landcovers found in our study area. When predicting tree health status only (live or dead), we obtained test accuracies of up to 94%, and up to 86% when predicting functional type only (broadleaf or needleleaf). Channel selection had a limited impact on overall classification accuracy, while window size increased the ability of the CNNs to predict plant functional type. The aggregation of multiple realizations of a CNN allowed us to avoid the selection of suboptimal models and help to remove much of the speckle effect when predicting on new aerial images. Test accuracies of plant functional type and health status were not affected in the extended model and were all above 95% for the 5 extra classes. Our results demonstrate the robustness of the CNN for between-scene variations in aerial photography and also suggest that this approach can be applied at operational level to map tree mortality across extensive territories. Numéro de notice : A2019-316 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2019.07.010 date de publication en ligne : 02/08/2019 En ligne : https://doi.org/10.1016/j.isprsjprs.2019.07.010 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93353 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2019101	RAB	Revue	Centre de documentation	En réserve 3L	Disponible
081-2019103	DEP-RECP	Revue	MATIS	Dépôt en unité	Exclu du prêt
081-2019102	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Cognitive aspects of human-computer interaction for GIS / Dieter Fritsch (2019)  

Public Titre : Cognitive aspects of human-computer interaction for GIS Type de document : Monographie Auteurs : Dieter Fritsch, Editeur scientifique Editeur : Bâle [Suisse] : Multidisciplinary Digital Publishing Institute MDPI Année de publication : 2019 Importance : 196 p. ISBN/ISSN/EAN : 978-3-03921-569-0 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Systèmes d'information géographique [Termes descripteurs IGN] Androïd [Termes descripteurs IGN] base de données statistiques [Termes descripteurs IGN] carte d'intérieur [Termes descripteurs IGN] classification par forêts aléatoires [Termes descripteurs IGN] cognition [Termes descripteurs IGN] état de l'art [Termes descripteurs IGN] géovisualisation [Termes descripteurs IGN] informatique en nuage [Termes descripteurs IGN] interface homme-machine [Termes descripteurs IGN] IOS [Termes descripteurs IGN] monde virtuel [Termes descripteurs IGN] oculométrie [Termes descripteurs IGN] représentation mentale spatiale [Termes descripteurs IGN] traitement de données localisées [Termes descripteurs IGN] visualisation de données Résumé : (éditeur) The book is dealing with recent progress in human–computer interaction (HCI) related to geographic information science (GIS). The Editorial starts with an overview about the evolution of the Internet and first HCI concepts and stimulates recent HCI developments using 3D and 4D apps, running on all mobile devices with OS Android, iOS, Linus, and Windows. Eight research articles present the state-of-the-art in HCI–GIS-related issues, starting with gender and age differences in using indoor maps via the estimation of building heights from space to an efficient visualization method for polygonal data with dynamic simplification. The review article deals with progress and challenges on entity alignment of geographic knowledge bases. Note de contenu : Editorial “Cognitive aspects of human-computer interaction for GIS” 1- Gender and age differences in using indoor maps for wayfinding in real environments 2- Collaborative Immersive Virtual Environments for Education in Geography 3- Evaluation of User Performance in Interactive and Static 3D Maps 4- Determining optimal video length for the estimation of building height through radial displacement measurement from space 5- 4D time density of trajectories: Discovering spatiotemporal patterns in movement data 6- Two-Dimensional Priority R-Tree Algorithm for Spatial Partitioning in SpatialHadoop 7- Estimating the performance of random forest versus multiple regression for predicting prices of the apartments 8- An efficient visualization method for polygonal data with dynamic simplification 9- Progress and challenges on entity alignment of geographic knowledge bases Numéro de notice : 25883 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Monographie DOI : 10.3390/books978-3-03921-569-0 En ligne : https://doi.org/10.3390/books978-3-03921-569-0 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95748

Les peintures murales des lieux de culte du Sud de l’arc alpin du XIVe au XVIe siècle / Océane Acquier in Géomatique expert, n° 124 (septembre - octobre 2018)

Permalink

GIS Coop: networks of silvicultural trials for supporting forest management under changing environment / Ingrid Seynave in Annals of Forest Science [en ligne], vol 75 n° 2 (June 2018)  

Permalink

Within- and between-tree variation of wood density components in Pinus nigra at six sites in Portugal / Alexandra Dias in Annals of Forest Science [en ligne], vol 75 n° 2 (June 2018)  

Permalink

How to enrich forest information by the analysis of the hardwood selling prices from public forests? : Case study, hardwood in Bourgogne Franche-Comte, France [diaporama] / Jean-Michel Leban (2018)  

Permalink

Partial polygon pruning of hydrographic features in automated generalization / Alexander K. Stum in Transactions in GIS, vol 21 n° 5 (October 2017)  

Permalink

A framework for interactive visual analysis of heterogeneous marine data in an integrated problem solving environment / Shuai Liu in Computers & geosciences, vol 104 (July 2017)  

Permalink

La BD Topage prend source / Marielle Mayo in Géomètre, n° 2145 (mars 2017)

Permalink

Optimizing the bioindication of forest soil acidity, nitrogen and mineral nutrition using plant species / Paulina E. Pinto in Ecological indicators, vol 71 (December 2016)  

Permalink

A new climatology of maximum and minimum temperature (1951–2010) in the Spanish mainland: a comparison between three different interpolation methods / D. Peña-Angulo in International journal of geographical information science IJGIS, vol 30 n° 11-12 (November - December 2016)  

Permalink

From virtual globes to ArcheoGIS : determining the technical and practical feasibilities / Berdien de Roo in Photogrammetric Engineering & Remote Sensing, PERS, vol 82 n° 9 (September 2016)  

Permalink