Descripteur
Documents disponibles dans cette catégorie (3895)
Ajouter le résultat dans votre panier
Visionner les documents numériques
Affiner la recherche Interroger des sources externes
Etendre la recherche sur niveau(x) vers le bas
Mapping forest in the Swiss Alps treeline ecotone with explainable deep learning / Thiên-Anh Nguyen in Remote sensing of environment, vol 281 (November 2022)
[article]
Titre : Mapping forest in the Swiss Alps treeline ecotone with explainable deep learning Type de document : Article/Communication Auteurs : Thiên-Anh Nguyen, Auteur ; Benjamin Kellenberger, Auteur ; Devis Tuia, Auteur Année de publication : 2022 Article en page(s) : n° 113217 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection
[Termes IGN] Alpes
[Termes IGN] apprentissage profond
[Termes IGN] canopée
[Termes IGN] carte forestière
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] écotone
[Termes IGN] hauteur des arbres
[Termes IGN] image à très haute résolution
[Termes IGN] image aérienne
[Termes IGN] image RVB
[Termes IGN] inventaire forestier étranger (données)
[Termes IGN] modèle numérique de surface de la canopée
[Termes IGN] SuisseRésumé : (auteur) Forest maps are essential to understand forest dynamics. Due to the increasing availability of remote sensing data and machine learning models like convolutional neural networks, forest maps can these days be created on large scales with high accuracy. Common methods usually predict a map from remote sensing images without deliberately considering intermediate semantic concepts that are relevant to the final map. This makes the mapping process difficult to interpret, especially when using opaque deep learning models. Moreover, such procedure is entirely agnostic to the definitions of the mapping targets (e.g., forest types depending on variables such as tree height and tree density). Common models can at best learn these rules implicitly from data, which greatly hinders trust in the produced maps. In this work, we aim at building an explainable deep learning model for forest mapping that leverages prior knowledge about forest definitions to provide explanations to its decisions. We propose a model that explicitly quantifies intermediate variables like tree height and tree canopy density involved in the forest definitions, corresponding to those used to create the forest maps for training the model in the first place, and combines them accordingly. We apply our model to mapping forest types using very high resolution aerial imagery and lay particular focus on the treeline ecotone at high altitudes, where forest boundaries are complex and highly dependent on the chosen forest definition. Results show that our rule-informed model is able to quantify intermediate key variables and predict forest maps that reflect forest definitions. Through its interpretable design, it is further able to reveal implicit patterns in the manually-annotated forest labels, which facilitates the analysis of the produced maps and their comparison with other datasets. Numéro de notice : A2022-794 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.rse.2022.113217 Date de publication en ligne : 01/09/2022 En ligne : https://doi.org/10.1016/j.rse.2022.113217 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101928
in Remote sensing of environment > vol 281 (November 2022) . - n° 113217[article]Semi-automatic development of thematic tactile maps / Jakub Wabiński in Cartography and Geographic Information Science, vol 49 n° 6 (November 2022)
[article]
Titre : Semi-automatic development of thematic tactile maps Type de document : Article/Communication Auteurs : Jakub Wabiński, Auteur ; Guillaume Touya , Auteur ; Albina Mościckaa, Auteur Année de publication : 2022 Projets : 3-projet - voir note / Article en page(s) : pp 545 - 565 Note générale : bibliographie
This research was funded by the Military University of Technology, Faculty of Civil Engineering and Geodesy, grant number [UGB/22-785/2022/WAT].Langues : Anglais (eng) Descripteur : [Termes IGN] carte tactile
[Termes IGN] carte thématique
[Termes IGN] généralisation cartographique automatisée
[Termes IGN] impression 3D
[Termes IGN] personne malvoyante
[Vedettes matières IGN] GénéralisationRésumé : (auteur) Tactile cartography has always been a niche topic, but even among tactile cartographers, little attention has been paid to thematic tactile maps. Thematic maps are used in education and the lack of such materials makes it difficult to fulfill particular subjects’ curriculums. In this research, we propose a methodology for automatic compilation of legible and cartographically sound educational thematic tactile maps that bases on the concept of anchor layers and uses unequivocal parameters for generalization operators. Using such an approach we were able to automate the most complicated parts of the procedure that deal particularly with the generalization of geospatial data. We verify the proposed methodology by preparing a sample case study 3D printed map that is later evaluated by students with visual impairments. We also evaluate a novel approach of hybrid map production that consists of both graphic and tactile content. Our results suggest that the proposed methodology can be used for fast and repeatable production of fully fledged thematic tactile maps and that it forms a significant step toward completely automatic tactile maps development in the future. Numéro de notice : A2022-680 Affiliation des auteurs : UGE-LASTIG+Ext (2020- ) Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/15230406.2022.2105747 Date de publication en ligne : 31/08/2022 En ligne : https://doi.org/10.1080/15230406.2022.2105747 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101521
in Cartography and Geographic Information Science > vol 49 n° 6 (November 2022) . - pp 545 - 565[article]Topographic descriptors on the early Dutch charts of the antipodes / Jan Tent in International journal of cartography, vol 8 n° 3 (November 2022)
[article]
Titre : Topographic descriptors on the early Dutch charts of the antipodes Type de document : Article/Communication Auteurs : Jan Tent, Auteur Année de publication : 2022 Article en page(s) : pp 272 - 290 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Toponymie
[Termes IGN] Australie
[Termes IGN] carte ancienne
[Termes IGN] descripteur
[Termes IGN] explorateur
[Termes IGN] littoral
[Termes IGN] néerlandais (langue)
[Termes IGN] nomenclature
[Termes IGN] Nouvelle-Zélande
[Termes IGN] Papouasie-Nouvelle-Guinée
[Termes IGN] toponymeRésumé : (auteur) The early Dutch charts of coastal Australia, New Zealand and New Guinea are peppered not only with toponyms but also with topographic descriptors. The latter were intended as navigational aids and warnings for future navigators. Naming or describing a geographic feature is a method of distinguishing it from the surrounding topography. At times some topographic descriptors have been considered or interpreted as toponyms. This article explores whether there are any means of determining the difference between the two, and what may have been initially intended by the explorers who entered them on their manuscript charts. Reasons for the relevance of making such a distinction are also considered. Numéro de notice : A2022-746 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE/TOPONYMIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/23729333.2020.1859937 Date de publication en ligne : 11/02/2021 En ligne : https://doi.org/10.1080/23729333.2020.1859937 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101731
in International journal of cartography > vol 8 n° 3 (November 2022) . - pp 272 - 290[article]Using converted WW1 Army Grid Referencing Systems to identify locations where Australian soldiers fell Europe / Rodney Deakin in International journal of cartography, vol 8 n° 3 (November 2022)
[article]
Titre : Using converted WW1 Army Grid Referencing Systems to identify locations where Australian soldiers fell Europe Type de document : Article/Communication Auteurs : Rodney Deakin, Auteur Année de publication : 2022 Article en page(s) : pp 308 - 325 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Projections
[Termes IGN] Australie
[Termes IGN] carte ancienne
[Termes IGN] carte militaire
[Termes IGN] carte topographique
[Termes IGN] coordonnées géographiques
[Termes IGN] Europe (géographie politique)
[Termes IGN] Google Maps
[Termes IGN] grille
[Termes IGN] guerre
[Termes IGN] projection conforme
[Termes IGN] projection Universal Transverse Mercator
[Termes IGN] transformation de coordonnées
[Termes IGN] vingtième siècleRésumé : (auteur) Topographic maps (1:40,000) used by the British Army on the Western Front in World War 1 had a five-part Grid Reference System consisting of: (1) Map Number; (2) Letter-Square – 24 letter squaresA to X on each map; (3) Number-Square – 36 (and sometimes 30) 1000-yard squares in each letter square; (4) Minor-Square – four 500-yard squares denoted a, b, c, d in each number square; (5) Small-Square – 10 × 10 = 100 small-squares in a minor-square. Letter and number grid Woesten references (e.g. X: 28.A.6.b.73) cannot be used by modern GPS navigation devices that require geographical coordinates (latitude and longitude) or current map grid coordinates. This paper provides the background behind this project and demonstrates a method of transforming WW1 grid references to Universal Transverse Mercator (UTM) grid coordinates using Google Maps to obtain geographical coordinates, Geographic to UTM grid conversion and a 2D Conformal transformation. As well, it provides a ‘snapshot’ of practical methods that were used to develop a software package that would allow amateur military historians to convert the WW1 Grid Reference System to contemporary coordinates. Numéro de notice : A2022-748 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/23729333.2021.1877890 Date de publication en ligne : 13/05/2021 En ligne : https://doi.org/10.1080/23729333.2021.1877890 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101734
in International journal of cartography > vol 8 n° 3 (November 2022) . - pp 308 - 325[article]Modelling and accessing land degradation vulnerability using remote sensing techniques and the analytical hierarchy process approach / Abebe Debele Tolche in Geocarto international, vol 37 n° 24 ([20/10/2022])
[article]
Titre : Modelling and accessing land degradation vulnerability using remote sensing techniques and the analytical hierarchy process approach Type de document : Article/Communication Auteurs : Abebe Debele Tolche, Auteur ; Megersa Adugna Gurara, Auteur ; Quoc Bao Pham, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 7122 - 7142 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection
[Termes IGN] carte thématique
[Termes IGN] dégradation des sols
[Termes IGN] Ethiopie
[Termes IGN] Google Earth
[Termes IGN] image Terra-MODIS
[Termes IGN] Normalized Difference Vegetation Index
[Termes IGN] pédologie locale
[Termes IGN] précipitation
[Termes IGN] processus de hiérarchisation analytique
[Termes IGN] température au sol
[Termes IGN] topographie locale
[Termes IGN] vulnérabilitéRésumé : (auteur) Land degradation and desertification have recently become a critical problem in Ethiopia. Accordingly, identification of land degradation vulnerable zonation and mapping was conducted in Wabe Shebele River Basin, Ethiopia. Precipitation derived from Global Precipitation Measurement Mission (GMP), the Moderate Resolution Imaging Spectroradiometer (MODIS) Normalized difference vegetation index (NDVI) and land surface temperature (LST), topography (slope), and pedological properties (i.e., soil depth, soil pH, soil texture, and soil drainage) were used in the current study. NDVI has been considered as the most significant parameter followed by the slope, precipitation and temperature. Geospatial techniques and the Analytical Hierarchy Process (AHP) approach were used to model the land degradation vulnerable index. Validation of the results with google earth image shows the applicability of the model in the study. The result is classified into very highly vulnerable (17.06%), highly vulnerable (15.01%), moderately vulnerable (32.72%), slightly vulnerable (16.40%), and very slightly vulnerable (18.81%) to land degradation. Due to the small rate of precipitation which is vulnerable to evaporation by high temperature in the region, the downstream section of the basis is categorized as highly vulnerable to Land Degradation (LD) and vice versa in the upstream section of the basin. Moreover, the validation using the Receiver Operating Characteristic (ROC) curve analysis shows an area under the ROC curve value of 80.92% which approves the prediction accuracy of the AHP method in assessing and modelling LD vulnerability zone in the study area. The study provides a substantial understanding of the effect of land degradation on sustainable land use management and development in the basin. Numéro de notice : A2022-776 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2021.1959656 Date de publication en ligne : 01/09/2021 En ligne : https://doi.org/10.1080/10106049.2021.1959656 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101831
in Geocarto international > vol 37 n° 24 [20/10/2022] . - pp 7122 - 7142[article]Land use/land cover mapping from airborne hyperspectral images with machine learning algorithms and contextual information / Ozlem Akar in Geocarto international, vol 37 n° 22 ([10/10/2022])PermalinkComparison of layer-stacking and Dempster-Shafer theory-based methods using Sentinel-1 and Sentinel-2 data fusion in urban land cover mapping / Dang Hung Bui in Geo-spatial Information Science, vol 25 n° 3 (October 2022)PermalinkDeep learning-based local climate zone classification using Sentinel-1 SAR and Sentinel-2 multispectral imagery / Lin Zhou in Geo-spatial Information Science, vol 25 n° 3 (October 2022)PermalinkDeep learning high resolution burned area mapping by transfer learning from Landsat-8 to PlanetScope / V.S. Martins in Remote sensing of environment, vol 280 (October 2022)PermalinkPyeo: A Python package for near-real-time forest cover change detection from Earth observation using machine learning / J.F. Roberts in Computers & geosciences, vol 167 (October 2022)PermalinkRiparian ecosystems mapping at fine scale: a density approach based on multi-temporal UAV photogrammetric point clouds / Elena Belcore in Remote sensing in ecology and conservation, vol 8 n° 5 (October 2022)PermalinkLe chantier de la Nouvelle carte de France / Pierre Clergeot in Géomètre, n° 2205 (septembre 2022)PermalinkDesign and construction of a colourblind-friendly Surabaya city angkot route map prototype / Arzakhy Indhira Pramesti in Cartographica, vol 57 n° 3 (September 2022)PermalinkHistorical mapping of rice fields in Japan using phenology and temporally aggregated Landsat images in Google Earth Engine / Luis Carrasco in ISPRS Journal of photogrammetry and remote sensing, vol 191 (September 2022)PermalinkMapping annual urban evolution process (2001–2018) at 250 m: A normalized multi-objective deep learning regression / Haoyu Wang in Remote sensing of environment, vol 278 (September 2022)Permalink