Descripteur
Documents disponibles dans cette catégorie (128)



Etendre la recherche sur niveau(x) vers le bas
Monthly mapping of forest harvesting using dense time series Sentinel-1 SAR imagery and deep learning / Feng Zhao in Remote sensing of environment, vol 269 (February 2022)
![]()
[article]
Titre : Monthly mapping of forest harvesting using dense time series Sentinel-1 SAR imagery and deep learning Type de document : Article/Communication Auteurs : Feng Zhao, Auteur ; Rui Sun, Auteur ; Liheng Zhong, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 112822 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications
[Termes IGN] Californie (Etats-Unis)
[Termes IGN] carte thématique
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] déboisement
[Termes IGN] image Sentinel-SAR
[Termes IGN] récolte de bois
[Termes IGN] Rondonia (Brésil)
[Termes IGN] série temporelle
[Termes IGN] surveillance forestièreRésumé : (auteur) Compared with disturbance maps produced at annual or multi-year time steps, monthly mapping of forest harvesting can provide more temporal details needed for studying the socio-economic drivers (e.g., differentiating salvage logging and slash-and-burn from other timber harvesting) of harvesting and characterizing the associated intra-annual carbon and hydrological dynamics. Frequent cloud cover limits the application of optical remote sensing in timely mapping of forest changes. The freely available Sentinel-1 synthetic aperture radar (SAR) sensor provides an unprecedented opportunity to achieve more frequent mapping of forest harvesting than ever before (i.e., at monthly interval). The unique landscape pattern of forest harvesting from Sentienl-1 data (i.e., how a harvested patch contrasts to surrounding intact forests) holds critical information for harvesting mapping but have not been fully explored. In this study, we propose a deep learning-based (i.e., U-Net) approach using the landscape pattern from Sentinel-1 data to produce monthly maps of forest harvesting in two deforestation hotspots - California, USA and Rondônia, Brazil – for as long as three years. Our results show that (1) our proposed approach is reliable (mean F1 scores (the geometric mean of user's and producer's accuracies) 0.74–0.78; mean IoU (the area of intersection over union between the prediction part and target part) 0.59–0.65) for monthly forest harvesting mapping with Sentinel-1 data, outperforming the traditional object-based approach (0.38–0.43 in IoU). The varying harvesting pattern from Sentinel-1 data can be recognized by the U-Net bottleneck block as whole entities, which is the key advantage of our proposed approach; (2) multi-temporal SAR filtering is helpful for improving the accuracies of our proposed approach (increased F1 and IoU for 0.04 and 0.06, respectively); (3) our proposed model can be trained using samples collected during a particular time period over one location and be fine-tuned using sparse local samples from a new area to achieve optimal performance, and hence can greatly reduce training data collection effort when applied to new study sites; (4) forest harvesting maps produced using our approach revealed substantial variations in monthly harvesting activities: in Rondônia, most of the forest harvest occurred in July/August (the dry season) and about 14% of the dry season harvesting were followed by fires (i.e., slash-and-burn); in California, the rates of forest harvesting were relatively stable, but abnormally high values could occur due to salvage logging after big fires. Our novel approach for mapping forest harvesting at monthly interval represents an important step towards timely monitoring of forest harvesting and assisting stakeholders in developing sustainable strategy of forest management, especially for regions with frequent cloud cover. Numéro de notice : A2022-078 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article DOI : 10.1016/j.rse.2021.112822 Date de publication en ligne : 08/12/2021 En ligne : https://doi.org/10.1016/j.rse.2021.112822 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99745
in Remote sensing of environment > vol 269 (February 2022) . - n° 112822[article]Spatial variability of suspended sediments in San Francisco Bay, California / Niky C. Taylor in Remote sensing, vol 13 n° 22 (November-2 2021)
![]()
[article]
Titre : Spatial variability of suspended sediments in San Francisco Bay, California Type de document : Article/Communication Auteurs : Niky C. Taylor, Auteur ; Raphael M. Kudela, Auteur Année de publication : 2021 Article en page(s) : n° 4625 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection
[Termes IGN] baie
[Termes IGN] échantillonnage
[Termes IGN] estuaire
[Termes IGN] image Sentinel-MSI
[Termes IGN] pas d'échantillonnage au sol
[Termes IGN] qualité des eaux
[Termes IGN] réflectance
[Termes IGN] San Francisco
[Termes IGN] sédiment
[Termes IGN] spectroradiométrie
[Termes IGN] surface de l'eau
[Termes IGN] surveillance du littoral
[Termes IGN] turbidité des eaux
[Termes IGN] variabilitéRésumé : (auteur) Understanding spatial variability of water quality in estuary systems is important for making monitoring decisions and designing sampling strategies. In San Francisco Bay, the largest estuary system on the west coast of North America, tracking the concentration of suspended materials in water is largely limited to point measurements with the assumption that each point is representative of its surrounding area. Strategies using remote sensing can expand monitoring efforts and provide a more complete view of spatial patterns and variability. In this study, we (1) quantify spatial variability in suspended particulate matter (SPM) concentrations at different spatial scales to contextualize current in-water point sampling and (2) demonstrate the potential of satellite and shipboard remote sensing to supplement current monitoring methods in San Francisco Bay. We collected radiometric data from the bow of a research vessel on three dates in 2019 corresponding to satellite overpasses by Sentinel-2, and used established algorithms to retrieve SPM concentrations. These more spatially comprehensive data identified features that are not picked up by current point sampling. This prompted us to examine how much variability exists at spatial scales between 20 m and 10 km in San Francisco Bay using 10 m resolution Sentinel-2 imagery. We found 23–80% variability in SPM at the 5 km scale (the scale at which point sampling occurs), demonstrating the risk in assuming limited point sampling is representative of a 5 km area. In addition, current monitoring takes place along a transect within the Bay’s main shipping channel, which we show underestimates the spatial variance of the full bay. Our results suggest that spatial structure and spatial variability in the Bay change seasonally based on freshwater inflow to the Bay, tidal state, and wind speed. We recommend monitoring programs take this into account when designing sampling strategies, and that end-users account for the inherent spatial uncertainty associated with the resolution at which data are collected. This analysis also highlights the applicability of remotely sensed data to augment traditional sampling strategies. In sum, this study presents ways to supplement water quality monitoring using remote sensing, and uses satellite imagery to make recommendations for future sampling strategies. Numéro de notice : A2021-839 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.3390/rs13224625 Date de publication en ligne : 17/11/2021 En ligne : https://doi.org/10.3390/rs13224625 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99022
in Remote sensing > vol 13 n° 22 (November-2 2021) . - n° 4625[article]Deep-learning-based burned area mapping using the synergy of Sentinel-1&2 data / Qi Zhang in Remote sensing of environment, vol 264 (October 2021)
![]()
[article]
Titre : Deep-learning-based burned area mapping using the synergy of Sentinel-1&2 data Type de document : Article/Communication Auteurs : Qi Zhang, Auteur ; Linlin Ge, Auteur ; Ruiheng Zhang, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : n° 112575 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection
[Termes IGN] apprentissage profond
[Termes IGN] Californie (Etats-Unis)
[Termes IGN] cartographie thématique
[Termes IGN] classification par forêts d'arbres décisionnels
[Termes IGN] classification par Perceptron multicouche
[Termes IGN] coefficient de rétrodiffusion
[Termes IGN] image Sentinel-MSI
[Termes IGN] image Sentinel-SAR
[Termes IGN] incendie
[Termes IGN] réflectance du sol
[Termes IGN] réseau neuronal siamoisRésumé : (auteur) Around 350 million hectares of land are affected by wildfires every year influencing the health of ecosystems and leaving a trail of destruction. Accurate information over burned areas (BA) is essential for governments and communities to prioritize recovery actions. Prior research over the past decades has established the potentials and limitations of space-borne earth observation for mapping BA over large geographic areas at various scales. The operational deployment of Sentinel-1 and Sentinel-2 constellations significantly improved the quality and quantity of the imagery from the microwave (C-band) and optical regions on the spectrum. Based on that, this study set to investigate whether the existing coarse BA products can be further improved by the synergy of optical surface reflectance (SR), radar backscatter coefficient (BS), and/or radar interferometric coherence (COR) data with higher spatial resolutions. A Siamese Self-Attention (SSA) classification strategy is proposed for the multi-sensor BA mapping and a multi-source dataset is constructed at the object level for the training and testing. Results are analyzed by test sites, feature sources, and classification strategies to appraise the improvements achieved by the proposed method. Numéro de notice : A2021-807 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1016/j.rse.2021.112575 Date de publication en ligne : 06/07/2021 En ligne : https://doi.org/10.1016/j.rse.2021.112575 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98866
in Remote sensing of environment > vol 264 (October 2021) . - n° 112575[article]Apport de la photogrammétrie satellite pour la modélisation du manteau neigeux / César Deschamps-Berger (2021)
![]()
Titre : Apport de la photogrammétrie satellite pour la modélisation du manteau neigeux Type de document : Thèse/HDR Auteurs : César Deschamps-Berger, Auteur ; Marie Dumont, Directeur de thèse ; Simon Gascoin, Directeur de thèse Editeur : Toulouse : Université de Toulouse 3 Paul Sabatier Année de publication : 2021 Importance : 266 p. Format : 21 x 30 cm Note générale : bibliographie
Thèse en vue de l'obtention du Doctorat de l'Université de Toulouse, Spécialité : Surfaces et interfaces continentales, HydrologieLangues : Français (fre) Descripteur : [Vedettes matières IGN] Photogrammétrie spatiale
[Termes IGN] avalanche
[Termes IGN] bassin hydrographique
[Termes IGN] Californie (Etats-Unis)
[Termes IGN] carte d'occupation du sol
[Termes IGN] image Pléiades
[Termes IGN] manteau neigeux
[Termes IGN] modèle numérique de surface
[Termes IGN] modèle stéréoscopique
[Termes IGN] neige
[Termes IGN] Pyrénées (montagne)
[Termes IGN] télédétection électromagnétiqueIndex. décimale : THESE Thèses et HDR Résumé : (auteur) Le manteau neigeux en montagne est une ressource importante pour les écosystèmes et les activités humaines comme l'irrigation, l'approvisionnement en eau des populations, la production hydroélectrique et l'économie touristique. Il représente aussi un risque dans les zones exposées aux avalanches. L'étude et le suivi du manteau neigeux en montagne s'appuie souvent sur des réseaux de mesure, des observations par télédétection et de la modélisation. Les avancées récentes en photogrammétrie satellite offrent de nouvelles perspectives pour compléter les réseaux de mesures qui sont souvent insuffisants vis-à-vis de la forte variabilité spatiale du manteau neigeux. Une méthode de cartographie de la hauteur de neige à partir d'images stéréoscopiques Pléiades est présentée et appliquée sur plusieurs sites. La comparaison avec une carte de référence par lidar aéroporté fournit une estimation de l'erreur des produits de photogrammétrie satellite sur un bassin versant de Californie (États-Unis). A l'échelle d'un pixel de 3 m, l'erreur standard est de 0,7 m. L'erreur décroît à ~0,3 m lorsque les mesures sont moyennées sur des surfaces supérieures à 103 m². Avec cette précision, les cartes de hauteur de neige par photogrammétrie satellite permettent d'observer les processus modelant le manteau neigeux en montagne (transport par le vent, avalanche), de mesurer le volume de neige sur des zones de plus 100 km² et de décrire la variabilité spatiale du manteau. Une série de cartes de hauteur de neige est assimilée dans la chaine de modélisation SAFRAN-Crocus afin d'évaluer le potentiel de ces données pour améliorer la représentation spatiale des propriétés physiques du manteau neigeux. Un filtre particulaire est utilisé pour assimiler une carte de hauteur de neige par hiver pendant cinq hivers sur un bassin versant des Pyrénées. L'assimilation corrige des biais dans les précipitations initialement sous-estimées à haute altitude et introduit une variabilité spatiale autrement absente des forçages et des processus modélisés. Cette combinaison innovante de produits de télédétection satellite et d'un modèle complexe spatialisé offre de nouvelles perspectives pour l'estimation de la ressource en eau en montagne et du risque avalanche. Note de contenu : Introduction générale
1- Utilisation de la photogrammétrie satellite pour mesurer les changements de topographie à la surface de la Terre
2- Cartographie de la hauteur de neige avec des images Pléiades
3- Cartographie pluriannuelle de la hauteur de neige dans les Pyrénées
4- Assimilation de cartes de hauteur de neige dans un modèle spatialisé du manteau neigeux
ConclusionNuméro de notice : 28324 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Thèse française Note de thèse : Thèse de Doctorat : Surfaces et interfaces continentales, Hydrologie : Toulouse 3 : 2021 Organisme de stage : CESBIO DOI : sans En ligne : https://hal.archives-ouvertes.fr/tel-03334086 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98362 Deep learning for wildfire progression monitoring using SAR and optical satellite image time series / Puzhao Zhang (2021)
![]()
Titre : Deep learning for wildfire progression monitoring using SAR and optical satellite image time series Type de document : Thèse/HDR Auteurs : Puzhao Zhang, Auteur Editeur : Stockholm : Royal Institute of Technology Année de publication : 2021 Importance : 100 p. Format : 21 x 30 cm ISBN/ISSN/EAN : 978-91-7873-935-6 Note générale : bibliographie
Doctoral Thesis in GeoinformaticsLangues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image mixte
[Termes IGN] Alberta (Canada)
[Termes IGN] apprentissage profond
[Termes IGN] bande C
[Termes IGN] Californie (Etats-Unis)
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] Colombie-Britannique (Canada)
[Termes IGN] détection de changement
[Termes IGN] gestion des risques
[Termes IGN] image radar moirée
[Termes IGN] image Sentinel-SAR
[Termes IGN] incendie de forêt
[Termes IGN] série temporelle
[Termes IGN] surveillance forestière
[Termes IGN] Sydney (Nouvelle-Galles du Sud)
[Termes IGN] zone sinistréeRésumé : (auteur) Wildfires have coexisted with human societies for more than 350 million years, always playing an important role in affecting the Earth's surface and climate. Across the globe, wildfires are becoming larger, more frequent, and longer-duration, and tend to be more destructive both in lives lost and economic costs, because of climate change and human activities. To reduce the damages from such destructive wildfires, it is critical to track wildfire progressions in near real-time, or even real-time. Satellite remote sensing enables cost-effective, accurate, and timely monitoring on the wildfire progressions over vast geographic areas. The free availability of global coverage Landsat-8 and Sentinel-1/2 data opens the new era for global land surface monitoring, providing an opportunity to analyze wildfire impacts around the globe. The advances in both cloud computing and deep learning empower the automatic interpretation of spatio-temporal remote sensing big data on a large scale. The overall objective of this thesis is to investigate the potential of modern medium resolution earth observation data, especially Sentinel-1 C-Band synthetic aperture radar (SAR) data, in wildfire monitoring and develop operational and effective approaches for real-world applications. This thesis systematically analyzes the physical basis of earth observation data for wildfire applications, and critically reviews the available wildfire burned area mapping methods in terms of satellite data, such as SAR, optical, and SAR-Optical fusion. Taking into account its great power in learning useful representations, deep learning is adopted as the main tool to extract wildfire-induced changes from SAR and optical image time series. On a regional scale, this thesis has conducted the following four fundamental studies that may have the potential to further pave the way for achieving larger scale or even global wildfire monitoring applications. To avoid manual selection of temporal indices and to highlight wildfire-induced changes in burned areas, we proposed an implicit radar convolutional burn index (RCBI), with which we assessed the roles of Sentinel-1 C-Band SAR intensity and phase in SAR-based burned area mapping. The experimental results show that RCBI is more effective than the conventional log-ratio differencing approach in detecting burned areas. Though VV intensity itself may perform poorly, the accuracy can be significantly improved when phase information is integrated using Interferometric SAR (InSAR). On the other hand, VV intensity also shows the potential to improve VH intensity-based detection results with RCBI. By exploiting VH and VV intensity together, the proposed RCBI achieved an overall mapping accuracy of 94.68% and 94.17% on the 2017 Thomas Fire and the 2018 Carr Fire. For the scenario of near real-time application, we investigated and demonstrated the potential Sentinel-1 SAR time series for wildfire progression monitoring with Convolutional Neural Networks (CNN). In this study, the available pre-fire SAR time series were exploited to compute temporal average and standard deviation for characterizing SAR backscatter behaviors over time and highlighting the changes with kMap. Trained with binarized kMap time series in a progression-wise manner, CNN showed good capability in detecting wildfire burned areas and capturing temporal progressions as demonstrated on three large and impactful wildfires with various topographic conditions. Compared to the pseudo masks (binarized kMap), CNN-based framework brought an 0.18 improvement in F1 score on the 2018 Camp Fire, and 0.23 on the 2019 Chuckegg Creek Fire. The experimental results demonstrated that spaceborne SAR time series with deep learning can play a significant role for near real-time wildfire monitoring when the data becomes available at daily and hourly intervals. For continuous wildfire progression mapping, we proposed a novel framework of learning U-Net without forgetting in a near real-time manner. By imposing a temporal consistency restriction on the network response, Learning without Forgetting (LwF) allows the U-Net to learn new capabilities for better handling with newly incoming data, and simultaneously keep its existing capabilities learned before. Unlike the continuous joint training (CJT) with all available historical data, LwF makes U-Net learning not dependent on the historical training data any more. To improve the quality of SAR-based pseudo progression masks, we accumulated the burned areas detected by optical data acquired prior to SAR observations. The experimental results demonstrated that LwF has the potential to match CJT in terms of the agreement between SAR-based results and optical-based ground truth, achieving a F1 score of 0.8423 on the Sydney Fire (2019-2020) and 0.7807 on the Chuckegg Creek Fire (2019). We also found that the SAR cross-polarization ratio (VH/VV) can be very useful in highlighting burned areas when VH and VV have diverse temporal change behaviors. SAR-based change detection often suffers from the variability of the surrounding background noise, we proposed a Total Variation (TV)-regularized U-Net model to relieve the influence of SAR-based noisy masks. Considering the small size of labeled wildfire data, transfer learning was adopted to fine-tune U-Net from pre-trained weights based on the past wildfire data. We quantified the effects of TV regularization on increasing the connectivity of SAR-based areas, and found that TV-regularized U-Net can significantly increase the burned area mapping accuracy, bringing an improvement of 0.0338 in F1 score and 0.0386 in IoU score on the validation set. With TV regularization, U-Net trained with noisy SAR masks achieved the highest F1 (0.6904) and IoU (0.5295), while U-Net trained with optical reference mask achieved the highest F1 (0.7529) and IoU (0.6054) score without TV regularization. When applied on wildfire progression mapping, TV-regularized U-Net also worked significantly better than vanilla U-Net with the supervision of noisy SAR-based masks, visually comparable to optical mask-based results. On the regional scale, we demonstrated the effectiveness of deep learning on SAR-based and SAR-optical fusion based wildfire progression mapping. To scale up deep learning models and make them globally applicable, large-scale globally distributed data is needed. Considering the scarcity of labelled data in the field of remote sensing, weakly/self-supervised learning will be our main research directions to go in the near future. Note de contenu : 1- Introduction
2- Literature review
3- Study areas and data
4- Metodology
5- Results and discussionNuméro de notice : 28309 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Thèse étrangère Note de thèse : PhD Thesis : Geomatics : RTK Stockholm : 2021 DOI : sans En ligne : http://kth.diva-portal.org/smash/record.jsf?pid=diva2%3A1557429 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98130 Quantification probabiliste des taux de déformation crustale par inversion bayésienne de données GPS / Colin Pagani (2021)
PermalinkLos Angeles as a digital place: The geographies of user‐generated content / Andrea Ballatore in Transactions in GIS, Vol 24 n° 4 (August 2020)
PermalinkAutomated estimation and tools to extract positions, velocities, breaks, and seasonal terms from daily GNSS measurements: illuminating nonlinear Salton Trough deformation / Michael B. Heflin in Earth and space science, vol 7 n° 7 (July 2020)
PermalinkDelineating and modeling activity space using geotagged social media data / Lingqian Hu in Cartography and Geographic Information Science, vol 47 n° 3 (May 2020)
PermalinkGeocoding of trees from street addresses and street-level images / Daniel Laumer in ISPRS Journal of photogrammetry and remote sensing, vol 162 (April 2020)
PermalinkUsing multi-scale and hierarchical deep convolutional features for 3D semantic classification of TLS point clouds / Zhou Guo in International journal of geographical information science IJGIS, vol 34 n° 4 (April 2020)
PermalinkImproving operational radar rainfall estimates using profiler observations over complex terrain in Northern California / Haonan Chen in IEEE Transactions on geoscience and remote sensing, vol 58 n° 3 (March 2020)
PermalinkSimilarity measurement on human mobility data with spatially weighted structural similarity index (SpSSIM) / Chanwoo Jin in Transactions in GIS, Vol 24 n° 1 (February 2020)
PermalinkComparison of multi-seasonal Landsat 8, Sentinel-2 and hyperspectral images for mapping forest alliances in Northern California / Matthew L. Clark in ISPRS Journal of photogrammetry and remote sensing, vol 159 (January 2020)
PermalinkDe l’image optique "multi-stéréo" à la topographie très haute résolution et la cartographie automatique des failles par apprentissage profond / Lionel Matteo (2020)
Permalink