Centre dedocumentation
scientifique

A second-order attention network for glacial lake segmentation from remotely sensed imagery / Shidong Wang in ISPRS Journal of photogrammetry and remote sensing, vol 189 (July 2022)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 189 (July 2022) . - pp 289 - 301 Titre : A second-order attention network for glacial lake segmentation from remotely sensed imagery Type de document : Article/Communication Auteurs : Shidong Wang, Auteur ; Maria V. Peppa, Auteur ; Wen Xiao, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 289 - 301 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage profond [Termes IGN] attention (apprentissage automatique) [Termes IGN] changement climatique [Termes IGN] covariance [Termes IGN] image Landsat-8 [Termes IGN] Inde [Termes IGN] itération [Termes IGN] lac glaciaire [Termes IGN] réflectance de surface [Termes IGN] segmentation d'image [Termes IGN] tenseur Résumé : (auteur) Climate change is increasing the risk of glacial lake outburst floods (GLOFs) in many of the world’s most vulnerable and high mountain regions. Simultaneously, remote sensing technologies now facilitate continuous monitoring of glacial lake evolution around the globe, although accurate and reliable automated glacial lake mapping from satellite data remains challenging. In this study, a Second-order Attention Network (SoAN) is devised for the automated segmentation of lakes from satellite imagery. In particular, a novel Second-order Attention Module (SoAM) is proposed to capture the long-range spatial dependencies and establish channel attention derived from the covariance representations of local features. Furthermore, as the dimensions of the input and output tensors are identical and it simply relies on matrix calculations, the proposed SoAM can be embedded into different positions of a given architecture while maintaining similar reference speed. The designed network is implemented on Landsat-8 imagery and outputs are compared against representative deep learning models, demonstrating improved results with a Dice of 81.02% and a F2 Score of 85.17%. Numéro de notice : A2022-470 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2022.05.007 Date de publication en ligne : 29/05/2022 En ligne : https://doi.org/10.1016/j.isprsjprs.2022.05.007 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100814 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2022071	SL	Revue	Centre de documentation	Revues en salle	Disponible

Use of multi-temporal and multi-sensor data for continental water body extraction in the context of the SWOT mission / Nicolas Gasnier (2022)  

Public Titre : Use of multi-temporal and multi-sensor data for continental water body extraction in the context of the SWOT mission Type de document : Thèse/HDR Auteurs : Nicolas Gasnier, Auteur ; Florence Tupin, Directeur de thèse ; Loïc Denis, Directeur de thèse Editeur : Paris : Institut Polytechnique de Paris Année de publication : 2022 Importance : 213 p. Format : 21 x 30 cm Note générale : Bibliographie Thèse de doctorat présentée à l’Institut Polytechnique de Paris, spécialité Images Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications [Termes IGN] base de données localisées [Termes IGN] détection d'objet [Termes IGN] détection de changement [Termes IGN] données hydrographiques [Termes IGN] hauteurs de mer [Termes IGN] image multitemporelle [Termes IGN] image radar moirée [Termes IGN] image Sentinel-SAR [Termes IGN] image SWOT [Termes IGN] lac [Termes IGN] rivière [Termes IGN] série temporelle [Termes IGN] télédétection en hyperfréquence Index. décimale : THESE Thèses et HDR Résumé : (Auteur) Spaceborne remote sensing provides hydrologists and decision-makers with data that are essential for understanding the water cycle and managing the associated resources and risks. The SWOT satellite, which is a collaboration between the French (CNES) and American (NASA, JPL) space agencies, is scheduled for launch in 2022 and will measure the height of lakes, rivers, and oceans with high spatial resolution. It will complement existing sensors, such as the SAR and optical constellations Sentinel-1 and 2, and in situ measurements. SWOT represents a technological breakthrough as it is the first satellite to carry a near-nadir swath altimeter. The estimation of water levels is done by interferometry on the SAR images acquired by SWOT. Detecting water in these images is therefore an essential step in processing SWOT data, but it can be very difficult, especially with low signal-to-noise ratios, or in the presence of unusual radiometries. In this thesis, we seek to develop new methods to make water detection more robust. To this end, we focus on the use of exogenous data to guide detection, the combination of multi-temporal and multi-sensor data and denoising approaches. The first proposed method exploits information from the river database used by SWOT (derived from GRWL) to detect narrow rivers in the image in a way that is robust to both noise in the image, potential errors in the database, and temporal changes. This method relies on a new linear structure detector, a least-cost path algorithm, and a new Conditional Random Field segmentation method that combines data attachment and regularization terms adapted to the problem. We also proposed a method derived from GrabCut that uses an a priori polygon containing a lake to detect it on a SAR image or a time series of SAR images. Within this framework, we also studied the use of a multi-temporal and multi-sensor combination between Sentinel-1 SAR and Sentinel-2 optical images. Finally, as part of a preliminary study on denoising methods applied to water detection, we studied the statistical properties of the geometric temporal mean and proposed an adaptation of the variational method MuLoG to denoise it. Note de contenu : 1. Introduction 1.1 Context 1.2 Contributions 1.3 Organization of the manuscript I BACKGROUND ON SAR REMOTE SENSING AND WATER SURFACE MONITORING WITH SAR IMAGES 2. SAR images 2.1 Physics and statistics of SAR images 2.2 The SWOT mission 2.3 Sentinel-1 3. SAR water detection and hydrological prior 3.1 Water detection in SAR images 3.2 SWOT processing and products 3.3 Prior water masks and databases 4. Methodological background 4.1 Markov random fields 4.2 Variational methods for image denoising PROPOSED APPROACHES 5. Guided extraction of narrow rivers on SAR images using an exogenous river database 5.1 Introduction 5.2 Proposed river segmentation pipeline 5.3 Experimental results 5.4 Conclusion 6. Adaptation of the GrabCut method to SAR images: lake detection from a priori polygon 6.1 Single-date GrabCut method for lake detection from a priori polygon 6.2 Multitemporal and multi-sensor adaptations of the method 6.3 2D+T GrabCut of SAR images with temporal regularization for lake detection within an a priori mask 6.4 Joint 2D+T segmentation of SAR and optical images 7. Denoising of the temporal geometric mean 7.1 Introduction 7.2 Statistics of the temporal geometric mean of SAR intensities 7.3 Denoising method 7.4 Experiments 7.5 Application to change detection 7.6 Application to ratio-based denoising of single SAR images within a time series 7.7 Conclusion 8 Conclusion and perspectives Numéro de notice : 26762 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Thèse française Note de thèse : Thèse de Doctorat : Images : Palaiseau : 2022 Organisme de stage : Télécom Paris nature-HAL : Thèse DOI : sans Date de publication en ligne : 17/02/2022 En ligne : https://tel.archives-ouvertes.fr/tel-03578831/document Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99823

Ten years of Lake Taupō surface height estimates using the GNSS interferometric reflectometry / Lucas D. Holden in Journal of geodesy, vol 95 n° 7 (July 2021)  

Public [article]  inJournal of geodesy > vol 95 n° 7 (July 2021) . - n° 74 Titre : Ten years of Lake Taupō surface height estimates using the GNSS interferometric reflectometry Type de document : Article/Communication Auteurs : Lucas D. Holden, Auteur ; Kristine M. Larson, Auteur Année de publication : 2021 Article en page(s) : n° 74 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de géodésie spatiale [Termes IGN] altimétrie satellitaire par radar [Termes IGN] lac [Termes IGN] Nouvelle-Zélande [Termes IGN] réflectométrie par GNSS [Termes IGN] série temporelle [Termes IGN] signal GNSS [Termes IGN] station GNSS Résumé : (auteur) A continuously operating GNSS station within a lake interior is uncommon, but advantageous for testing the GNSS Interferometric Reflectometry (GNSS-IR) technique. In this research, GNSS-IR is used to estimate ten years of lake surface heights for Lake Taupō in New Zealand. This is achieved using data collected from station TGHO, approximately 4 km from the lake’s shoreline. Its reliability is assessed by comparisons with shoreline gauges and satellite radar altimetry lake surface heights. Relative RMS differences between the daily averaged lake gauge and GNSS-IR lake surface heights range from ± 0.027 to ± 0.028 m. Relative RMS differences between the satellite radar altimetry lake surface heights and the GNSS-IR lake surface heights are ± 0.069 m and ± 0.124 m. The results show that the GNSS-IR technique at Lake Taupō can provide reliable lake surface height estimates in a terrestrial reference frame. A new ground-based absolute satellite radar altimetry calibration/validation approach based on GNSS-IR is proposed and discussed. Numéro de notice : A2021-513 Affiliation des auteurs : non IGN Thématique : POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s00190-021-01523-7 Date de publication en ligne : 18/06/2021 En ligne : https://doi.org/10.1007/s00190-021-01523-7 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97932 [article]

Using remote sensing and modeling to monitor and understand harmful algal blooms. Application to Karaoun Reservoir (Lebanon) / Najwa Sharaf (2021)  

Public Titre : Using remote sensing and modeling to monitor and understand harmful algal blooms. Application to Karaoun Reservoir (Lebanon) Type de document : Thèse/HDR Auteurs : Najwa Sharaf, Auteur ; Brigitte Vinçon-Leite, Directeur de thèse ; Kamal Slim, Directeur de thèse Editeur : Paris : Ecole Nationale des Ponts et Chaussées ENPC Année de publication : 2021 Importance : 132 p. Format : 21 x 30 cm Note générale : bibliographie Thèse de Doctorat Sciences et Techniques de l’environnement Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] algue [Termes IGN] barrage [Termes IGN] chlorophylle [Termes IGN] distribution spatiale [Termes IGN] espèce exotique envahissante [Termes IGN] hydrodynamique [Termes IGN] image Landsat-8 [Termes IGN] image Sentinel-MSI [Termes IGN] lac [Termes IGN] Liban [Termes IGN] modélisation 3D [Termes IGN] plancton [Termes IGN] simulation hydrodynamique [Termes IGN] température de surface Index. décimale : THESE Thèses et HDR Résumé : (auteur) Reservoirs are strategic water resources in particular for drinking water and hydropower production. Nevertheless, their physical and biogeochemical processes have been long influenced by anthropogenic pressures. A complete and regular monitoring of reservoir water quality in the context of current climate change, eutrophication and higher water demand, has become crucial for optimal management strategies. Recent progress in the satellite remote sensing field made it possible to enhance data acquisition on a synoptic scale and to perform retrospective studies. Satellite data can complement measurements however over a limited depth of the water column. In addition, three-dimensional (3D) numerical models which integrate physical, chemical and biological processes can fill temporal gaps and extend the information into the vertical domain.In this context, this PhD thesis focuses on the combined use of techniques and data derived from field monitoring, satellite remote sensing and 3D modeling. The overreaching objective of this work is to propose a combined approach for surveying the water quality of medium-sized reservoirs (~ 14 km2).The study site is Karaoun Reservoir, Lebanon (semi-arid climate, surface 12 km2, capacity 110 hm3). It mainly serves for hydropower however with possibly a future drinking water production. It is eutrophic and has been experiencing regular events of toxic cyanobacterial blooms. The following methodological approach was adopted:i) In situ measurements were regularly collected from spring to fall for the calibration and the validation of remote sensing algorithms and of the model.ii) In order to calibrate and validate remote sensing algorithms, Landsat 8 and Sentinel-2 imagery were atmospherically corrected using a single-channel algorithm and the 6SV code respectively.a. Four algorithms from literature for deriving surface temperature were validated using Landsat 8 thermal data.b. A previously calibrated and validated Sentinel-2 algorithm was applied to retrieve chlorophyll-a concentrations.c. An empirical algorithm was calibrated and validated in order to retrieve transparency from Sentinel-2 data.iii) In order to conduct a retrospective analysis of surface temperature, the validated single channel algorithm was applied to a series of Landsat images from 1984 to 2018.iv) In order to reproduce the hydrodynamics and ecological processes, including cyanobacterial biomass in space and time, the Delft3D model was configured, calibrated and validated for summer and fall. The spatial distribution of surface temperature and chlorophyll-a concentrations from the satellite and the model were investigated.The results of this study revealed that, among the four tested algorithms, the single channel algorithm dependent on atmospheric water vapor content and lake water emissivity yielded the best estimations of surface temperature. Using this validated algorithm, the retrospective analysis of surface temperature did not reveal any warming trend over the 1984-2018 period at the study site. Compared to in situ profiles, the Delft3D model represented well the evolution of the water level fluctuations, and the time and vertical distribution of temperature and phytoplankton biomass. Satellite data and model simulations showed minor spatial heterogeneities of surface temperature ( Note de contenu : General introduction 1- State of the art 2- Materials and methods 3- Field data analysis 4- Lake surface temperature retrieval from Landsat-8 and retrospective analysis 5- Thermal regime of reservoirs: A satellite and 3D modeling approach 6- 3D ecological modeling at Karaoun Reservoir 7- Conclusions and perspectives Numéro de notice : 28499 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Thèse française Note de thèse : Thèse de Doctorat : Sciences et Techniques de l’environnement : Ponts ParisTech : 2021 Organisme de stage : Laboratoire Eau Environnement et Systèmes Urbains DOI : sans En ligne : https://pastel.archives-ouvertes.fr/tel-03404563 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99311

A novel algorithm to estimate phytoplankton carbon concentration in inland lakes using Sentinel-3 OLCI images / Heng Lyu in IEEE Transactions on geoscience and remote sensing, vol 58 n° 9 (September 2020)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 58 n° 9 (September 2020) . - pp 6512 - 6523 Titre : A novel algorithm to estimate phytoplankton carbon concentration in inland lakes using Sentinel-3 OLCI images Type de document : Article/Communication Auteurs : Heng Lyu, Auteur ; Zhiqian Yang, Auteur ; Lei Shi, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 6512 - 6523 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] analyse spatio-temporelle [Termes IGN] changement climatique [Termes IGN] Chine [Termes IGN] chlorophylle [Termes IGN] corrélation [Termes IGN] image Sentinel-OLCI [Termes IGN] lac [Termes IGN] plancton [Termes IGN] réflectance [Termes IGN] série temporelle [Termes IGN] teneur en carbone Résumé : (auteur) Phytoplankton carbon, an important biogeochemical and ecological parameter, plays a critical role in the carbon cycle and in global warming reduction. Estimation of phytoplankton carbon in inland waters on a large scale using remote sensing is useful for understanding, evaluating, and monitoring the carbon dynamics, and, in particular, for determining the spatial–temporal variation of primary production in inland waters. In a correlation analysis of the phytoplankton carbon concentration and water components, the result revealed no significant correlation between the chlorophyll-a concentration and phytoplankton carbon concentration in inland waters. However, the absorption peak height of particles at 675 nm, which is defined as the absorption at 675 nm subtracted by that at 660 nm, was found to be closely correlated with the phytoplankton carbon concentration. Thus, the absorption peak height of particles at 675 nm could be used as an indicator of the phytoplankton carbon concentration. A semianalytical method based on the remote-sensing reflectance in Sentinel-3 Ocean and Land Color Instrument (OLCI) bands 8, 9, and 17 was developed to derive the absorption peak of particles at a wavelength of 675 nm. Finally, an algorithm for estimating the phytoplankton carbon concentration in inland waters using OLCI bands 8, 9, and 17 was constructed. From 2013 to 2018, eight field campaigns were conducted in inland lakes in different seasons, and the optical properties, optically active water components, and phytoplankton carbon concentrations were obtained. An assessment of its accuracy using an independent data set demonstrated that the algorithm performance is acceptable (mean absolute percentage error, 48.6%, and root mean square error, 0.36 mg/L). As a demonstration, the algorithm was successfully applied to map the phytoplankton carbon concentration in Taihu Lake and Chaohu Lake, China, using OLCI images acquired on December 5, 2017, and August 5, 2018 and December 8, 2... Numéro de notice : A2020-531 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2020.2977080 Date de publication en ligne : 12/03/2020 En ligne : https://doi.org/10.1109/TGRS.2020.2977080 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95714 [article]

Télédétection radar SAR et photogrammétrie / Radouane Hout (2020)  

Permalink

Classification of glacial lakes using integrated approach of DFPS technique and gradient analysis using Sentinel 2A data / Prateek Verma in Geocarto international, vol 34 n° 10 ([15/07/2019])  

Permalink

Using Sentinel-1A DInSAR interferometry and Landsat 8 data for monitoring water level changes in two lakes in Crete, Greece / D.D. Alexakis in Geocarto international, vol 34 n° 7 ([01/06/2019])  

Permalink

Geospatial analyses of Earth observation (EO) data / Antonio Pepe (2019)  

Permalink

Historic reconstruction of reservoir topography using contour line interpolation and structure from motion photogrammetry / Ana Casado in International journal of geographical information science IJGIS, vol 32 n° 11-12 (November - December 2018)  

Permalink

Above-bottom biomass retrieval of aquatic plants with regression models and SfM data acquired by a UAV platform – A case study in Wild Duck Lake Wetland, Beijing, China / Ran Jing in ISPRS Journal of photogrammetry and remote sensing, vol 134 (December 2017)  

Permalink

Object-based water body extraction model using Sentinel-2 satellite imagery / Gordana Kaplan in European journal of remote sensing, vol 50 n° 1 (2017)  

Permalink

Geometric accuracy of topographical objects at Polish topographic maps / Radzym Lawniczack in Geodesy and cartography, vol 65 n° 1 (June 2016)  

Permalink

Recent variations of supraglacial lakes on the Baltoro Glacier in the central Karakoram Himalaya and its possible teleconnections with the pacific decadal oscillation / Bijeesh Kozhikkodan Veettil in Geocarto international, vol 31 n° 1 - 2 (January - February 2016)  

Permalink

Bathymetry of lake Constance – a high-resolution survey in a large, deep lake / Martin Wessels in ZFV, Zeitschrift für Geodäsie, Geoinformation und Landmanagement, Vol 140 n° 4 (Juli - August 2015)

Permalink