Centre dedocumentation
scientifique

A deep learning framework based on generative adversarial networks and vision transformer for complex wetland classification using limited training samples / Ali Jamali in International journal of applied Earth observation and geoinformation, vol 115 (December 2022)  

Public [article]  inInternational journal of applied Earth observation and geoinformation > vol 115 (December 2022) . - n° 103095 Titre : A deep learning framework based on generative adversarial networks and vision transformer for complex wetland classification using limited training samples Type de document : Article/Communication Auteurs : Ali Jamali, Auteur ; Masoud Mahdianpari, Auteur ; fariba Mohammadimanesh, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 103095 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] apprentissage profond [Termes IGN] Canada [Termes IGN] carte thématique [Termes IGN] données d'entrainement (apprentissage automatique) [Termes IGN] image Sentinel-MSI [Termes IGN] image Sentinel-SAR [Termes IGN] réseau antagoniste génératif [Termes IGN] zone humide Résumé : (auteur) Wetlands have long been recognized among the most critical ecosystems globally, yet their numbers quickly diminish due to human activities and climate change. Thus, large-scale wetland monitoring is essential to provide efficient spatial and temporal insights for resource management and conservation plans. However, the main challenge is the lack of enough reference data for accurate large-scale wetland mapping. As such, the main objective of this study was to investigate the efficient deep-learning models for generating high-resolution and temporally rich training datasets for wetland mapping. The Sentinel-1 and Sentinel-2 satellites from the European Copernicus program deliver radar and optical data at a high temporal and spatial resolution. These Earth observations provide a unique source of information for more precise wetland mapping from space. The second objective was to investigate the efficiency of vision transformers for complex landscape mapping. As such, we proposed a 3D Generative Adversarial Network (3D GAN) to best achieve these two objectives of synthesizing training data and a Vision Transformer model for large-scale wetland classification. The proposed approach was tested in three different study areas of Saint John, Sussex, and Fredericton, New Brunswick, Canada. The results showed the ability of the 3D GAN to stimulate and increase the number of training data and, as a result, increase the accuracy of wetland classification. The quantitative results also demonstrated the capability of jointly using data augmentation, 3D GAN, and Vision Transformer models with overall accuracy, average accuracy, and Kappa index of 75.61%, 73.4%, and 71.87%, respectively, using a disjoint data sampling strategy. Therefore, the proposed deep learning method opens a new window for large-scale remote sensing wetland classification. Numéro de notice : A2022-828 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1016/j.jag.2022.103095 Date de publication en ligne : 08/11/2022 En ligne : https://doi.org/10.1016/j.jag.2022.103095 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102012 [article]

Deep 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)  

Public [article]  inGeo-spatial Information Science > vol 25 n° 3 (October 2022) . - pp 383 - 398 Titre : Deep learning-based local climate zone classification using Sentinel-1 SAR and Sentinel-2 multispectral imagery Type de document : Article/Communication Auteurs : Lin Zhou, Auteur ; Zhenfeng Shao, Auteur ; Shugen Wang, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 383 - 398 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image mixte [Termes IGN] apprentissage profond [Termes IGN] carte climatique [Termes IGN] Chine [Termes IGN] filtre de déchatoiement [Termes IGN] ilot thermique urbain [Termes IGN] image Sentinel-MSI [Termes IGN] image Sentinel-SAR [Termes IGN] température de l'air Résumé : (auteur) As a newly developed classification system, the LCZ scheme provides a research framework for Urban Heat Island (UHI) studies and standardizes the worldwide urban temperature observations. With the growing popularity of deep learning, deep learning-based approaches have shown great potential in LCZ mapping. Three major cities in China are selected as the study areas. In this study, we design a deep convolutional neural network architecture, named Residual combined Squeeze-and-Excitation and Non-local Network (RSNNet), that consists of the Squeeze-and-Excitation (SE) block and non-local block to classify LCZ using freely available Sentinel-1 SAR and Sentinel-2 multispectral imagery. Overall Accuracy (OA) of 0.9202, 0.9524 and 0.9004 for three selected cities are obtained by applying RSNNet and training data of individual city, and OA of 0.9328 is obtained by training RSNNet with data from all three cities. RSNNet outperforms other popular Convolutional Neural Networks (CNNs) in terms of LCZ mapping accuracy. We further design a series of experiments to investigate the effect of different characteristics of Sentinel-1 SAR data on the performance of RSNNet in LCZ mapping. The results suggest that the combination of SAR and multispectral data can improve the accuracy of LCZ classification. The proposed RSNNet achieves an OA of 0.9425 when integrating the three decomposed components with Sentinel-2 multispectral images, 2.44% higher than using Sentinel-2 images alone. Numéro de notice : A2022-723 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1080/10095020.2022.2030654 Date de publication en ligne : 15/02/2022 En ligne : https://doi.org/10.1080/10095020.2022.2030654 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101666 [article]

DSNUNet: An improved forest change detection network by combining Sentinel-1 and Sentinel-2 images / Jiawei Jiang in Remote sensing, vol 14 n° 19 (October-1 2022)  

Public [article]  inRemote sensing > vol 14 n° 19 (October-1 2022) . - n° 5046 Titre : DSNUNet: An improved forest change detection network by combining Sentinel-1 and Sentinel-2 images Type de document : Article/Communication Auteurs : Jiawei Jiang, Auteur ; Yuanjun Xing, Auteur ; Wei Wei, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 5046 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image mixte [Termes IGN] apprentissage profond [Termes IGN] Chine [Termes IGN] détection de changement [Termes IGN] gestion forestière [Termes IGN] image radar moirée [Termes IGN] image Sentinel-MSI [Termes IGN] image Sentinel-SAR [Termes IGN] réseau neuronal siamois [Termes IGN] ressources forestières Résumé : (auteur) The use of remote sensing images to detect forest changes is of great significance for forest resource management. With the development and implementation of deep learning algorithms in change detection, a large number of models have been designed to detect changes in multi-phase remote sensing images. Although synthetic aperture radar (SAR) data have strong potential for application in forest change detection tasks, most existing deep learning-based models have been designed for optical imagery. Therefore, to effectively combine optical and SAR data in forest change detection, this paper proposes a double Siamese branch-based change detection network called DSNUNet. DSNUNet uses two sets of feature branches to extract features from dual-phase optical and SAR images and employs shared weights to combine features into groups. In the proposed DSNUNet, different feature extraction branch widths were used to compensate for a difference in the amount of information between optical and SAR images. The proposed DSNUNet was validated by experiments on the manually annotated forest change detection dataset. According to the obtained results, the proposed method outperformed other change detection methods, achieving an F1-score of 76.40%. In addition, different combinations of width between feature extraction branches were analyzed in this study. The results revealed an optimal performance of the model at initial channel numbers of the optical imaging branch and SAR image branch of 32 and 8, respectively. The prediction results demonstrated the effectiveness of the proposed method in accurately predicting forest changes and suppressing cloud interferences to some extent. Numéro de notice : A2022-772 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article DOI : 10.3390/rs14195046 Date de publication en ligne : 10/10/2022 En ligne : https://doi.org/10.3390/rs14195046 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101800 [article]

Towards a global seasonal and permanent reference water product from Sentinel-1/2 data for improved flood mapping / Sandro Martinis in Remote sensing of environment, vol 278 (September 2022)  

Public [article]  inRemote sensing of environment > vol 278 (September 2022) . - n° 113077 Titre : Towards a global seasonal and permanent reference water product from Sentinel-1/2 data for improved flood mapping Type de document : Article/Communication Auteurs : Sandro Martinis, Auteur ; Sandro Groth, Auteur ; Marc Wieland, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 113077 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image mixte [Termes IGN] Allemagne [Termes IGN] Australie [Termes IGN] carte thématique [Termes IGN] fusion d'images [Termes IGN] image radar moirée [Termes IGN] image Sentinel-MSI [Termes IGN] image Sentinel-SAR [Termes IGN] Inde [Termes IGN] inondation [Termes IGN] Mozambique [Termes IGN] prévention des risques [Termes IGN] série temporelle [Termes IGN] Soudan [Termes IGN] surveillance hydrologique [Termes IGN] variation saisonnière [Termes IGN] zone à risque Résumé : (auteur) Satellite-based flood mapping has become an important part of disaster response. In order to accurately distinguish flood inundation from normally present conditions, up-to-date, high-resolution information on the seasonal water cover is crucial. This information is usually neglected in disaster management, which may result in a non-reliable representation of the flood extent, mainly in regions with highly dynamic hydrological conditions. In this study, we present a fully automated method to generate a global reference water product specifically designed for the use in global flood mapping applications based on high resolution Earth Observation data. The proposed methodology combines existing processing pipelines for flood detection based on Sentinel-1/2 data and aggregates permanent as well as seasonal water masks over an adjustable reference time period. The water masks are primarily based on the analysis of Sentinel-2 data and are complemented by Sentinel-1-based information in optical data scarce regions. First results are demonstrated in five selected study areas (Australia, Germany, India, Mozambique, and Sudan), distributed across different climate zones and are systematically compared with external products. Further, the proposed product is exemplary applied to three real flood events in order to evaluate the impact of the used reference water mask on the derived flood extent. Results show, that it is possible to generate a consistent reference water product at 10–20 m spatial resolution, that is more suitable for the use in rapid disaster response than previous masks. The proposed multi-sensor approach is capable of producing reasonable results, even if only few or no information from optical data is available. Further it becomes clear, that the consideration of seasonality of water bodies, especially in regions with highly dynamic hydrological and climatic conditions, reduces potential over-estimation of the inundation extent and gives a more reliable picture on flood-affected areas. Numéro de notice : A2022-467 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1016/j.rse.2022.113077 Date de publication en ligne : 17/05/2022 En ligne : https://doi.org/10.1016/j.rse.2022.113077 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100801 [article]

Detection and characterization of slow-moving landslides in the 2017 Jiuzhaigou earthquake area by combining satellite SAR observations and airborne Lidar DSM / Jiehua Cai in Engineering Geology, vol 305 (August 2022)  

Public [article]  inEngineering Geology > vol 305 (August 2022) . - n° 106730 Titre : Detection and characterization of slow-moving landslides in the 2017 Jiuzhaigou earthquake area by combining satellite SAR observations and airborne Lidar DSM Type de document : Article/Communication Auteurs : Jiehua Cai, Auteur ; Lu Zhang, Auteur ; Jie Dong, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 106730 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] cartographie des risques [Termes IGN] déformation de surface [Termes IGN] données lidar [Termes IGN] données multisources [Termes IGN] effondrement de terrain [Termes IGN] géomorphologie [Termes IGN] image ALOS-PALSAR [Termes IGN] image optique [Termes IGN] image Sentinel-SAR [Termes IGN] interféromètrie par radar à antenne synthétique [Termes IGN] MNS lidar [Termes IGN] MNS SRTM [Termes IGN] séisme [Termes IGN] Setchouan (Chine) [Termes IGN] surveillance géologique Résumé : (auteur) On 8th August 2017, a catastrophic Ms. 7.0 earthquake with a focal depth of 20 km struck the Jiuzhaigou County in Sichuan Province, China. It exerted a strong influence on the slope stability within the surrounding areas and triggered numerous secondary geohazards including rockfalls and other co-seismic landslides, which incurred drastic surface changes, and thus can be easily identified from cloud-free high-resolution optical imagery. Most of such landslides became stabilized shortly after the earthquake while others moving very slowly for years. In contrast, some slopes were destabilized without significant surface change into slow-moving landslides, which may pose long-term potential threats to people's life and property. Therefore, it is crucial to accurately identify these slow-moving landslides and regularly monitor their post-seismic activity. In this study, we employed the synthetic aperture radar interferometry (InSAR) techniques to detect and monitor slow-moving landslides after the earthquake in the Jiuzhaigou area, and analyzed the impacts of the earthquake on these landslides through integration of multi-source data (InSAR, Lidar, optical image, and field survey). As a result, 16 slow-moving landslides were detected by InSAR in the Jiuzhaigou area, including several historical landslides. The results of time-series InSAR analyses enabled identification of three kinds of landslide evolution modes affected by the earthquake, i.e. acceleration of deformation of pre-existing landslides, reactivation of dormant landslide, and remobilization of earthquake-triggered landslide. Each mode is supported by detailed analyses of multi-source data. The results demonstrated that satellite InSAR combined with high-resolution Lidar and optical data can provide a cost-effective approach of post-earthquake geohazards detection and monitoring. Numéro de notice : A2022-469 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1016/j.enggeo.2022.106730 Date de publication en ligne : 28/05/2022 En ligne : https://doi.org/10.1016/j.enggeo.2022.106730 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100811 [article]

Estimating mangrove above-ground biomass at Maowei Sea, Beibu Gulf of China using machine learning algorithm with Sentinel-1 and Sentinel-2 data / Zhuomei Huang in Geocarto international, vol inconnu n° inconnu ([01/08/2022])  

Permalink

The influence of data density and integration on forest canopy cover mapping using Sentinel-1 and Sentinel-2 time series in Mediterranean oak forests / Vahid Nasiri in ISPRS International journal of geo-information, vol 11 n° 8 (August 2022)  

Permalink

Multiscale assimilation of Sentinel and Landsat data for soil moisture and Leaf Area Index predictions using an ensemble-Kalman-filter-based assimilation approach in a heterogeneous ecosystem / Nicola Montaldo in Remote sensing, vol 14 n° 14 (July-2 2022)  

Permalink

Quantifying the influence of plot-level uncertainty in above ground biomass up scaling using remote sensing data in central Indian dry deciduous forest / Thangavelu Mayamanikandan in Geocarto international, vol 37 n° 12 ([01/07/2022])  

Permalink

A dual-generator translation network fusing texture and structure features for SAR and optical image matching / Han Nie in Remote sensing, Vol 14 n° 12 (June-2 2022)  

Permalink

Combination of Sentinel-1 and Sentinel-2 data for tree species classification in a Central European biosphere reserve / Michael Lechner in Remote sensing, vol 14 n° 11 (June-1 2022)  

Permalink

Multi-modal temporal attention models for crop mapping from satellite time series / Vivien Sainte Fare Garnot in ISPRS Journal of photogrammetry and remote sensing, vol 187 (May 2022)  

Permalink

Flood mapping using multi-temporal Sentinel-1 SAR images: A case study—Inaouene watershed from Northeast of Morocco / Brahim Benzougagh in Iranian Journal of Science and Technology - Transactions of Civil Engineering, vol 46 n° 2 (April 2022)  

Permalink

Parcel-based summer maize mapping and phenology estimation combined using Sentinel-2 and time series Sentinel-1 data / Yanyan Wang in International journal of applied Earth observation and geoinformation, vol 108 (April 2022)  

Permalink

The integration of multi-source remotely sensed data with hierarchically based classification approaches in support of the classification of wetlands / Aaron Judah in Canadian journal of remote sensing, vol 48 n° 2 (April 2022)  

Permalink