Centre de documentation
scientifique

Large-scale burn severity mapping in multispectral imagery using deep semantic segmentation models / Xikun Hu in ISPRS Journal of photogrammetry and remote sensing, vol 196 (February 2023)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 196 (February 2023) . - pp 228 - 240 Titre : Large-scale burn severity mapping in multispectral imagery using deep semantic segmentation models Type de document : Article/Communication Auteurs : Xikun Hu, Auteur ; Puzhao Zhang, Auteur ; Yifang Ban, Auteur Année de publication : 2023 Article en page(s) : pp 228 - 240 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] carte thématique [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] dommage [Termes IGN] image Landsat-ETM+ [Termes IGN] image Landsat-OLI [Termes IGN] image Landsat-TM [Termes IGN] image multibande [Termes IGN] image Sentinel-MSI [Termes IGN] incendie de forêt [Termes IGN] jeu de données localisées [Termes IGN] segmentation sémantique [Termes IGN] surveillance forestière [Termes IGN] zone sinistrée Résumé : (auteur) Nowadays Earth observation satellites provide forest fire authorities and resource managers with spatial and comprehensive information for fire stabilization and recovery. Burn severity mapping is typically performed by classifying bi-temporal indices (e.g., dNBR, and RdNBR) using thresholds derived from parametric models incorporating field-based measurements. Analysts are currently expending considerable manual effort using prior knowledge and visual inspection to determine burn severity thresholds. In this study, we aim to employ highly automated approaches to provide spatially explicit damage level estimates. We first reorganize a large-scale Landsat-based bi-temporal burn severity assessment dataset (Landsat-BSA) by visual data cleaning based on annotated MTBS data (approximately 1000 major fire events in the United States). Then we apply state-of-the-art deep learning (DL) based methods to map burn severity based on the Landsat-BSA dataset. Experimental results emphasize that multi-class semantic segmentation algorithms can approximate the threshold-based techniques used extensively for burn severity classification. UNet-like models outperform other region-based CNN and Transformer-based models and achieve accurate pixel-wise classification results. Combined with the online hard example mining algorithm to reduce class imbalance issue, Attention UNet achieves the highest mIoU (0.78) and the highest Kappa coefficient close to 0.90. The bi-temporal inputs with ancillary spectral indices work much better than the uni-temporal multispectral inputs. The restructured dataset will be publicly available and create opportunities for further advances in remote sensing and wildfire communities. Numéro de notice : A2023-122 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2022.12.026 Date de publication en ligne : 11/01/2023 En ligne : https://doi.org/10.1016/j.isprsjprs.2022.12.026 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102498 [article]

Rapid mapping of seismic intensity assessment using ground motion data calculated from early aftershocks selected by GIS spatial analysis / Huaiqun Zhao in Geomatics, Natural Hazards and Risk, vol 14 n° 1 (2023)  

Public [article]  inGeomatics, Natural Hazards and Risk > vol 14 n° 1 (2023) . - pp 1 - 21 Titre : Rapid mapping of seismic intensity assessment using ground motion data calculated from early aftershocks selected by GIS spatial analysis Type de document : Article/Communication Auteurs : Huaiqun Zhao, Auteur ; Yijiao Jia, Auteur ; Wenkai Chen, Auteur ; et al., Auteur Année de publication : 2023 Article en page(s) : pp 1 - 21 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications SIG [Termes IGN] cartographie thématique [Termes IGN] Chine [Termes IGN] distribution spatiale [Termes IGN] dommage [Termes IGN] régression [Termes IGN] sismologie [Termes IGN] zone sinistrée [Termes IGN] zone tampon Résumé : (auteur) Following a major earthquake, disaster information services must deliver accurate damage assessment results during the emergency ‘black box’ phase when data is scarce. Seismic intensity maps contain crucial information for determining the damage in the affected area. For earthquakes with Mw between 5.5 and 7, this study proposes using GIS analysis to mine aftershock events in early aftershock sequences that are closely related to the mainshock fault, and then using these events to generate seismic intensity assessment maps. Regression curves were first obtained using a nonparametric method (rLowess) to analyse the geographical coordinates of early aftershocks. Then, a buffer of 1 or 1.5 km radius was made for the curve, and the aftershocks in the buffer were used to calculate the predicted peak ground velocity (PGV) values over a specific km-grid range. Finally, rapid mapping of seismic intensity was assessed based on the intensity scale. This straightforward and repeatable method employs seismic station data obtained shortly after the mainshock. The assessed seismic intensity accurately reflects the location and extent of the hardest hit areas and can be cross-referenced with geophysical results to accurately assess the damage in the affected areas. Numéro de notice : A2023-035 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE/POSITIONNEMENT Nature : Article DOI : 10.1080/19475705.2022.2160663 Date de publication en ligne : 02/01/2023 En ligne : https://doi.org/10.1080/19475705.2022.2160663 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102304 [article]

Building a small fire database for Sub-Saharan Africa from Sentinel-2 high-resolution images / Emilio Chuvieco in Science of the total environment, vol 845 (November 1 2022)  

Public [article]  inScience of the total environment > vol 845 (November 1 2022) . - n° 157139 Titre : Building a small fire database for Sub-Saharan Africa from Sentinel-2 high-resolution images Type de document : Article/Communication Auteurs : Emilio Chuvieco, Auteur ; Ekhi Roteta, Auteur ; Matteo Sali, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 157139 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] Afrique subsaharienne [Termes IGN] base de données localisées [Termes IGN] image Sentinel-MSI [Termes IGN] zone sinistrée Résumé : (auteur) Coarse resolution sensors are not very sensitive at detecting small fire patches, making current estimations of global burned areas (BA) very conservative. Using medium or high-resolution sensors to generate BA products becomes then a priority, particularly in areas where fires tend to be small and frequent. Building on previous work that developed a small fire dataset (SFD) for Sub-Saharan Africa for 2016, this paper presents a new version of the dataset for 2019 using the two Sentinel-2 satellites (A and B) and VIIRS active fires. Total estimated BA was 4.8 Mkm2. This value was much higher than estimations from two global, coarser-spatial resolution BA products based on MODIS data for the same area and period: 80 % greater than estimates from FireCCI51 (based on MODIS 250 m bands) and 120 % larger than MCD64A1 (based on MODIS 500 m bands). The main differences were observed in those months with higher fire occurrence (November to January for the Northern Hemisphere regions and June to September for the Southern Hemisphere ones). Accuracy assessment of the SFD product was based on a novel sampling strategy designed to obtain independent fire reference perimeters. Validation results showed remarkable high accuracy values comparing to existing global BA products. Overall omission errors (OE) were estimated as 8.5 %, commission errors (CE) as 15.0 %, with a Dice Coefficient of 87.7 %. All of these estimations implied significant improvements over the global, coarser spatial resolution BA products (OE > 50 % and CE > 20 % for the same area and period), as well as over the previous SFD product for 2016 of the same area, generated from a single Sentinel-2 satellite and MODIS active fires (OE = 26.5 % and CE = 19.3 %). Temporal accuracies greatly increased as well with the new product, with 92.5 % of fires detected within the first 10 days of occurrence. Numéro de notice : A2022-570 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1016/j.scitotenv.2022.157139 Date de publication en ligne : 13/07/2022 En ligne : https://doi.org/10.1016/j.scitotenv.2022.157139 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101279 [article]

Analyzing spatio-temporal pattern of the forest fire burnt area in Uttarakhand using Sentinel-2 data / Shailja Mamgain in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol V-3-2022 (2022 edition)  

Public [article]  inISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences > vol V-3-2022 (2022 edition) . - pp 533 - 539 Titre : Analyzing spatio-temporal pattern of the forest fire burnt area in Uttarakhand using Sentinel-2 data Type de document : Article/Communication Auteurs : Shailja Mamgain, Auteur ; Harish Chandra Karnatak, Auteur ; Arijit Roy, Auteur ; Prakash Chauhan, Auteur Année de publication : 2022 Article en page(s) : pp 533 - 539 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes IGN] analyse spatio-temporelle [Termes IGN] image Sentinel-MSI [Termes IGN] incendie de forêt [Termes IGN] indice de végétation [Termes IGN] régression multiple [Termes IGN] Uttarakhand (Inde ; état) [Termes IGN] zone sinistrée Résumé : (auteur) Forest fire burnt area estimation using Normalized Burn Ratio at regional level helps in understanding the pattern of the frequency and severity of forest fires. In this study, burnt area is estimated for all the thirteen districts of Indian state Uttarakhand for last six years from 2016 to 2021 using Sentinel 2A and 2B datasets. The spatial and temporal pattern of the burnt area was analyzed by incorporating different parameters such as meteorological parameters like land surface temperature, rainfall; edaphic parameter like surface soil moisture and vegetation parameters like Normalized Difference Vegetation Index & Enhanced Vegetation Index. The estimated burnt area was statistically analyzed with respect to the parameters stated and the relationship among them was quantified. It was found that burnt area is positively correlated with the land surface temperature, while it showed negative correlation with the pre-fire precipitation, pre-fire NDVI & EVI and the surface soil moisture for 11 out of 13 districts. The district-wise forest fire burnt area assessment and analysis of its spatio-temporal pattern can be used in the preparedness and mitigation planning to prevent drastic ecological impacts of forest fires on the landscape. Numéro de notice : A2022-443 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article DOI : 10.5194/isprs-annals-V-3-2022-533-2022 Date de publication en ligne : 17/05/2022 En ligne : https://doi.org/10.5194/isprs-annals-V-3-2022-533-2022 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100778 [article]

Mapping burn severity in the western Italian Alps through phenologically coherent reflectance composites derived from Sentinel-2 imagery / Donato Morresi in Remote sensing of environment, vol 269 (February 2022)  

Public [article]  inRemote sensing of environment > vol 269 (February 2022) . - n° 112800 Titre : Mapping burn severity in the western Italian Alps through phenologically coherent reflectance composites derived from Sentinel-2 imagery Type de document : Article/Communication Auteurs : Donato Morresi, Auteur ; Raffaella Marzano, Auteur ; Emanuele Lingua, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 112800 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] carte de la végétation [Termes IGN] cartographie des risques [Termes IGN] détection de changement [Termes IGN] forêt alpestre [Termes IGN] image multibande [Termes IGN] image Sentinel-MSI [Termes IGN] incendie de forêt [Termes IGN] phénologie [Termes IGN] Piémont (Italie) [Termes IGN] réflectance spectrale [Termes IGN] risque naturel [Termes IGN] variation saisonnière [Termes IGN] zone sinistrée Résumé : (auteur) Deriving burn severity from multispectral satellite data is a widely adopted approach to infer the degree of environmental change caused by fire. Burn severity maps obtained by thresholding bi-temporal indices based on pre- and post-fire Normalized Burn Ratio (NBR) can vary substantially depending on temporal constraints such as matched acquisition and optimal seasonal timing. Satisfying temporal requirements is crucial to effectively disentangle fire and non-fire induced spectral changes and can be particularly challenging when only a few cloud-free images are available. Our study focuses on 10 wildfires that occurred in mountainous areas of the Piedmont Region (Italy) during autumn 2017 following a severe and prolonged drought period. Our objectives were to: (i) generate reflectance composites using Sentinel-2 imagery that were optimised for seasonal timing by embedding spatial patterns of long-term land surface phenology (LSP); (ii) produce and validate burn severity maps based on the modelled relationship between bi-temporal indices and field data; (iii) compare burn severity maps obtained using either a pair of cloud-free Sentinel-2 images, i.e. paired images, or reflectance composites. We proposed a pixel-based compositing algorithm coupling the weighted geometric median and thematic spatial information, e.g. long-term LSP metrics derived from the MODIS Collection 6 Land Cover Dynamics Product, to rank all the clear observations available in the growing season. Composite Burn Index data and bi-temporal indices exhibited a strong nonlinear relationship (R2 > 0.85) using paired images or reflectance composites. Burn severity maps attained overall classification accuracy ranging from 76.9% to 83.7% (Kappa between 0.61 and 0.72) and the Relative differenced NBR (RdNBR) achieved the best results compared to other bi-temporal indices (differenced NBR and Relativized Burn Ratio). Improvements in overall classification accuracy offered by the calibration of bi-temporal indices with the dNBR offset were limited to burn severity maps derived from paired images. Reflectance composites provided the highest overall classification accuracy and differences with paired images were significant using uncalibrated bi-temporal indices (4.4% to 5.2%) while they decreased (2.8% to 3.2%) when we calibrated bi-temporal indices derived from paired images. The extent of the high severity category increased by ~19% in burn severity maps derived from reflectance composites (uncalibrated RdNBR) compared to those from paired images (calibrated RdNBR). The reduced contrast between healthy and burnt conditions associated with suboptimal seasonal timing caused an underestimation of burnt areas. By embedding spatial patterns of long-term LSP metrics, our approach provided consistent reflectance composites targeted at a specific phenological stage and minimising non-fire induced inter-annual changes. Being independent from the multispectral dataset employed, the proposed pixel-based compositing approach offers new opportunities for operational change detection applications in geographic areas characterised by persistent cloud cover. Numéro de notice : A2022-095 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1016/j.rse.2021.112800 Date de publication en ligne : 22/11/2021 En ligne : https://doi.org/10.1016/j.rse.2021.112800 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99534 [article]

Annotation sémantique pour la géolocalisation d'entités spatiales dans des tweets / Gaëtan Caillaut (2022)  

Permalink

Mapping burned areas and land-uses in Kangaroo Island using an object-based image classification framework and Landsat 8 Imagery from Google Earth Engine / Jiyu Liu in Geomatics, Natural Hazards and Risk, vol 13 (2022)  

Permalink

Répartitions spatiale et temporelle des feux à Madagascar / Solofo Rakotondraompiana in Revue Française de Photogrammétrie et de Télédétection, n° 223 (mars - décembre 2021)  

Permalink

Deep learning for wildfire progression monitoring using SAR and optical satellite image time series / Puzhao Zhang (2021)  

Permalink

Comparison of tree-based classification algorithms in mapping burned forest areas / Dilek Kucuk Matci in Geodetski vestnik, vol 64 n° 3 (September - November 2020)  

Permalink

Incorporating Sentinel-1 SAR imagery with the MODIS MCD64A1 burned area product to improve burn date estimates and reduce burn date uncertainty in wildland fire mapping / Kristofer Lasko in Geocarto international, vol 35 n° 6 ([01/05/2020])  

Permalink

Shrub biomass estimates in former burnt areas using Sentinel 2 images processing and classification / Jose Aranha in Forests, vol 11 n° 5 (May 2020)  

Permalink

Assessing the shape accuracy of coarse resolution burned area identifications / Michael L. Humber in IEEE Transactions on geoscience and remote sensing, vol 58 n° 3 (March 2020)  

Permalink

The potentiality of Sentinel-2 to assess the effect of fire events on Mediterranean mountain vegetation / Walter de Simone in Plant sociology, vol 57 n° 1 ([01/02/2020])  

Permalink

A model for phased evacuations for disasters with spatio-temporal randomness / Menghui Li in International journal of geographical information science IJGIS, Vol 33 n° 5-6 (May - June 2019)  

Permalink