Centre dedocumentation
scientifique

Learning from multimodal and multitemporal earth observation data for building damage mapping / Bruno Adriano in ISPRS Journal of photogrammetry and remote sensing, vol 175 (May 2021)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 175 (May 2021) . - pp 132 - 143 Titre : Learning from multimodal and multitemporal earth observation data for building damage mapping Type de document : Article/Communication Auteurs : Bruno Adriano, Auteur ; Naoto Yokoya, Auteur ; Junshi Xia, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 132 - 143 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] cartographie des risques [Termes descripteurs IGN] catastrophe naturelle [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] cyclone [Termes descripteurs IGN] dommage [Termes descripteurs IGN] données multitemporelles [Termes descripteurs IGN] image à haute résolution [Termes descripteurs IGN] image optique [Termes descripteurs IGN] image radar moirée [Termes descripteurs IGN] observation de la Terre [Termes descripteurs IGN] segmentation sémantique [Termes descripteurs IGN] séisme [Termes descripteurs IGN] surveillance d'ouvrage [Termes descripteurs IGN] tsunami Résumé : (auteur) Earth observation (EO) technologies, such as optical imaging and synthetic aperture radar (SAR), provide excellent means to continuously monitor ever-growing urban environments. Notably, in the case of large-scale disasters (e.g., tsunamis and earthquakes), in which a response is highly time-critical, images from both data modalities can complement each other to accurately convey the full damage condition in the disaster aftermath. However, due to several factors, such as weather and satellite coverage, which data modality will be the first available for rapid disaster response efforts is often uncertain. Hence, novel methodologies that can utilize all accessible EO datasets are essential for disaster management. In this study, we developed a global multimodal and multitemporal dataset for building damage mapping. We included building damage characteristics from three disaster types, namely, earthquakes, tsunamis, and typhoons, and considered three building damage categories. The global dataset contains high-resolution (HR) optical imagery and high-to-moderate-resolution SAR data acquired before and after each disaster. Using this comprehensive dataset, we analyzed five data modality scenarios for damage mapping: single-mode (optical and SAR datasets), cross-modal (pre-disaster optical and post-disaster SAR datasets), and mode fusion scenarios. We defined a damage mapping framework for semantic segmentation of damaged buildings based on a deep convolutional neural network (CNN) algorithm. We also compared our approach to another state-of-the-art model for damage mapping. The results indicated that our dataset, together with a deep learning network, enabled acceptable predictions for all the data modality scenarios. We also found that the results from cross-modal mapping were comparable to the results obtained from a fusion sensor and optical mode analysis. Numéro de notice : A2021-272 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2021.02.016 date de publication en ligne : 17/03/2021 En ligne : https://doi.org/10.1016/j.isprsjprs.2021.02.016 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97343 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2021051	SL	Revue	Centre de documentation	Revues en salle	Disponible
081-2021052	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt
081-2021053	DEP-RECP	Revue	Saint-Mandé	Dépôt en unité	Exclu du prêt

Shoreline changes along Northern Ibaraki Coast after the great East Japan earthquake of 2011 / Quang Nguyen Hao in Remote sensing, vol 13 n° 7 (April 2021)  

Public [article]  inRemote sensing > vol 13 n° 7 (April 2021) . - n° 1399 Titre : Shoreline changes along Northern Ibaraki Coast after the great East Japan earthquake of 2011 Type de document : Article/Communication Auteurs : Quang Nguyen Hao, Auteur ; Satoshi Takewaka, Auteur Année de publication : 2021 Article en page(s) : n° 1399 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes descripteurs IGN] détection de changement [Termes descripteurs IGN] effondrement de terrain [Termes descripteurs IGN] image ALOS-AVNIR2 [Termes descripteurs IGN] image proche infrarouge [Termes descripteurs IGN] image Sentinel-MSI [Termes descripteurs IGN] image Terra-ASTER [Termes descripteurs IGN] Japon [Termes descripteurs IGN] Normalized Difference Water Index [Termes descripteurs IGN] séisme [Termes descripteurs IGN] surveillance du littoral [Termes descripteurs IGN] trait de côte Résumé : (auteur) In this study, we analyze the influence of the Great East Japan Earthquake, which occurred on 11 March 2011, on the shoreline of the northern Ibaraki Coast. After the earthquake, the area experienced subsidence of approximately 0.4 m. Shoreline changes at eight sandy beaches along the coast are estimated using various satellite images, including the ASTER (Advanced Spaceborne Thermal Emission and Reflection Radiometer), ALOS AVNIR-2 (Advanced Land Observing Satellite, Advanced Visible and Near-infrared Radiometer type 2), and Sentinel-2 (a multispectral sensor). Before the earthquake (for the period March 2001–January 2011), even though fluctuations in the shoreline position were observed, shorelines were quite stable, with the averaged change rates in the range of ±1.5 m/year. The shoreline suddenly retreated due to the earthquake by 20–40 m. Generally, the amount of retreat shows a strong correlation with the amount of land subsidence caused by the earthquake, and a moderate correlation with tsunami run-up height. The ground started to uplift gradually after the sudden subsidence, and shoreline positions advanced accordingly. The recovery speed of the beaches varied from +2.6 m/year to +6.6 m/year, depending on the beach conditions. Numéro de notice : A2021-351 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.3390/rs13071399 date de publication en ligne : 05/04/2021 En ligne : https://doi.org/10.3390/rs13071399 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97601 [article]

GIS-based spatial landslide distribution analysis of district Neelum, AJ&K, Pakistan / Shah Naseer in Natural Hazards, vol 106 n° 1 (March 2021)  

Public [article]  inNatural Hazards > vol 106 n° 1 (March 2021) . - pp 965 - 989 Titre : GIS-based spatial landslide distribution analysis of district Neelum, AJ&K, Pakistan Type de document : Article/Communication Auteurs : Shah Naseer, Auteur ; Tanveer Ul Haq, Auteur ; Abdullah Khan, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 965 - 989 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications SIG [Termes descripteurs IGN] ArcGIS [Termes descripteurs IGN] distribution spatiale [Termes descripteurs IGN] effondrement de terrain [Termes descripteurs IGN] fréquence [Termes descripteurs IGN] Google Earth [Termes descripteurs IGN] lit majeur [Termes descripteurs IGN] modèle numérique de surface [Termes descripteurs IGN] Pakistan [Termes descripteurs IGN] réseau hydrographique [Termes descripteurs IGN] réseau routier [Termes descripteurs IGN] sismicité Résumé : (auteur) The Landslide happens in mountainous regions due to the catastrophe of slope through intensive rain and seismicity. The Himalayas is one of the susceptible parts of the world in the perspective of slope catastrophe hazard; i.e., Mass Movement, especially Neelum valley is considerable destruction of community infrastructure, highway, and critically disturbed the tourism segment. Landslide is a common and recurrent phenomenon in the northern mountainous terrain of Pakistan such as District Neelum. After the 2005 Kashmir earthquake, the importance of landslide investigation is increasing. The purpose of this research is to establish a brief landslide inventory and to determine the relationship of landslides with causative factors by spatial distribution analysis. With the aid of Google Earth imageries and field visits, a total of 618 landslides were identified in the study area of 3621 km. These landslide localities compared with causative factors. Finally, distribution maps are generated and analyse their feature class through Digital Elevation Model and ArcGIS. Landslide intensity is calculated in terms of landslide concentration. Landslide concentration (LC) is significantly found very high in slope gradient less than 30 (1.21) and the first 100 m zone around the road network (15.06). A bit higher landslide frequency is noted in east orienting slopes. In the first 100 m, zone road network and drainage networks are 83.49% and 62.78% of the total landslide occurs having LC value 4.6, respectively. The analysis shows that the steep slopes, an area closer to the road network, drainage network, barren lands, and Quaternary alluvium of loose material are more susceptible to landslides. In addition, a landslide classification map is also prepared on the basis of field observation that shows that debris slides are more dominating. Numéro de notice : A2021-420 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.1007/s11069-021-04502-5 date de publication en ligne : 21/01/2021 En ligne : https://doi.org/10.1007/s11069-021-04502-5 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97770 [article]

Machine learning in ground motion prediction / Farid Khosravikia in Computers & geosciences, vol 148 (March 2021)  

Public [article]  inComputers & geosciences > vol 148 (March 2021) . - n° 104700 Titre : Machine learning in ground motion prediction Type de document : Article/Communication Auteurs : Farid Khosravikia, Auteur ; Patricia Clayton, Auteur Année de publication : 2021 Article en page(s) : n° 104700 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes descripteurs IGN] apprentissage automatique [Termes descripteurs IGN] classification par séparateurs à vaste marge [Termes descripteurs IGN] Etats-Unis [Termes descripteurs IGN] modèle de régression [Termes descripteurs IGN] modèle de simulation [Termes descripteurs IGN] mouvement de terrain [Termes descripteurs IGN] régression linéaire [Termes descripteurs IGN] réseau neuronal artificiel [Termes descripteurs IGN] sismicité Résumé : (auteur) This paper studies the advantages and disadvantages of different machine learning techniques in predicting ground-motion intensity measures given source characteristics, source-to-site distance, and local site conditions. Typically, linear regression-based models with predefined equations and coefficients are used in ground motion prediction. However, restrictions of the linear regression models may limit their capabilities in extracting complex nonlinear behaviors in the data. Therefore, the present paper comparatively investigates potential benefits from employing other machine learning techniques as statistical method in ground motion prediction such as Artificial Neural Network, Random Forest, and Support Vector Machine. This study quantifies event-to-event and site-to-site variability of the ground motions by implementing them as random effect terms to reduce the aleatory uncertainty. All the algorithms are trained using a selected database of 4528 ground-motions, including 376 seismic events with magnitude 3 to 5.8, recorded over the hypocentral distance range of 4–500 km in Oklahoma, Kansas, and Texas since 2005. The results indicate the algorithms satisfy some physically sound characteristics such as magnitude scaling distance dependency without requiring predefined equations or coefficients. Moreover, it is found that, when sufficient data is available, all the alternative algorithms tend to provide more accurate estimates compared to the conventional linear regression-based method, and particularly, Random Forest outperforms the other algorithms. However, the conventional method is a better tool when limited data is available. Numéro de notice : A2021-230 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE/POSITIONNEMENT Nature : Article DOI : 10.1016/j.cageo.2021.104700 date de publication en ligne : 21/01/2021 En ligne : https://doi.org/10.1016/j.cageo.2021.104700 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97220 [article]

Une nouvelle détermination de l'altitude de l'Everest par le Népal et la Chine / Gavin Schrock in XYZ, n° 166 (mars 2021)

Public [article]  inXYZ > n° 166 (mars 2021) . - pp 57 - 67 Titre : Une nouvelle détermination de l'altitude de l'Everest par le Népal et la Chine Type de document : Article/Communication Auteurs : Gavin Schrock, Auteur ; Bernard Flacelière, Auteur Année de publication : 2021 Article en page(s) : pp 57 - 67 Note générale : Bibliographie Cet article est issu des publications “Surveying the head of the Earth touching heaven” de Gavin Schrock et de “Two hours on the summit” de Khim Lal Gautam, avec l'autorisation de Geospatial Media and Communications et des auteurs. Langues : Français (fre) Descripteur : [Vedettes matières IGN] Géodésie physique [Termes descripteurs IGN] altitude normale [Termes descripteurs IGN] antenne GNSS [Termes descripteurs IGN] Chine [Termes descripteurs IGN] déformation horizontale de la croute terrestre [Termes descripteurs IGN] données GNSS [Termes descripteurs IGN] Everest [Termes descripteurs IGN] gravimétrie [Termes descripteurs IGN] Népal [Termes descripteurs IGN] précision altimétrique [Termes descripteurs IGN] séisme Résumé : (Auteur) After more than a decade of dispute and controversy, China and Nepal have finally agreed on the altitude of Mount Everest. The highest peak in the world, which lies on Nepal's border with Tibet in the Himalayas, stands at 8,848.86 meters, officials from the two countries announced on December 8, 2020. To relate this human and technique epic, open our columns to Gavin Schrock, consulting editor and land surveyor who interviewed several protagonists and to Khim Lal Gautam, leader of the Nepalese expedition in 2019. Bernard Flacelière, editor-in-chief of XYZ recalls here the forgotten mission of 1992. Numéro de notice : A2021-249 Affiliation des auteurs : non IGN Thématique : POSITIONNEMENT Nature : Article nature-HAL : ArtSansCL DOI : sans Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97330 [article]

Réservation

Réserver ce document

Exemplaires (2)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
112-2021011	SL	Revue	Centre de documentation	Revues en salle	Disponible
112-2021012	SL	Revue	Centre de documentation	Revues en salle	Disponible

A GIS-based system for spatial-temporal availability evaluation of the open spaces used as emergency shelters: The case of Victoria, British Columbia, Canada / Yibing Yao in ISPRS International journal of geo-information, vol 10 n° 2 (February 2021)  

Permalink

GIS-based multicriteria evaluation for earthquake response: a case study of expert opinion in Vancouver, Canada / Blake Byron Walker in Natural Hazards, Vol 105 n° 2 (January 2021)  

Permalink

Bayesian-deep-learning estimation of earthquake location from single-station observations / S. Mostafa Mousavi in IEEE Transactions on geoscience and remote sensing, vol 58 n° 11 (November 2020)  

Permalink

Geo-environment risk assessment in Zhengzhou City, China / Chuanming Ma in Geomatics, Natural Hazards and Risk, vol 11 n° 1 (2020)  

Permalink

Illuminating the spatio-temporal evolution of the 2008–2009 Qaidam earthquake sequence with the joint use of Insar time series and teleseismic data / Simon Daout in Remote sensing, vol 12 n° 17 (September 2020)  

Permalink

Conjugate ruptures and seismotectonic implications of the 2019 Mindanao earthquake sequence inferred from Sentinel-1 InSAR data / Bingquan Li in International journal of applied Earth observation and geoinformation, vol 90 (August 2020)  

Permalink

Automated 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)  

Permalink

Performance of real-time undifferenced precise positioning assisted by remote IGS multi-GNSS stations / Zhiqiang Liu in GPS solutions, vol 24 n° 2 (April 2020)  

Permalink

Bayesian inversion of convolved hidden Markov models with applications in reservoir prediction / Torstein Fjeldstad in IEEE Transactions on geoscience and remote sensing, vol 58 n° 3 (March 2020)  

Permalink

Poststack seismic data denoising based on 3-D convolutional neural network / Dawei Liu in IEEE Transactions on geoscience and remote sensing, vol 58 n° 3 (March 2020)  

Permalink