Centre dedocumentation
scientifique

Automatic extraction of damaged houses by earthquake based on improved YOLOv5: A case study in Yangbi / Yafei Jing in Remote sensing, vol 14 n° 2 (January 2 2022)  

Public [article]  inRemote sensing > vol 14 n° 2 (January 2 2022) . - n° 382 Titre : Automatic extraction of damaged houses by earthquake based on improved YOLOv5: A case study in Yangbi Type de document : Article/Communication Auteurs : Yafei Jing, Auteur ; Yuhuan Ren, Auteur ; Yalan Liu, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 382 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] apprentissage profond [Termes IGN] détection d'objet [Termes IGN] détection de cible [Termes IGN] dommage matériel [Termes IGN] extraction automatique [Termes IGN] image captée par drone [Termes IGN] orthoimage [Termes IGN] séisme [Termes IGN] Yunnan (Chine) Résumé : (auteur) Efficiently and automatically acquiring information on earthquake damage through remote sensing has posed great challenges because the classical methods of detecting houses damaged by destructive earthquakes are often both time consuming and low in accuracy. A series of deep-learning-based techniques have been developed and recent studies have demonstrated their high intelligence for automatic target extraction for natural and remote sensing images. For the detection of small artificial targets, current studies show that You Only Look Once (YOLO) has a good performance in aerial and Unmanned Aerial Vehicle (UAV) images. However, less work has been conducted on the extraction of damaged houses. In this study, we propose a YOLOv5s-ViT-BiFPN-based neural network for the detection of rural houses. Specifically, to enhance the feature information of damaged houses from the global information of the feature map, we introduce the Vision Transformer into the feature extraction network. Furthermore, regarding the scale differences for damaged houses in UAV images due to the changes in flying height, we apply the Bi-Directional Feature Pyramid Network (BiFPN) for multi-scale feature fusion to aggregate features with different resolutions and test the model. We took the 2021 Yangbi earthquake with a surface wave magnitude (Ms) of 6.4 in Yunan, China, as an example; the results show that the proposed model presents a better performance, with the average precision (AP) being increased by 9.31% and 1.23% compared to YOLOv3 and YOLOv5s, respectively, and a detection speed of 80 FPS, which is 2.96 times faster than YOLOv3. In addition, the transferability test for five other areas showed that the average accuracy was 91.23% and the total processing time was 4 min, while 100 min were needed for professional visual interpreters. The experimental results demonstrate that the YOLOv5s-ViT-BiFPN model can automatically detect damaged rural houses due to destructive earthquakes in UAV images with a good performance in terms of accuracy and timeliness, as well as being robust and transferable. Numéro de notice : A2022-104 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.3390/rs14020382 Date de publication en ligne : 14/01/2022 En ligne : https://doi.org/10.3390/rs14020382 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99577 [article]

Co-seismic ionospheric disturbances following the 2016 West Sumatra and 2018 Palu earthquakes from GPS and GLONASS measurements / Mokhamad Nur Cahyadi in Remote sensing, vol 14 n° 2 (January 2 2022)  

Public [article]  inRemote sensing > vol 14 n° 2 (January 2 2022) . - n° 401 Titre : Co-seismic ionospheric disturbances following the 2016 West Sumatra and 2018 Palu earthquakes from GPS and GLONASS measurements Type de document : Article/Communication Auteurs : Mokhamad Nur Cahyadi, Auteur ; Buldan Muslim, Auteur ; Danar Guruh Pratomo, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 401 Note générale : biliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géodésie spatiale [Termes IGN] déformation verticale de la croute terrestre [Termes IGN] diffusion de Rayleigh [Termes IGN] données GLONASS [Termes IGN] données GNSS [Termes IGN] Indonésie [Termes IGN] onde acoustique [Termes IGN] perturbation ionosphérique [Termes IGN] propagation ionosphérique [Termes IGN] séisme [Termes IGN] Sumatra [Termes IGN] teneur totale en électrons [Termes IGN] tsunami Résumé : (auteur) The study of ionospheric disturbances associated with the two large strike-slip earthquakes in Indonesia was investigated, which are West Sumatra on 2 March 2016 (Mw = 7.8), and Palu on 28 September 2018 (Mw = 7.5). The anomalies were observed by measuring co-seismic ionospheric disturbances (CIDs) using the Global Navigation Satellite System (GNSS). The results show positive and negative CIDs polarization changes for the 2016 West Sumatra earthquake, depending on the position of the satellite line-of-sight, while the 2018 Palu earthquake shows negative changes only due to differences in co-seismic vertical crustal displacement. The 2016 West Sumatra earthquake caused uplift and subsidence, while the 2018 Palu earthquake was dominated by subsidence. TEC anomalies occurred about 10 to 15 min after the two earthquakes with amplitude of 2.9 TECU and 0.4 TECU, respectively. The TEC anomaly amplitude was also affected by the magnitude of the earthquake moment. The disturbance signal propagated with a velocity of ~1–1.72 km s−1 for the 2016 West Sumatra earthquake and ~0.97–1.08 km s−1 for the 2018 Palu mainshock earthquake, which are consistent with acoustic waves. The wave also caused an oscillation signal of ∼4 mHz, and their azimuthal asymmetry of propagation confirmed the phenomena in the Southern Hemisphere. The CID signal could be identified at a distance of around 400–1500 km from the epicenter in the southwestern direction. Numéro de notice : A2022-103 Affiliation des auteurs : non IGN Thématique : POSITIONNEMENT Nature : Article DOI : 10.3390/rs14020401 Date de publication en ligne : 16/01/2022 En ligne : https://doi.org/10.3390/rs14020401 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99571 [article]

A rapid assessment method for earthquake-induced landslide casualties based on GIS and logistic regression model / Yuqian Dai in Geomatics, Natural Hazards and Risk, vol 13 n° 1 (2022)  

Public [article]  inGeomatics, Natural Hazards and Risk > vol 13 n° 1 (2022) . - pp 222 - 248 Titre : A rapid assessment method for earthquake-induced landslide casualties based on GIS and logistic regression model Type de document : Article/Communication Auteurs : Yuqian Dai, Auteur ; Xianfu Bai, Auteur ; Gaozhong Nie, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 222 - 248 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes IGN] Chine [Termes IGN] classification par maximum de vraisemblance [Termes IGN] effondrement de terrain [Termes IGN] modèle de régression [Termes IGN] régression logistique [Termes IGN] secours d'urgence [Termes IGN] séisme [Termes IGN] système d'information géographique Résumé : (auteur) The accuracy of rapid earthquake assessment and the emergency assessment system for earthquake-induced damages could be substantially enhanced if the casualties triggered by earthquake-induced geological disasters, such as landslides, are subjected to comprehensive scientific evaluation. However, no credible solution for this purpose has been formulated yet. This study suggests a three-step rapid assessment method designed for earthquake-induced landslide casualties based on the GIS and an associated logistic regression model, as follows: (1) Partition of the region to be evaluated as a 1 km × 1 km grid in the GIS, with assignment of a certain amount of population to each of the grid cells as its population attribute. (2) Calculation of the death rate for each grid cell based upon its earthquake-induced landslide susceptibility attribute using the logistic regression model. (3) The earthquake-induced landslide casualties are first determined for each of the kilometer grid cells, and then for the entire region under evaluation. The proposed method was implemented to test the assessment of earthquake-induced landslide casualties in three earthquake-stricken regions. The study reveals the feasibility of the extensibility and applicability of the proposed rapid assessment method for earthquake-induced landslide casualties, and its suitability for similar assessments and calculations of other regions. Numéro de notice : A2022-036 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.1080/19475705.2021.2017022 Date de publication en ligne : 29/12/2021 En ligne : https://doi.org/10.1080/19475705.2021.2017022 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99367 [article]

Joint inversion of ground gravity data and satellite gravity gradients between Nepal and Bhutan: New insights on structural and seismic segmentation of the Himalayan arc / Rodolphe Cattin in Physics and chemistry of the Earth (A/B/C), vol 123 (October 2021)  

Public [article]  inPhysics and chemistry of the Earth (A/B/C) > vol 123 (October 2021) . - n° 103002 Titre : Joint inversion of ground gravity data and satellite gravity gradients between Nepal and Bhutan: New insights on structural and seismic segmentation of the Himalayan arc Type de document : Article/Communication Auteurs : Rodolphe Cattin, Auteur ; Théo Berthet, Auteur ; György Hetényi, Auteur ; Anita Thea Saraswati, Auteur ; Isabelle Panet , Auteur ; Stéphane Mazzotti, Auteur ; Cécilia Cadio, Auteur ; Matthieu Ferry, Auteur Année de publication : 2021 Projets : TOPO-Extreme / Cattin, Rodolphe, TOSCA / Cattin, Rodolphe Article en page(s) : n° 103002 Note générale : bibliographie This work was supported by grants from the Agence Nationale de la Recherche ANR-18-CE01-0017 and CNES TOSCA, as well as the Swiss National Science Foundation grant PP00P2_157627 (project OROG3NY). Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de géodésie spatiale [Termes IGN] Bhoutan [Termes IGN] gradient de gravitation [Termes IGN] gravimétrie spatiale [Termes IGN] Himalaya [Termes IGN] levé gravimétrique [Termes IGN] Népal [Termes IGN] séisme Résumé : (auteur) Along-strike variation in the geometry of lithospheric structures is a key control parameter for the occurrence and propagation of major interplate earthquakes in subduction and collision zones. The lateral segmentation of the Himalayan arc is now well-established from various observations, including topography, gravity anomalies, exhumation rates, and present-day seismic activity. Good knowledge of the main geometric features of these segments and their boundaries is thus the next step to improve seismic hazard assessment in this area. Following recent studies, we focus our approach on the transition zone between Nepal and Bhutan where both M > 8 earthquakes and changes in the geometry of the Indian plate have been documented. Ground gravity data sets are combined with satellite gravity gradients provided by the GOCE mission (Gravity Field and Steady-State Ocean Circulation Explorer) in a joint inversion to assess the location and the geometry of this transition. We obtain a ca. 10 km wide transition zone located at the western border of Bhutan that is aligned with the Madhupur fault in the foreland and coincides with the Dhubri–Chungthang fault zone and the Yadong-Gulu rift in Himalaya and southern Tibet, respectively. This sharp segment boundary at depth can act as a barrier to earthquake rupture propagation. It can possibly restrict the size of large earthquakes and thus reduce the occurrence probability of M > 9 earthquakes along the Main Himalayan Thrust. Numéro de notice : A2021-500 Affiliation des auteurs : UMR IPGP-Géod+Ext (2020- ) Thématique : POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.pce.2021.103002 En ligne : https://doi.org/10.1016/j.pce.2021.103002 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98261 [article]

Disaster intensity-based selection of training samples for remote sensing building damage classification / Luis Moya in IEEE Transactions on geoscience and remote sensing, vol 59 n° 10 (October 2021)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 59 n° 10 (October 2021) . - pp 8288 - 8304 Titre : Disaster intensity-based selection of training samples for remote sensing building damage classification Type de document : Article/Communication Auteurs : Luis Moya, Auteur ; Christian Geiss, Auteur ; Masakazu Hashimoto, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 8288 - 8304 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] apprentissage automatique [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] déformation d'édifice [Termes IGN] détection de changement [Termes IGN] détection du bâti [Termes IGN] dommage matériel [Termes IGN] données de terrain [Termes IGN] échantillonnage de données [Termes IGN] image optique [Termes IGN] inondation [Termes IGN] séisme Résumé : (auteur) Previous applications of machine learning in remote sensing for the identification of damaged buildings in the aftermath of a large-scale disaster have been successful. However, standard methods do not consider the complexity and costs of compiling a training data set after a large-scale disaster. In this article, we study disaster events in which the intensity can be modeled via numerical simulation and/or instrumentation. For such cases, two fully automatic procedures for the detection of severely damaged buildings are introduced. The fundamental assumption is that samples that are located in areas with low disaster intensity mainly represent nondamaged buildings. Furthermore, areas with moderate to strong disaster intensities likely contain damaged and nondamaged buildings. Under this assumption, a procedure that is based on the automatic selection of training samples for learning and calibrating the standard support vector machine classifier is utilized. The second procedure is based on the use of two regularization parameters to define the support vectors. These frameworks avoid the collection of labeled building samples via field surveys and/or visual inspection of optical images, which requires a significant amount of time. The performance of the proposed method is evaluated via application to three real cases: the 2011 Tohoku-Oki earthquake–tsunami, the 2016 Kumamoto earthquake, and the 2018 Okayama floods. The resulted accuracy ranges between 0.85 and 0.89, and thus, it shows that the result can be used for the rapid allocation of affected buildings. Numéro de notice : A2021-711 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2020.3046004 Date de publication en ligne : 13/01/2021 En ligne : https://doi.org/10.1109/TGRS.2020.3046004 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98615 [article]

Estimation of surface deformation due to Pasni earthquake using RADAR interferometry / Muhammad Ali in Geocarto international, vol 36 n° 14 ([01/08/2021])  

Permalink

Investigating the application of artificial intelligence for earthquake prediction in Terengganu / Suzlyana Marhain in Natural Hazards, vol 108 n° 1 (August 2021)  

Permalink

Orogenic collapse and stress adjustments revealed by an intense seismic swarm following the 2015 Gorkha earthquake in Nepal / Lok Bijaya Adhikari in Frontiers in Earth Science, vol 9 (2021)  

Permalink

Three-dimensional reconstruction of seismo-traveling ionospheric disturbances after March 11, 2011, Japan Tohoku earthquake / Changzhi Zhai in Journal of geodesy, vol 95 n° 7 (July 2021)  

Permalink

Anomalous variations of air temperature prior to earthquakes / Irfan Mahmood in Geocarto international, vol 36 n° 12 ([01/07/2021])  

Permalink

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)  

Permalink

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)  

Permalink

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

Permalink

Earthquake sensitivity to tides and seasons: theoretical studies / François Pétrélis in Journal of Statistical Mechanics: Theory and Experiment, vol 2021 n° 2 (February 2021)  

Permalink

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