Centre dedocumentation
scientifique

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]

Forest tree species classification based on Sentinel-2 images and auxiliary data / Haotian You in Forests, vol 13 n° 9 (september 2022)  

Public [article]  inForests > vol 13 n° 9 (september 2022) . - n° 1416 Titre : Forest tree species classification based on Sentinel-2 images and auxiliary data Type de document : Article/Communication Auteurs : Haotian You, Auteur ; Yuanwei Huang, Auteur ; Zhigang Qin, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 1416 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] classification et arbre de régression [Termes IGN] classification par forêts d'arbres décisionnels [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] dioxyde d'azote [Termes IGN] distribution spatiale [Termes IGN] Extreme Gradient Machine [Termes IGN] image Sentinel-MSI [Termes IGN] phénologie [Termes IGN] précipitation [Termes IGN] réflectance spectrale [Termes IGN] température de l'air [Termes IGN] texture du sol [Termes IGN] topographie locale Résumé : (auteur) Most research on forest tree species classification based on optical image data uses information such as spectral reflectance, vegetation index, texture, and phenology data. However, owing to the limited spectral resolution of multispectral images and the high cost of hyperspectral data, there is room for improvement in the classification of tree species in large areas based on optical images. The combined application of multispectral images and other auxiliary data can provide a new method for improving tree species classification accuracy. Hence, Sentinel-2 images were used to extract spectral reflectance, spectral index, texture, and phenological information. Data for topography, precipitation, air temperature, ultraviolet aerosol index, NO2 concentration, and other variables were included as auxiliary data. Models for forest tree species classification were constructed through feature combination and feature optimization using the random forest (RF), gradient tree boost (GTB), support vector machine (SVM), and classification and regression tree (CART) algorithms. The classification results of 16 feature combinations with the 4 classification methods were compared, and the contributions of different features to the classification models of forest tree species were evaluated. Finally, the optimal classification model was selected to identify the spatial distribution of forest tree species in the study area. The model based on feature optimization gave the best results among the 16 feature combination models. The overall accuracy and kappa coefficient were increased by 18% and 0.21, respectively, compared with the spectral classification model, and by 17% and 0.20, respectively, compared with the spectral and spectral index classification model. By analyzing the feature optimization model, it was found that terrain, ultraviolet aerosol index, and phenological information ranked as the top three features in terms of importance. Although the importance of spectral reflectance and spectral index features was lower, the number of feature variables accounted for a large proportion of the total. The importance of commonly used texture features was limited, and these features were not present in the feature optimization model. The RF algorithm had the highest classification accuracy, with an overall accuracy of 82.69% and a kappa coefficient of 0.80, among the four classification algorithms. The results of GTB were close to those of RF, and the difference in overall classification accuracy was only 0.14%. However, the results of the SVM and CART algorithms were relatively weaker, with overall classification accuracies of about 70%. It can be concluded that the combined application of Sentinel-2 images and auxiliary data can improve forest tree species classification accuracy. The model based on feature optimization achieved the highest classification accuracy among the 16 feature combination models. The spectral reflectance and spectral index data extracted from optical images are useful for tree species classification, but the effect of texture features was very limited. Auxiliary data, such as topographic features, ultraviolet aerosol index, phenological features, NO2 concentration features, topographic diversity features, precipitation features, temperature features, and multi-scale topographic location index data, can effectively improve forest tree species classification accuracy. The RF algorithm had the highest accuracy, and it can be used for tree species classification space distribution identification. The combined application of Sentinel-2 images and auxiliary data can improve classification accuracy, but the highest accuracy of the model was only 82.69%, which leaves room for improvement. Thus, more effective auxiliary data and the vertical structural parameters extracted from satellite LiDAR can be combined with multispectral images to improve forest tree species classification accuracy in future research. Numéro de notice : A2022-754 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article DOI : 10.3390/f13091416 Date de publication en ligne : 02/09/2022 En ligne : https://doi.org/10.3390/f13091416 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101757 [article]

GIS and machine learning for analysing influencing factors of bushfires using 40-year spatio-temporal bushfire data / Wanqin He in ISPRS International journal of geo-information, vol 11 n° 6 (June 2022)  

Public [article]  inISPRS International journal of geo-information > vol 11 n° 6 (June 2022) . - n° 336 Titre : GIS and machine learning for analysing influencing factors of bushfires using 40-year spatio-temporal bushfire data Type de document : Article/Communication Auteurs : Wanqin He, Auteur ; Sara Shirowzhan, Auteur ; Christopher Pettit, Auteur Année de publication : 2022 Article en page(s) : n° 336 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications SIG [Termes IGN] analyse diachronique [Termes IGN] apprentissage automatique [Termes IGN] brousse [Termes IGN] classification par forêts d'arbres décisionnels [Termes IGN] coefficient de corrélation [Termes IGN] données météorologiques [Termes IGN] données spatiotemporelles [Termes IGN] humidité du sol [Termes IGN] incendie [Termes IGN] indice de végétation [Termes IGN] Nouvelle-Galles du Sud [Termes IGN] prévention des risques [Termes IGN] régression linéaire [Termes IGN] Spark [Termes IGN] système d'information géographique [Termes IGN] température de l'air Résumé : (auteur) The causes of bushfires are extremely complex, and their scale of burning and probability of occurrence are influenced by the interaction of a variety of factors such as meteorological factors, topography, human activity and vegetation type. An in-depth understanding of the combined mechanisms of factors affecting the occurrence and spread of bushfires is needed to support the development of effective fire prevention plans and fire suppression measures and aid planning for geographic, ecological maintenance and urban emergency management. This study aimed to explore how bushfires, meteorological variability and other natural factors have interacted over the past 40 years in NSW Australia and how these influencing factors synergistically drive bushfires. The CSIRO’s Spark toolkit has been used to simulate bushfire burning spread over 24 h. The study uses NSW wildfire data from 1981–2020, combined with meteorological factors (temperature, precipitation, wind speed), vegetation data (NDVI data, vegetation type) and topography (slope, soil moisture) data to analyse the relationship between bushfires and influencing factors quantitatively. Machine learning-random forest regression was then used to determine the differences in the influence of bushfire factors on the incidence and burn scale of bushfires. Finally, the data on each influence factor was imported into Spark, and the results of the random forest model were used to set different influence weights in Spark to visualise the spread of bushfires burning over 24 h in four hotspot regions of bushfire in NSW. Wind speed, air temperature and soil moisture were found to have the most significant influence on the spread of bushfires, with the combined contribution of these three factors exceeding 60%, determining the spread of bushfires and the scale of burning. Precipitation and vegetation showed a greater influence on the annual frequency of bushfires. In addition, burn simulations show that wind direction influences the main direction of fire spread, whereas the shape of the flame front is mainly due to the influence of land classification. Besides, the simulation results from Spark could predict the temporal and spatial spread of fire, which is a potential decision aid for fireproofing agencies. The results of this study can inform how fire agencies can better understand fire occurrence mechanisms and use bushfire prediction and simulation techniques to support both their operational (short-term) and strategic (long-term) fire management responses and policies. Numéro de notice : A2022-481 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.3390/ijgi11060336 Date de publication en ligne : 05/06/2022 En ligne : https://doi.org/10.3390/ijgi11060336 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100894 [article]

ART-RISK 3.0, a fuzzy-based platform that combine GIS and expert assessments for conservation strategies in cultural heritage / M. Moreno in Journal of Cultural Heritage, vol 55 (May - June 2022)  

Public [article]  inJournal of Cultural Heritage > vol 55 (May - June 2022) . - pp 263 - 276 Titre : ART-RISK 3.0, a fuzzy-based platform that combine GIS and expert assessments for conservation strategies in cultural heritage Type de document : Article/Communication Auteurs : M. Moreno, Auteur ; R. Ortiz, Auteur ; D. Cagigas-Muñiz, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 263 - 276 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications SIG [Termes IGN] analyse des risques [Termes IGN] conservation du patrimoine [Termes IGN] église [Termes IGN] Espagne [Termes IGN] gelée [Termes IGN] Inférence floue [Termes IGN] inondation [Termes IGN] intelligence artificielle [Termes IGN] logique floue [Termes IGN] monument historique [Termes IGN] patrimoine culturel [Termes IGN] risque naturel [Termes IGN] séisme [Termes IGN] système d'information géographique [Termes IGN] température de l'air Résumé : (auteur) Heritage preservation poses numerous difficulties, especially in emergency situations or during budget cuts. In these contexts, having tools that facilitate efficient and rapid management of hazards-vulnerabilities is a priority for the preventive conservation and triage of cultural assets. This paper presents the first (to the authors' knowledge) free and public availability Artificial Intelligence platform designed for conservation strategies in cultural heritage. Art-Risk 3.0 is a platform designed as a fuzzy-logic inference system that combines information from geographical information system maps with expert assessments, in order to identify the contextual threat level and the degree of vulnerability that heritage buildings present. Thanks to the possibilities that the geographic information system offers, 12 Spanish churches (11th - 16th centuries) were analyzed. The artificial intelligence platform developed makes it possible to analyze the index of hazard, vulnerability and functionality, classify buildings according to the risk in order to do a sustainable use of budgets through the rational management of preventive conservation. The data stored in the system allows identify the danger due to geotechnics, precipitation, torrential downpour, thermal oscillation, frost, earthquake and flooding. Through the use of fuzzy logic, the tool interrelates environmental conditions with 14 other variables related to structural risks and the vulnerability of buildings, which are evaluated through bibliographic search and review of photographic images. The geographic information system has identified torrential rains and thermal oscillations as the environmental threats that mostly impact heritage buildings in Spain. The results obtained highlight the Church of Santiago de Jesús as the most vulnerable building due to a lack of preventive conservation programs. These results, consistent with the inclusion of this monument on the list of heritage at risk defined by Hispania Nostra, corroborate the functionality of the model. Numéro de notice : A2022-472 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.1016/j.culher.2022.03.012 Date de publication en ligne : 14/04/2022 En ligne : https://doi.org/10.1016/j.culher.2022.03.012 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100818 [article]

Multi-method monitoring of rockfall activity along the classic route up Mont Blanc (4809 m a.s.l.) to encourage adaptation by mountaineers / Jacques Mourey in Natural Hazards and Earth System Sciences, vol 22 n° 2 (February 2022)  

Public [article]  inNatural Hazards and Earth System Sciences > vol 22 n° 2 (February 2022) . - pp 445 - 460 Titre : Multi-method monitoring of rockfall activity along the classic route up Mont Blanc (4809 m a.s.l.) to encourage adaptation by mountaineers Type de document : Article/Communication Auteurs : Jacques Mourey, Auteur ; Pascal Lacroix, Auteur ; Pierre-Allain Duvillard, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 445 - 460 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] capteur actif [Termes IGN] capteur non-imageur [Termes IGN] carte thématique [Termes IGN] détection de changement [Termes IGN] éboulement [Termes IGN] modèle numérique de terrain [Termes IGN] Mont-Blanc, massif du [Termes IGN] onde sismique [Termes IGN] pergélisol [Termes IGN] prévention des risques [Termes IGN] risque naturel [Termes IGN] saison [Termes IGN] sismologie [Termes IGN] surveillance géologique [Termes IGN] température de l'air Résumé : (auteur) There are on average 35 fatal mountaineering accidents per summer in France. On average, since 1990, 3.7 of them have occurred every summer in the Grand Couloir du Goûter, on the classic route up Mont Blanc (4809 m a.s.l.). Rockfall is one of the main factors that explain this high accident rate and contribute to making it one of the most accident-prone areas in the Alps for mountaineers. In this particular context, the objective of this study is to document the rockfall activity and its triggering factors in the Grand Couloir du Goûter in order to disseminate the results to mountaineers and favour their adaptation to the local rockfall hazard. Using a multi-method monitoring system (five seismic sensors, an automatic digital camera, three rock subsurface temperature sensors, a traffic sensor, a high-resolution topographical survey, two weather stations and a rain gauge), we acquired a continuous database on rockfalls during a period of 68 d in 2019 and some of their potential triggering factors (precipitation, ground and air temperatures, snow cover, frequentation by climbers). At the seasonal scale, our results confirm previous studies showing that rockfalls are most frequent during the snowmelt period in permafrost-affected rockwalls. Furthermore, the unprecedented time precision and completeness of our rockfall database at high elevation thanks to seismic sensors allowed us to investigate the factors triggering rockfalls. We found a clear correlation between rockfall frequency and air temperature, with a 2 h delay between peak air temperature and peak rockfall activity. A small number of rockfalls seem to be triggered by mountaineers. Our data set shows that climbers are not aware of the variations in rockfall frequency and/or cannot/will not adapt their behaviour to this hazard. These results should help to define an adaptation strategy for climbers. Therefore, we disseminated our results within the mountaineering community thanks to the full integration of our results into the management of the route by local actors. Knowledge built during this experiment has already been used for the definition and implementation of management measures for the attendance in summer 2020. Numéro de notice : A2022-181 Affiliation des auteurs : non IGN Thématique : IMAGERIE/POSITIONNEMENT Nature : Article DOI : 10.5194/nhess-22-445-2022 En ligne : https://doi.org/10.5194/nhess-22-445-2022 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99859 [article]

Seven decades of coastal change at Barter Island, Alaska: Exploring the importance of waves and temperature on erosion of coastal permafrost bluffs / Ann E. Gibbs in Remote sensing, vol 13 n° 21 (November-1 2021)  

Permalink

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

Permalink

Climate warming predispose sessile oak forests to drought-induced tree mortality regardless of management legacies / Any Mary Petritan in Forest ecology and management, vol 491 (July-1 2021)  

Permalink

Glacier elevation change in the Western Qilian mountains as observed by TerraSAR-X/TanDEM-X images / Qibing Zhang in Geocarto international, vol 36 n° 12 ([01/07/2021])  

Permalink

Temperature and humidity effects on CG-6 gravity observations / P. I. A. Weerasinghe in Journal of applied geodesy, vol 15 n° 3 (July 2021)  

Permalink

Global Climate [in “State of the Climate in 2019"] / A. Ades in Bulletin of the American Meteorological Society, vol 101 n° 8 (August 2020)  

Permalink

Evaluating the potential of red spruce (Picea rubens Sarg.) to persist under climate change using historic provenance trials in eastern Canada / Wushuang Li in Forest ecology and management, Vol 466 (15 June 2020)  

Permalink

Estimating spatio-temporal air temperature in London (UK) using machine learning and earth observation satellite data / Rochelle Schneider dos Santos in International journal of applied Earth observation and geoinformation, vol 88 (June 2020)  

Permalink

Impact of precipitation, air temperature and abiotic emissions on gross primary production in Mediterranean ecosystems in Europe / S. Bartsch in European Journal of Forest Research, vol 139 n° 1 (February 2020)  

Permalink

Co-visualization of air temperature and urban data for visual exploration / Jacques Gautier (2020)    

Permalink