Descripteur
Documents disponibles dans cette catégorie (1700)
Ajouter le résultat dans votre panier
Visionner les documents numériques
Affiner la recherche Interroger des sources externes
Etendre la recherche sur niveau(x) vers le bas
Solid waste mapping based on very high resolution remote sensing imagery and a novel deep learning approach / Bowen Niu in Geocarto international, vol 38 n° 1 ([01/01/2023])
[article]
Titre : Solid waste mapping based on very high resolution remote sensing imagery and a novel deep learning approach Type de document : Article/Communication Auteurs : Bowen Niu, Auteur ; Quanlong Feng, Auteur ; Jianyu Yang, Auteur ; et al., Auteur Année de publication : 2023 Article en page(s) : n° 2164361 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection
[Termes IGN] cartographie thématique
[Termes IGN] Chine
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] contour
[Termes IGN] déchet
[Termes IGN] fusion de données
[Termes IGN] image à très haute résolution
[Termes IGN] Inde
[Termes IGN] Mexique
[Termes IGN] urbanisationRésumé : (auteur) The urbanization worldwide leads to the rapid increase of solid waste, posing a threat to environment and people’s wellbeing. However, it is challenging to detect solid waste sites with high accuracy due to complex landscape, and very few studies considered solid waste mapping across multi-cities and in large areas. To tackle this issue, this study proposes a novel deep learning model for solid waste mapping from very high resolution remote sensing imagery. By integrating a multi-scale dilated convolutional neural network (CNN) and a Swin-Transformer, both local and global features are aggregated. Experiments in China, India and Mexico indicate that the proposed model achieves high performance with an average accuracy of 90.62%. The novelty lies in the fusion of CNN and Transformer for solid waste mapping in multi-cities without the need for pixel-wise labelled data. Future work would consider more sophisticated methods such as semantic segmentation for fine-grained solid waste classification. Numéro de notice : A2023-109 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2022.2164361 Date de publication en ligne : 04/01/2023 En ligne : https://doi.org/10.1080/10106049.2022.2164361 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102407
in Geocarto international > vol 38 n° 1 [01/01/2023] . - n° 2164361[article]Understanding public perspectives on fracking in the United States using social media big data / Xi Gong in Annals of GIS, vol 29 n° 1 (January 2023)
[article]
Titre : Understanding public perspectives on fracking in the United States using social media big data Type de document : Article/Communication Auteurs : Xi Gong, Auteur ; Yujian Lu, Auteur ; Daniel Beene, Auteur ; et al., Auteur Année de publication : 2023 Article en page(s) : pp 21 - 35 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique web
[Termes IGN] analyse socio-économique
[Termes IGN] données issues des réseaux sociaux
[Termes IGN] données massives
[Termes IGN] enquête sociologique
[Termes IGN] Etats-Unis
[Termes IGN] fracturation
[Termes IGN] hétérogénéité spatiale
[Termes IGN] régression géographiquement pondérée
[Termes IGN] TwitterRésumé : (auteur) People’s attitudes towards hydraulic fracturing (fracking) can be shaped by socio-demographics, economic development, social equity and politics, environmental impacts, and fracking-related information. Existing research typically conducts surveys and interviews to study public attitudes towards fracking among a small group of individuals in a specific geographic area, where limited samples may introduce bias. Here, we compiled geo-referenced social media big data from Twitter during 2018–2019 for the entire United States to present a more holistic picture of people’s attitudes towards fracking. We used a multiscale geographically weighted regression (MGWR) to investigate county-level relationships between the aforementioned factors and percentages of negative tweets concerning fracking. Results indicate spatial heterogeneity and varying scales of those associations. Counties with higher median household income, larger African American populations, and/or lower educational level are less likely to oppose fracking, and these associations show global stationarity in all contiguous US counties. Eastern and Central US counties with higher unemployment rates, counties east of the Great Plains with less fracking sites nearby, and Western and Gulf Coast region counties with higher health insurance enrolments are more likely to oppose fracking activities. These three variables show clear East-West geographical divides in influencing public perspective on fracking. In counties across the southern Great Plains, negative attitudes towards fracking are less often vocalized on Twitter as the share of Republican voters increases. These findings have implications for both predicting public perspectives and needed policy adjustments. The methodology can also be conveniently applied to investigate public perspectives on other controversial topics. Numéro de notice : A2023-160 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.1080/19475683.2022.2121856 Date de publication en ligne : 10/09/2022 En ligne : https://doi.org/10.1080/19475683.2022.2121856 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102862
in Annals of GIS > vol 29 n° 1 (January 2023) . - pp 21 - 35[article]Urban infrastructure expansion and artificial light pollution degrade coastal ecosystems, increasing natural-to-urban structural connectivity / Moisés A. Aguilera in Landscape and Urban Planning, vol 229 (January 2023)
[article]
Titre : Urban infrastructure expansion and artificial light pollution degrade coastal ecosystems, increasing natural-to-urban structural connectivity Type de document : Article/Communication Auteurs : Moisés A. Aguilera, Auteur ; Maria Gracia González, Auteur Année de publication : 2023 Article en page(s) : n° 104609 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale
[Termes IGN] ArcGIS
[Termes IGN] Chili
[Termes IGN] croissance urbaine
[Termes IGN] dégradation de l'environnement
[Termes IGN] écosystème
[Termes IGN] étalement urbain
[Termes IGN] habitat (nature)
[Termes IGN] intensité lumineuse
[Termes IGN] littoral
[Termes IGN] méthode de Monte-Carlo
[Termes IGN] paysage urbain
[Termes IGN] pollution lumineuse
[Termes IGN] urbanismeRésumé : (auteur) Urbanization is provoking habitat loss and fragmentation, driving rapid landscape transformation worldwide. Remnant habitats in urban areas can be especially prone to degradation by human activities at short time scales, and poor planning during urban expansion can erode their structural and functional connectivity. Foredunes in particular are threatened significantly by human activities, including coastal urban infrastructure expansion, by bulldozing them and/or by interrupting their continuity across the shoreline, and also by associated light pollution. However, there is still scarce quantification about how urban processes determine changes in remnant habitat extent and modify the configuration of structural connectivity in coastal urban settings. Using an expanding conurbation located in north-central Chile (∼29°S) as model system, we investigated the rate of coastal foredune loss and spatial fragmentation due to urban expansion, and the change in the type of structural connectivity, i.e. with other natural habitats vs with urban infrastructure. Based on map analyses of structural connectivity among habitats and with urban infrastructure through time, we estimated foredune habitat extent and fragmentation and their shared border with other habitats and built infrastructure during two time intervals, 2010–2015 and 2015–2020. Distribution and intensity of light pollution on present foredunes were also quantified in situ through field sampling. We found 36 % decline in foredune area and increase in their connection with urban infrastructure. Urban wetlands and parallel dunes also experienced persistent area loss and increase in connection with urban infrastructure. Light pollution was intense in the foredune-beach ecotone. Given the rapid erosion of functional and structural connectivity of natural habitats, it becomes imperious to halt the reduction of remnant habitats and ecotones, and improve natural corridors in urban settings. Numéro de notice : A2023-127 Affiliation des auteurs : non IGN Thématique : BIODIVERSITE/GEOMATIQUE/URBANISME Nature : Article DOI : 10.1016/j.landurbplan.2022.104609 Date de publication en ligne : 17/10/2022 En ligne : https://doi.org/10.1016/j.landurbplan.2022.104609 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102507
in Landscape and Urban Planning > vol 229 (January 2023) . - n° 104609[article]Bayesian inference on the initiation phase of the 2014 Iquique, Chile, earthquake / Cédric Twardzik in Earth and planetary science letters, vol 600 (15 December 2022)
[article]
Titre : Bayesian inference on the initiation phase of the 2014 Iquique, Chile, earthquake Type de document : Article/Communication Auteurs : Cédric Twardzik, Auteur ; Zacharie Duputel, Auteur ; Romain Jolivet, Auteur ; Emilie Klein, Auteur ; Paul Rebischung , Auteur Année de publication : 2022 Projets : SLES-S5 / Nocquet, Jean-Mathieu Article en page(s) : n° 117835 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de géodésie spatiale
[Termes IGN] Chili
[Termes IGN] coordonnées GNSS
[Termes IGN] effondrement de terrain
[Termes IGN] inférence
[Termes IGN] matrice de covariance
[Termes IGN] séisme
[Termes IGN] série temporelle
[Termes IGN] sismologieRésumé : (auteur) We investigate the initiation phase of the 2014 Mw8.1 Iquique earthquake in northern Chile. In particular, we focus on the month preceding the mainshock, a time period known to exhibit an intensification of the seismic and aseismic activity in the region. The goal is to estimate the time-evolution and partitioning of seismic and aseismic slip during the preparatory phase of the mainshock. To do so, we develop a Bayesian inversion scheme to infer the spatio-temporal evolution of pre-slip from position time-series along with the corresponding uncertainty. To extract the aseismic component to the pre-seismic motion, we correct geodetic observations from the displacement induced by foreshocks. We find that aseismic slip accounts for ∼80 percents of the slip budget. That aseismic slip takes the form of a slow-slip events occurring between 20 to 5 days before the future mainshock. This time-evolution is not consistent with self-accelerating fault slip, a model that is often invoked to explain earthquake nucleation. Instead, the slow-slip event seems to have interacted with the foreshock sequence such that the foreshocks contributed to the arrest of aseismic slip. In addition, we observe some evidence of late self-accelerating slip, but associated with large uncertainties, making it difficult to assess its reliability from our observations alone. Numéro de notice : A2022-698 Affiliation des auteurs : UMR IPGP-Géod+Ext (2020- ) Thématique : POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.epsl.2022.117835 Date de publication en ligne : 26/10/2022 En ligne : https://doi.org/10.1016/j.epsl.2022.117835 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102117
in Earth and planetary science letters > vol 600 (15 December 2022) . - n° 117835[article]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)
[article]
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 humideRésumé : (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
in International journal of applied Earth observation and geoinformation > vol 115 (December 2022) . - n° 103095[article]A new data-adaptive network design methodology based on the k-means clustering and modified ISODATA algorithm for regional gravity field modeling via spherical radial basis functions / Rasit Ulug in Journal of geodesy, vol 96 n° 12 (December 2022)PermalinkA semi-automatic method for extraction of urban features by integrating aerial images and LIDAR data and comparing its performance in areas with different feature structures (case study: comparison of the method performance in Isfahan and Toronto) / Masoud Azad in Applied geomatics, vol 14 n° 4 (December 2022)PermalinkGA-Net: A geometry prior assisted neural network for road extraction / Xin Chen in International journal of applied Earth observation and geoinformation, vol 114 (November 2022)PermalinkIntegrating Bayesian networks to forecast sea-level rise impacts on barrier island characteristics and habitat availability / Benjamin T. Gutierrez in Earth and space science, vol 9 n° 11 (November 2022)PermalinkA machine learning approach for detecting rescue requests from social media / Zheye Wang in ISPRS International journal of geo-information, vol 11 n° 11 (November 2022)PermalinkAn estimation method to reduce complete and partial nonresponse bias in forest inventory / James A. Westfall in European Journal of Forest Research, vol 141 n° 5 (October 2022)PermalinkPredicting the variability in pedestrian travel rates and times using crowdsourced GPS data / Michael J. Campbell in Computers, Environment and Urban Systems, vol 97 (October 2022)PermalinkSimulating multiple urban land use changes by integrating transportation accessibility and a vector-based cellular automata: a case study on city of Toronto / Xiaocong Xu in Geo-spatial Information Science, vol 25 n° 3 (October 2022)PermalinkSpatio-temporal graph convolutional networks for road network inundation status prediction during urban flooding / Faxi Yuan in Computers, Environment and Urban Systems, vol 97 (October 2022)PermalinkComparing Landsat-8 and Sentinel-2 top of atmosphere and surface reflectance in high latitude regions: case study in Alaska / Jiang Chen in Geocarto international, vol 37 n° 20 ([20/09/2022])Permalink