Centre de documentation
scientifique

Volcano-seismic transfer learning and uncertainty quantification with bayesian neural networks / Angel Bueno in IEEE Transactions on geoscience and remote sensing, vol 58 n° 2 (February 2020)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 58 n° 2 (February 2020) . - pp Titre : Volcano-seismic transfer learning and uncertainty quantification with bayesian neural networks Type de document : Article/Communication Auteurs : Angel Bueno, Auteur ; Carmen Benitez, Auteur ; Silvio De Angelis, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Statistiques [Termes IGN] apprentissage profond [Termes IGN] classification bayesienne [Termes IGN] classification par réseau neuronal [Termes IGN] forme d'onde [Termes IGN] incertitude des données [Termes IGN] réseau bayesien [Termes IGN] réseau neuronal profond [Termes IGN] Russie [Termes IGN] séisme [Termes IGN] sismologie [Termes IGN] surveillance géologique [Termes IGN] volcanologie [Termes IGN] Washington (Etats-Unis ; état) Résumé : (auteur) Over the past few years, deep learning (DL) has emerged as an important tool in the fields of volcano and earthquake seismology. However, these methods have been applied without performing thorough analyses of the associated uncertainties. Here, we propose a solution to enhance volcano-seismic monitoring systems, through probabilistic Bayesian DL; we implement and demonstrate a workflow for waveform classification, rapid quantification of the associated uncertainty, and link these uncertainties to changes in volcanic unrest. Specifically, we introduce Bayesian neural networks (BNNs) to perform event identification, classification, and their estimated uncertainty on data gathered at two active volcanoes, Mount St. Helens, Washington, USA, and Bezymianny, Kamchatka, Russia. We demonstrate how BNNs achieve excellent performance (92.08%) in discriminating both the type of event and its origin when the two data sets are merged together, and no additional training information is provided. Finally, we demonstrate that the data representations learned by the BNNs are transferable across different eruptive periods. We also find that the estimated uncertainty is related to changes in the state of unrest at the volcanoes and propose that it could be used to gauge whether the learned models may be exported to other eruptive scenarios. Numéro de notice : A2020-094 Affiliation des auteurs : non IGN Thématique : MATHEMATIQUE/POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2019.2941494 Date de publication en ligne : 07/10/2019 En ligne : https://doi.org/10.1109/TGRS.2019.2941494 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94657 [article]

What is so “hot” in heatmap? qualitative code cluster analysis with foursquare venue / Ilyoung Hong in Cartographica, vol 52 n° 4 (Winter 2017)  

Public [article]  inCartographica > vol 52 n° 4 (Winter 2017) . - pp 332 - 348 Titre : What is so “hot” in heatmap? qualitative code cluster analysis with foursquare venue Type de document : Article/Communication Auteurs : Ilyoung Hong, Auteur ; Jin-Kyu Jung, Auteur Année de publication : 2017 Article en page(s) : pp 332 - 348 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] analyse spatiale [Termes IGN] carte de densité de clics [Termes IGN] distribution spatiale [Termes IGN] réseau social géodépendant [Termes IGN] Seattle (Washington) [Vedettes matières IGN] Géovisualisation Résumé : (Auteur) Foursquare is a popular Web service and a representative location-based social network (LBSN) service using position data. Heatmap is a widely used means of geovisualization for analyzing social data with locational values. Until now, heatmap analysis of LBSN has focused on identifying quantitative distribution and patterns, with little consideration of the qualitative analysis of data content. Based on a case study of Foursquare venues and user-created content in Seattle, WA, this study conducts analyses assessing both the quantitative spatial distribution and the qualitative characteristics of coffee shops in the Seattle metropolitan area. It specifically proposes a new analytical method referred to as “code cluster,” which is designed to employ quantitative and qualitative approaches simultaneously. The significance of this method is its capacity to explain geographical differences in terms of qualitative traits in cluster regions, in addition to analyzing their spatial characteristics and distributions. In introducing this new hybrid approach, our aims are to reflect the original intent and essence of the data throughout the research process and to make further efforts to analyze and interpret the contextualized meanings. This will be possible through integration of advanced spatial analysis, geovisualization, and qualitative research that build on current geographic and geovisual research with big data. Numéro de notice : A2017-830 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.3138/cart.52.4.2016-0005 En ligne : https://doi.org/10.3138/cart.52.4.2016-0005 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=89364 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
031-2017041	SL	Revue	Centre de documentation	Revues en salle	Disponible

A little disturbance goes a long way: 33-year understory successional responses to a thin tephra deposit / Dylan G. Fischer in Forest ecology and management, vol 382 (15 December 2016)  

Public [article]  inForest ecology and management > vol 382 (15 December 2016) . - pp 236 - 243 Titre : A little disturbance goes a long way: 33-year understory successional responses to a thin tephra deposit Type de document : Article/Communication Auteurs : Dylan G. Fischer, Auteur ; Joseph A. Antos, Auteur ; William G. Grandy, Auteur ; Donald B. Zobel, Auteur Année de publication : 2016 Article en page(s) : pp 236 - 243 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] association végétale [Termes IGN] éruption volcanique [Termes IGN] phytosociologie [Termes IGN] placette d'échantillonnage [Termes IGN] richesse floristique [Termes IGN] Saint-Helens, Mont [Termes IGN] Washington (Etats-Unis ; état) [Vedettes matières IGN] Ecologie forestière Résumé : (auteur) Large volcanic eruptions can alter forest plant communities through a variety of mechanisms, including direct destruction of forests and changes to forest soils through tephra (aerially transported volcanic ejecta) deposits. While many studies have examined succession following direct destruction of forests, impacts to plant communities through tephra effects are less obvious, especially where the tephra depth is less than plant height. We used a 33-year experiment in an old growth forest that received shallow tephra deposition in the 1980 eruption of Mount St. Helens (WA, USA), to examine plant communities. We determined if community differences between plots with and without tephra: (1) were detectable, and (2) changed over time. We found that plant communities differed significantly between plots with and without tephra after 33 years. Further, differences were stronger after 33 years than at two years following the eruption. Species richness increased over time in both plots with and without tephra, but live cover was largely stable after two years. Nevertheless, communities shifted in different directions over time, where the changes in species composition and abundance immediately following tephra deposition were inconsistent with net changes that occurred over 30 years afterwards. These results suggest that widespread and apparently minor deposits of tephra, usually interpreted to be of transient importance if any, may induce long-term modifications of understory plant communities. Numéro de notice : A2016-717 Affiliation des auteurs : non IGN Thématique : FORET Nature : Article DOI : 10.1016/j.foreco.2016.10.018 En ligne : http://dx.doi.org/10.1016/j.foreco.2016.10.018 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=82192 [article]

Bumps and bruises in the digital skins of cities: unevenly distributed user-generated content across US urban areas / Colin Robertson in Cartography and Geographic Information Science, Vol 43 n° 4 (September 2016)  

Public [article]  inCartography and Geographic Information Science > Vol 43 n° 4 (September 2016) . - pp 283 - 300 Titre : Bumps and bruises in the digital skins of cities: unevenly distributed user-generated content across US urban areas Type de document : Article/Communication Auteurs : Colin Robertson, Auteur ; Robert Feick, Auteur Année de publication : 2016 Article en page(s) : pp 283 - 300 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique web [Termes IGN] analyse de données [Termes IGN] Dallas (Texas) [Termes IGN] données descriptives [Termes IGN] données localisées des bénévoles [Termes IGN] données socio-économiques [Termes IGN] géobalise [Termes IGN] image 2D [Termes IGN] Nouvelle-Orléans (Louisiane) [Termes IGN] qualité des données [Termes IGN] représentation des données [Termes IGN] representativité [Termes IGN] Seattle (Washington) Résumé : (Auteur) As momentum and interest build to leverage new forms of user-generated content that contains geographical information, classical issues of data quality remain significant research challenges. In this article, we explore issues of representativeness for one form of user-generated content, geotagged photographs in US urban centers. Generalized linear models were developed to associate photograph distribution with underlying socioeconomic descriptors at the city-scale, and examine intra-city variation in relation to income inequality. We conclude our analyses with a detailed examination of Dallas, Seattle, and New Orleans. Our findings add to the growing volume of evidence outlining uneven representativeness in user-generated data, and our approach contributes to the stock of methods available to investigate geographic variations in representativeness. In addition to city-scale variables relating to distribution of user-generated content, variability remains at localized scales that demand an individual and contextual understanding of their form and nature. The findings demonstrate that careful analysis of representativeness at both macro and micro scales can simultaneously provide important insights into the processes giving rise to user-generated data sets and potentially shed light on their embedded biases and suitability as inputs to analysis. Numéro de notice : A2016-415 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.1080/15230406.2015.1088801 En ligne : https://doi.org/10.1080/15230406.2015.1088801 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=81309 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
032-2016041	RAB	Revue	Centre de documentation	En réserve L003	Disponible

Spatial optimization as a generative technique for sustainable multiobjective land-use allocation / A. Ligmann-Zielinska in International journal of geographical information science IJGIS, vol 22 n° 6-7 (june 2008)  

Public [article]  inInternational journal of geographical information science IJGIS > vol 22 n° 6-7 (june 2008) . - pp 601 - 622 Titre : Spatial optimization as a generative technique for sustainable multiobjective land-use allocation Type de document : Article/Communication Auteurs : A. Ligmann-Zielinska, Auteur ; R.L. Church, Auteur ; Piotr Jankowski, Auteur Année de publication : 2008 Article en page(s) : pp 601 - 622 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications SIG [Termes IGN] allocation [Termes IGN] aménagement du territoire [Termes IGN] développement durable [Termes IGN] modèle mathématique [Termes IGN] optimisation (mathématiques) [Termes IGN] répartition géographique [Termes IGN] système d'information géographique [Termes IGN] utilisation du sol [Termes IGN] Washington (Etats-Unis ; état) Résumé : (Auteur) In this paper, we examine the applicability of spatial optimization as a generative modelling technique for sustainable land-use allocation. Specifically, we test whether spatial optimization can be used to generate a number of compromise spatial alternatives that are both feasible and different from each other. We present a new spatial multiobjective optimization model, which encourages efficient utilization of urban space through infill development, compatibility of adjacent land uses, and defensible redevelopment. The model uses a density-based design constraint developed by the authors. The constraint imposes a predefined level of consistent neighbourhood development to promote contiguity and compactness of urban areas. First, the model is tested on a hypothetical example. Further, we demonstrate a real-world application of the model to land-use planning in Chelan, a small environmental amenity town in the north-central region of the State of Washington, USA. The results indicate that spatial optimization is a promising method for generating land-use alternatives for further consideration in spatial decision-making. Copyright Taylor & Francis Numéro de notice : A2008-223 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.1080/13658810701587495 En ligne : https://doi.org/10.1080/13658810701587495 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=29218 [article]

Exemplaires(2)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
079-08041	RAB	Revue	Centre de documentation	En réserve L003	Disponible
079-08042	RAB	Revue	Centre de documentation	En réserve L003	Disponible

Mapping impervious surface type and sub-pixel abundance using Hyperion hyperspectral imagery / J. Falcone in Geocarto international, vol 20 n° 4 (December 2005 - February 2006)  

Permalink

A geographic analysis of historical grizzly bear sightings in the north cascades / J.K. Agee in Photogrammetric Engineering & Remote Sensing, PERS, vol 55 n° 11 (november 1989)  

Permalink

Satellite-derived urban heat islands from three coastal cities and the utilization of such data in urban climatology / M. Roth in International Journal of Remote Sensing IJRS, vol 10 n° 11 (November 1989)  

Permalink

Remote sensing of soils in the eastern Palouse region with Landsat Thematic Mapper / B.E. Frazier in Remote sensing of environment, vol 28 n° 1 (April - June 1989)  

Permalink