Centre dedocumentation
scientifique

An integrated framework of global sensitivity analysis and calibration for spatially explicit agent-based models / Jeon-Young Kang in Transactions in GIS, vol 26 n° 1 (February 2022)  

Public [article]  inTransactions in GIS > vol 26 n° 1 (February 2022) . - pp 100 - 128 Titre : An integrated framework of global sensitivity analysis and calibration for spatially explicit agent-based models Type de document : Article/Communication Auteurs : Jeon-Young Kang, Auteur ; Alexander Michels, Auteur ; Andrew Crooks, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 100 - 128 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique [Termes IGN] analyse de sensibilité [Termes IGN] analyse de variance [Termes IGN] épidémie [Termes IGN] étalonnage de modèle [Termes IGN] maladie virale [Termes IGN] méthode de Monte-Carlo [Termes IGN] Miami [Termes IGN] modèle de simulation [Termes IGN] modèle orienté agent [Termes IGN] WebSIG Résumé : (auteur) Calibration of agent-based models (ABMs) is a major challenge due to the complex nature of the systems being modeled, the heterogeneous nature of geographical regions, the varying effects of model inputs on the outputs, and computational intensity. Nevertheless, ABMs need to be carefully tuned to achieve the desirable goal of simulating spatiotemporal phenomena of interest, and a well-calibrated model is expected to achieve an improved understanding of the phenomena. To address some of the above challenges, this article proposes an integrated framework of global sensitivity analysis (GSA) and calibration, called GSA-CAL. Specifically, variance-based GSA is applied to identify input parameters with less influence on differences between simulated outputs and observations. By dropping these less influential input parameters in the calibration process, this research reduces the computational intensity of calibration. Since GSA requires many simulation runs, due to ABMs' stochasticity, we leverage the high-performance computing power provided by the advanced cyberinfrastructure. A spatially explicit ABM of influenza transmission is used as the case study to demonstrate the utility of the framework. Leveraging GSA, we were able to exclude less influential parameters in the model calibration process and demonstrate the importance of revising local settings for an epidemic pattern in an outbreak. Numéro de notice : A2022-176 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1111/tgis.12837 Date de publication en ligne : 03/09/2021 En ligne : https://doi.org/10.1111/tgis.12837 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99832 [article]

Modeling transit-assisted hurricane evacuation through socio-spatial networks / Yan Yang in International journal of geographical information science IJGIS, vol 35 n° 12 (December 2021)  

Public [article]  inInternational journal of geographical information science IJGIS > vol 35 n° 12 (December 2021) . - pp 2424 - 2441 Titre : Modeling transit-assisted hurricane evacuation through socio-spatial networks Type de document : Article/Communication Auteurs : Yan Yang, Auteur ; Sara Metcalf, Auteur ; Liang Mao, Auteur Année de publication : 2021 Article en page(s) : pp 2424 - 2441 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes IGN] comportement [Termes IGN] Floride (Etats-Unis) [Termes IGN] gestion de crise [Termes IGN] modèle de simulation [Termes IGN] modèle orienté agent [Termes IGN] réseau social [Termes IGN] système multi-agents [Termes IGN] tempête [Termes IGN] trafic routier [Termes IGN] transport public Résumé : (auteur) Increasing intensity and frequency of hurricane events underscores the need for efficient and inclusive evacuation plans, particularly for carless and disabled populations. Hurricane evacuation intrinsically involves both social and spatial processes. People’s decision to evacuate spreads over social networks; once their decisions are made, they flee through spatial transportation networks. This article describes a novel effort to integrate socio-spatial networks into an agent-based evacuation simulation model, taking the Florida Keys in the USA as a study area. In the model, households, as agents, were synthesized from Census data, then connected by a ‘home-workplace-neighborhood’ social network, and registered to a spatial road network. A threshold decision model was used to simulate social contagion of households’ decision to evacuate. The resulting travel demands were input into the TRANSIMS platform to generate on-road traffic. The model analyzed scenarios of automobile-only and public transit-assisted evacuation. The results show that the simulated traffic under the automobile-only scenario aligns with the observed traffic dynamics, which validates our socio-spatially integrated model. Adding public transportation capacity significantly reduces the traffic load and evacuation time, and provides a practical, accessible, and equitable route to safety for low mobility populations. Numéro de notice : A2021-874 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2020.1828590 Date de publication en ligne : 02/10/2020 En ligne : https://doi.org/10.1080/13658816.2020.1828590 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99137 [article]

Measuring shallow-water bathymetric signal strength in lidar point attribute data using machine learning / Kim Lowell in International journal of geographical information science IJGIS, vol 35 n° 8 (August 2021)  

Public [article]  inInternational journal of geographical information science IJGIS > vol 35 n° 8 (August 2021) . - pp 1592 - 1610 Titre : Measuring shallow-water bathymetric signal strength in lidar point attribute data using machine learning Type de document : Article/Communication Auteurs : Kim Lowell, Auteur ; Brian Calder, Auteur ; Anthony Lyons, Auteur Année de publication : 2021 Article en page(s) : pp 1592 - 1610 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] apprentissage automatique [Termes IGN] bathymétrie laser [Termes IGN] données lidar [Termes IGN] Extreme Gradient Machine [Termes IGN] Floride (Etats-Unis) [Termes IGN] hydrographie [Termes IGN] lever bathymétrique [Termes IGN] semis de points Résumé : (auteur) The goal of this work was to evaluate if routinely collected but seldom used airborne lidar metadata – ‘point attribute data’ (PAD) – analyzed using machine learning/artificial intelligence can improve extraction of shallow-water (less than 20 m) bathymetry from lidar point clouds. Extreme gradient boosting (XGB) models relating PAD to an existing bathymetry/not bathymetry classification were fitted and evaluated for four areas near the Florida Keys. The PAD examined include ‘pulse specific’ information such as the return intensity and PAD describing flight path consistency. The R2 values for the XGB models were between 0.34 and 0.74. Global classification accuracies were above 80% although this reflected a sometimes extreme Bathy/NotBathy imbalance that inflated global accuracy. This imbalance was mitigated by employing a probability decision threshold (PDT) that equalizes the true positive (Bathy) and true negative (NotBathy) rates. It was concluded that 1) the strength of the bathymetric signal in the PAD should be sufficient to increase accuracy of density-based lidar point cloud bathymetry extraction methods and 2) ML can successfully model the relationship between the PAD and the Bathy/NotBathy classification. A method is also presented to examine the spatial and feature-space distribution of errors that will facilitate quality assurance and continuous improvement. Numéro de notice : A2021-548 Affiliation des auteurs : non IGN Thématique : IMAGERIE/POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2020.1867147 Date de publication en ligne : 30/12/2020 En ligne : https://doi.org/10.1080/13658816.2020.1867147 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98061 [article]

Extracting Shallow-Water Bathymetry from Lidar point clouds using pulse attribute data: Merging density-based and machine learning approaches / Kim Lowell in Marine geodesy, vol 44 n° 4 (July 2021)  

Public [article]  inMarine geodesy > vol 44 n° 4 (July 2021) . - pp 259 - 286 Titre : Extracting Shallow-Water Bathymetry from Lidar point clouds using pulse attribute data: Merging density-based and machine learning approaches Type de document : Article/Communication Auteurs : Kim Lowell, Auteur ; Brian Calder, Auteur Année de publication : 2021 Article en page(s) : pp 259 - 286 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] angle d'incidence [Termes IGN] apprentissage automatique [Termes IGN] bathymétrie laser [Termes IGN] classification barycentrique [Termes IGN] données lidar [Termes IGN] Extreme Gradient Machine [Termes IGN] Floride (Etats-Unis) [Termes IGN] lever bathymétrique [Termes IGN] profondeur [Termes IGN] semis de points Résumé : (auteur) To automate extraction of bathymetric soundings from lidar point clouds, two machine learning (ML1) techniques were combined with a more conventional density-based algorithm. The study area was four data “tiles” near the Florida Keys. The density-based algorithm determined the most likely depth (MLD) for a grid of “estimation nodes” (ENs). Unsupervised k-means clustering determined which EN’s MLD depth and associated soundings represented ocean depth rather than ocean surface or noise to produce a preliminary classification. An extreme gradient boosting (XGB) model was fitted to pulse return metadata – e.g. return intensity, incidence angle – to produce a final Bathy/NotBathy classification. Compared to an operationally produced reference classification, the XGB model increased global accuracy and decreased the false negative rate (FNR) – i.e. undetected bathymetry – that are most important for nautical navigation for all but one tile. Agreement between the final XGB and operational reference classifications ranged from 0.84 to 0.999. Imbalance between Bathy and NotBathy was addressed using a probability decision threshold that equalizes the FNR and the true positive rate (TPR). Two methods are presented for visually evaluating differences between the two classifications spatially and in feature-space. Numéro de notice : A2021-525 Affiliation des auteurs : non IGN Thématique : IMAGERIE/POSITIONNEMENT Nature : Article DOI : 10.1080/01490419.2021.1925790 Date de publication en ligne : 25/05/2021 En ligne : https://doi.org/10.1080/01490419.2021.1925790 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97964 [article]

Identifying the effects of chronic saltwater intrusion in coastal floodplain swamps using remote sensing / Elliott White Jr in Remote sensing of environment, vol 258 (June 2021)  

Public [article]  inRemote sensing of environment > vol 258 (June 2021) . - n° 112385 Titre : Identifying the effects of chronic saltwater intrusion in coastal floodplain swamps using remote sensing Type de document : Article/Communication Auteurs : Elliott White Jr, Auteur ; David Kaplan, Auteur Année de publication : 2021 Article en page(s) : n° 112385 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] biomasse aérienne [Termes IGN] eau de mer [Termes IGN] Enhanced vegetation index [Termes IGN] Floride (Etats-Unis) [Termes IGN] littoral [Termes IGN] Louisiane (Etats-Unis) [Termes IGN] marais [Termes IGN] Mexique (golfe du) [Termes IGN] montée du niveau de la mer [Termes IGN] salinité [Termes IGN] série temporelle Résumé : (auteur) Coastal floodplain swamps (CFS) are an important part of the coastal wetland mosaic, however they are threatened due to accelerated rates of sea level rise and saltwater intrusion (SWI). While remote sensing-based detection of wholesale coastal ecosystem shifts (i.e., from forest to marsh) are relatively straightforward, assessments of chronic, low-level SWI into CFS using remote sensing have yet to be developed and can provide a critical early-warning signal of ecosystem deterioration. In this study, we developed nine ecologically-based hypotheses to test whether remote sensing data could be used to reliably detect the presence of CFS experiencing SWI. Hypotheses were motivated by field- and literature-based understanding of the phenological and vegetative dynamics of CFS experiencing SWI relative to unimpacted, control systems. Hypotheses were organized into two primary groups: those that analyzed differences in summary measures (e.g., median and distribution) between SWI-impacted and unimpacted control sites and those that examined timeseries trends (e.g., sign and magnitude of slope). The enhanced vegetation index (EVI) was used as a proxy for production/biomass and was generated using MODIS surface reflectance data spanning 2000 to 2018. Experimental sites (n = 8) were selected from an existing network of long-term monitoring sites and included 4 pairs of impacted/non-impacted CFS across the northern Gulf of Mexico from Texas to Florida. The four best-supported hypotheses (81% across all sties) all used summary statistics, indicating that there were significant differences in the EVI of CFS experiencing chronic, low-level SWI compared to controls. These hypotheses were tested using data across a large and diverse region, supporting their implementation by researchers and managers seeking to identify CFS undergoing the first phases of SWI. In contrast, hypotheses that assessed CFS change over time were poorly supported, likely due to the slow and variable pace of ecological change, relatively short remote sensing data record, and/or specific site histories. Overall, these results show that remote sensing data can be used to identify differences in CFS vegetation associated with long-term, low-level SWI, but further methodological advancements are needed to reliably detect the temporal transition process. Numéro de notice : A2021-444 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1016/j.rse.2021.112385 Date de publication en ligne : 12/03/2021 En ligne : https://doi.org/10.1016/j.rse.2021.112385 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97851 [article]

Remote sensing applications in coastal environment / Pawel Terefenko (2021)  

Permalink

Sea level acceleration under the magnifier / Huseyin Baki Iz in Journal of geodetic science, vol 11 n° 1 (January 2021)  

Permalink

A preliminary exploration of the cooling effect of tree shade in urban landscapes / Qiuyan Yu in International journal of applied Earth observation and geoinformation, vol 92 (October 2020)  

Permalink

Exploratory bivariate and multivariate geovisualizations of a social vulnerability index / Georgianna Strode in Cartographic perspectives, n° 95 (July 2020)  

Permalink

Visualizing when, where, and how fires happen in U.S. parks and protected areas / Nicole C. Inglis in ISPRS International journal of geo-information, vol 9 n° 5 (May 2020)  

Permalink

Optimizing arbovirus surveillance using risk mapping and coverage modelling / Joni A. Downs in Annals of GIS, Vol 26 n° 1 (January 2020)  

Permalink

Total Vertical Uncertainty (TVU) modeling for topo-bathymetric LIDAR systems / Firat Eren in Photogrammetric Engineering & Remote Sensing, PERS, vol 85 n° 8 (August 2019)  

Permalink

Disaggregation of remotely sensed soil moisture in heterogeneous landscapes using holistic structure-based models / Subit Chakrabarti in IEEE Transactions on geoscience and remote sensing, vol 54 n° 8 (August 2016)  

Permalink

Combining hyperspectral and Lidar data for vegetation mapping in the Florida Everglades / Caiyun Zhang in Photogrammetric Engineering & Remote Sensing, PERS, vol 80 n° 8 (August 2014)  

Permalink

Mapping and assessing of urban impervious areas using multiple endmember spectral mixture analysis: a case study in the city of Tampa, Florida / Fenqing Weng in Geocarto international, vol 28 n° 7-8 (November - December 2013)  

Permalink