Centre dedocumentation
scientifique

Can machine learning improve small area population forecasts? A forecast combination approach / Irina Grossman in Computers, Environment and Urban Systems, vol 95 (July 2022)  

Public [article]  inComputers, Environment and Urban Systems > vol 95 (July 2022) . - n° 101806 Titre : Can machine learning improve small area population forecasts? A forecast combination approach Type de document : Article/Communication Auteurs : Irina Grossman, Auteur ; Kasun Bandara, Auteur ; Tom Wilson, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 101806 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes IGN] analyse en composantes principales [Termes IGN] apprentissage automatique [Termes IGN] Australie [Termes IGN] démographie [Termes IGN] Extreme Gradient Machine [Termes IGN] infrastructure [Termes IGN] lissage de données [Termes IGN] modèle de simulation [Termes IGN] modèle empirique [Termes IGN] Nouvelle-Zélande [Termes IGN] planification stratégique [Termes IGN] pondération [Termes IGN] série temporelle Résumé : (auteur) Generating accurate small area population forecasts is vital for governments and businesses as it provides better grounds for decision making and strategic planning of future demand for services and infrastructure. Small area population forecasting faces numerous challenges, including complex underlying demographic processes, data sparsity, and short time series due to changing geographic boundaries. In this paper, we propose a novel framework for small area forecasting which combines proven demographic forecasting methods, an exponential smoothing based algorithm, and a machine learning based forecasting technique. The proposed forecasting combination contains four base models commonly used in demographic forecasting, a univariate forecasting model specifically suitable for forecasting yearly data, and a globally trained Light Gradient Boosting Model (LGBM) that exploits the similarities between a collection of population time series. In this study, three forecast combination techniques are investigated to weight the forecasts generated by these base models. We empirically evaluate our method, by preparing small area population forecasts for Australia and New Zealand. The proposed framework is able to achieve competitive results in terms of forecasting accuracy. Moreover, we show that the inclusion of the LGBM model always improves the accuracy of combination models on both datasets, relative to combination models which only include the demographic models. In particular, the results indicate that the proposed combination framework decreases the prevalence of relatively poor forecasts, while improving the reliability of small area population forecasts. Numéro de notice : A2022-374 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.1016/j.compenvurbsys.2022.101806 Date de publication en ligne : 19/04/2022 En ligne : https://doi.org/10.1016/j.compenvurbsys.2022.101806 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100621 [article]

Using textual volunteered geographic information to model nature-based activities: A case study from Aotearoa New Zealand / Ekaterina Egorova in Journal of Spatial Information Science (JoSIS), n° 23 (2021)  

Public [article]  inJournal of Spatial Information Science (JoSIS) > n° 23 (2021) . - pp 25 - 63 Titre : Using textual volunteered geographic information to model nature-based activities: A case study from Aotearoa New Zealand Type de document : Article/Communication Auteurs : Ekaterina Egorova, Auteur Année de publication : 2021 Article en page(s) : pp 25 - 63 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes IGN] cognition [Termes IGN] corpus [Termes IGN] données d'entrainement (apprentissage automatique) [Termes IGN] données localisées des bénévoles [Termes IGN] émotion [Termes IGN] interaction homme-milieu [Termes IGN] littérature [Termes IGN] loisir [Termes IGN] milieu naturel [Termes IGN] Nouvelle-Zélande [Termes IGN] réseau social [Termes IGN] service écosystémique Résumé : (auteur) A boom in volunteered geographic information has led to extensive data-driven exploration and modeling of places. While many studies have used such data to explore human-environment interaction in urban settings, few have investigated natural, non-urban settings. To address this gap, this study systematically explores the content of online reviews of nature-based recreation activities, and develops a fine-grained hierarchical model that includes 28 aspects grouped into three main domains: activity, settings, and emotions/cognition. It further demonstrates how the model can be used to explore the variation in recreation experiences across activities, setting the stage for the analysis of the spatio-temporal variations in recreation experiences in the future. Importantly, the study provides an annotated corpus that can be used as a training dataset for developing methods to automatically capture aspects of recreation experiences in texts. Numéro de notice : A2021-950 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.5311/JOSIS.2021.23.157 Date de publication en ligne : 24/12/2021 En ligne : https://doi.org/10.5311/JOSIS.2021.23.157 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99644 [article]

A method of extracting high-accuracy elevation control points from ICESat-2 altimetry data / Binbin Li in Photogrammetric Engineering & Remote Sensing, PERS, vol 87 n° 11 (November 2021)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 87 n° 11 (November 2021) . - pp 821 - 830 Titre : A method of extracting high-accuracy elevation control points from ICESat-2 altimetry data Type de document : Article/Communication Auteurs : Binbin Li, Auteur ; Huan Xie, Auteur ; Shijie Liu, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 821 - 830 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] altimétrie satellitaire par laser [Termes IGN] contour [Termes IGN] données ICEsat [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] Etats-Unis [Termes IGN] grande échelle [Termes IGN] modèle numérique de surface [Termes IGN] Nouvelle-Zélande [Termes IGN] photon [Termes IGN] semis de points [Termes IGN] télémétrie laser aéroporté Résumé : (Auteur) Due to its high ranging accuracy, spaceborne laser altimetry technology can improve the accuracy of satellite stereo mapping without ground control points. In the past, full-waveform ICE, CLOUD, and Land Elevation Satellite (ICESat) laser altimeter data have been used as one of the main data sources for global elevation control. As a second-generation satellite, ICESat-2 is equipped with an altimeter using photon counting mode. This can further improve the application capability for stereo mapping because of the six laser beams with high along-track repetition frequency, which can provide more detailed ground contour descriptions. Previous studies have addressed how to extract high-accuracy elevation control points from ICESat data. However, these methods cannot be directly applied to ICESat-2 data because of the different modes of the laser altimeters. Therefore, in this paper, we propose a method using comprehensive evaluation labels that can extract high-accuracy elevation control points that meet the different level elevation accuracy requirements for large scale mapping from the ICESat-2 land-vegetation along-track product. The method was verified using two airborne lidar data sets. In flat, hilly, and mountainous areas, by using our method to extract the terrain elevation, the root-mean-square error of elevation control points decrease from 1.249–2.094 m, 2.237–3.225 m, and 2.791–4.822 m to 0.262–0.429 m, 0.484–0.596 m, and 0.611–1.003 m, respectively. The results show that the extraction elevations meet the required accuracy for large scale mapping. Numéro de notice : A2021-895 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.14358/PERS.21-00009R2 Date de publication en ligne : 01/11/2021 En ligne : https://doi.org/10.14358/PERS.21-00009R2 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99271 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
105-2021111	SL	Revue	Centre de documentation	Revues en salle	Disponible

Ten years of Lake Taupō surface height estimates using the GNSS interferometric reflectometry / Lucas D. Holden in Journal of geodesy, vol 95 n° 7 (July 2021)  

Public [article]  inJournal of geodesy > vol 95 n° 7 (July 2021) . - n° 74 Titre : Ten years of Lake Taupō surface height estimates using the GNSS interferometric reflectometry Type de document : Article/Communication Auteurs : Lucas D. Holden, Auteur ; Kristine M. Larson, Auteur Année de publication : 2021 Article en page(s) : n° 74 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de géodésie spatiale [Termes IGN] altimétrie satellitaire par radar [Termes IGN] lac [Termes IGN] Nouvelle-Zélande [Termes IGN] réflectométrie par GNSS [Termes IGN] série temporelle [Termes IGN] signal GNSS [Termes IGN] station GNSS Résumé : (auteur) A continuously operating GNSS station within a lake interior is uncommon, but advantageous for testing the GNSS Interferometric Reflectometry (GNSS-IR) technique. In this research, GNSS-IR is used to estimate ten years of lake surface heights for Lake Taupō in New Zealand. This is achieved using data collected from station TGHO, approximately 4 km from the lake’s shoreline. Its reliability is assessed by comparisons with shoreline gauges and satellite radar altimetry lake surface heights. Relative RMS differences between the daily averaged lake gauge and GNSS-IR lake surface heights range from ± 0.027 to ± 0.028 m. Relative RMS differences between the satellite radar altimetry lake surface heights and the GNSS-IR lake surface heights are ± 0.069 m and ± 0.124 m. The results show that the GNSS-IR technique at Lake Taupō can provide reliable lake surface height estimates in a terrestrial reference frame. A new ground-based absolute satellite radar altimetry calibration/validation approach based on GNSS-IR is proposed and discussed. Numéro de notice : A2021-513 Affiliation des auteurs : non IGN Thématique : POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s00190-021-01523-7 Date de publication en ligne : 18/06/2021 En ligne : https://doi.org/10.1007/s00190-021-01523-7 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97932 [article]

Urban expansion in Auckland, New Zealand: a GIS simulation via an intelligent self-adapting multiscale agent-based model / Tingting Xu in International journal of geographical information science IJGIS, vol 34 n° 11 (November 2020)  

Public [article]  inInternational journal of geographical information science IJGIS > vol 34 n° 11 (November 2020) . - pp 2136 - 2159 Titre : Urban expansion in Auckland, New Zealand: a GIS simulation via an intelligent self-adapting multiscale agent-based model Type de document : Article/Communication Auteurs : Tingting Xu, Auteur ; Jay Gao, Auteur ; Giovanni Coco, Auteur ; Shuliang Wang, Auteur Année de publication : 2020 Article en page(s) : pp 2136 - 2159 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications SIG [Termes IGN] agent (intelligence artificielle) [Termes IGN] Auckland [Termes IGN] croissance urbaine [Termes IGN] étalement urbain [Termes IGN] modèle de simulation [Termes IGN] modèle orienté agent [Termes IGN] occupation du sol [Termes IGN] réseau neuronal artificiel [Termes IGN] simulation dynamique [Termes IGN] utilisation du sol Résumé : (auteur) When modelling urban expansion dynamics, cellular automata models focus mostly on the physical environments and cell neighbours, but ignore the ‘human’ aspect of the allocation of urban expansion cells. This limitation is overcome here using an intelligent self-adapting multiscale agent-based model. To simulate the urban expansion of Auckland, New Zealand, a total of 15 urban expansion drivers/constraints were considered over two periods (2000–2005, 2005–2010). The modelling takes into consideration both a macro-scale agent (government) and micro-scale agents (residents of three income levels), and their multi-level interactions. In order to achieve reliable simulation results, ABM was coupled with an artificial neural network to reveal the learning process and heterogeneity of the multi-sub-residential agents. The ANN-ABM accurately simulated the urban expansion of Auckland at both the global and local scales, with kappa simulation value at 0.48 and 0.55, respectively. The validated simulation result shows that the intelligent and self-adapting ANN-ABM approach is more accurate than an ABM with a general type of agent model (kappa simulation = 0.42) at the global scale, and more accurate than an ANN-based CA model (kappa simulation = 0.47) at the local scale. Simulation inaccuracy stems mostly from the outdated master land use plan. Numéro de notice : A2020-613 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2020.1748192 Date de publication en ligne : 17/04/2020 En ligne : https://doi.org/10.1080/13658816.2020.1748192 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95984 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
079-2020111	SL	Revue	Centre de documentation	Revues en salle	Disponible

Decolonizing world heritage maps using indigenous toponyms, stories, and interpretive attributes / Mark Palmer in Cartographica, vol 55 n° 3 (Fall 2020)  

Permalink

Geomorphic Change Detection Using Cost-Effective Structure-from-Motion Photogrammetry: Evaluation of Direct Georeferencing from Consumer-Grade UAS at Orewa Beach (New Zealand) / Stéphane Bertin in Photogrammetric Engineering & Remote Sensing, PERS, vol 86 n° 5 (May 2020)  

Permalink

Performance of real-time undifferenced precise positioning assisted by remote IGS multi-GNSS stations / Zhiqiang Liu in GPS solutions, vol 24 n° 2 (April 2020)  

Permalink

Comparative usability of an augmented reality sandtable and 3D GIS for education / Antoni B. Moore in International journal of geographical information science IJGIS, vol 34 n° 2 (February 2020)  

Permalink

National scale identification and characterization of braided rivers in New Zealand using Google Earth Engine / Alexis Jean (2020) 

Permalink

Optimal segmentation of high spatial resolution images for the classification of buildings using random forests / James Bialas in International journal of applied Earth observation and geoinformation, vol 82 (October 2019)  

Permalink

Simulation of urban expansion via integrating artificial neural network with Markov chain – cellular automata / Tingting Xu in International journal of geographical information science IJGIS, vol 33 n° 10 (October 2019)  

Permalink

Unmanned aerial vehicles (UAVs) for monitoring macroalgal biodiversity: comparison of RGB and multispectral imaging sensors for biodiversity assessments / Leigh Tait in Remote sensing, vol 11 n° 19 (October-1 2019)  

Permalink

Thinking outside the square: Evidence that plot shape and layout in forest inventories can bias estimates of stand metrics / Thomas S. H. Paul in Methods in ecology and evolution, vol 10 n° 3 (March 2019)  

Permalink

Research and development progress in 3D cadastral systems / Peter J. M. Van Oosterom (2019)  

Permalink