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]

Coupling graph deep learning and spatial-temporal influence of built environment for short-term bus travel demand prediction / Tianhong Zhao in Computers, Environment and Urban Systems, vol 94 (June 2022)  

Public [article]  inComputers, Environment and Urban Systems > vol 94 (June 2022) . - n° 101776 Titre : Coupling graph deep learning and spatial-temporal influence of built environment for short-term bus travel demand prediction Type de document : Article/Communication Auteurs : Tianhong Zhao, Auteur ; Zhengdong Huang, Auteur ; Wei Tu, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 101776 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes IGN] apprentissage profond [Termes IGN] bati [Termes IGN] données spatiotemporelles [Termes IGN] gestion de trafic [Termes IGN] graphe [Termes IGN] logement [Termes IGN] migration pendulaire [Termes IGN] modèle de simulation [Termes IGN] régression géographiquement pondérée [Termes IGN] service public [Termes IGN] Shenzhen [Termes IGN] système de transport intelligent [Termes IGN] transport public [Termes IGN] transport urbain Résumé : (auteur) Accurate and robust short-term bus travel prediction facilitates operating the bus fleet to provide comfortable and flexible bus services. The built environment, including land use, buildings, and public facilities, has an important influence on bus travel demand prediction. However, previous studies regarded the built environment as a static feature thus even ignored its influence on bus travel in deep learning framework. To fill this gap, we propose a graph deep learning-based approach coupling with spatiotemporal influence of built environment (GDLBE) to enhance short-term bus travel demand prediction. A time-dependent geographically weighted regression method is used to resolve the dynamic influence of the built environment on bus travel demand at different times of the day. A graph deep learning module is used to capture the comprehensive spatial and temporal dependency behind massive bus travel demand. The short-term bus travel demand is predicted by fusing the dynamic built environment influences and spatiotemporal dependency. An experiment in Shenzhen is conducted to evaluate the performance of the proposed approach. Baseline methods are compared, and the results demonstrate that the proposed approach outperforms the baselines. These results will help bus fleet dispatch for smart transportation. Numéro de notice : A2022-245 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.1016/j.compenvurbsys.2022.101776 Date de publication en ligne : 12/03/2022 En ligne : https://doi.org/10.1016/j.compenvurbsys.2022.101776 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100185 [article]

Discovering co-location patterns in multivariate spatial flow data / Jiannan Cai in International journal of geographical information science IJGIS, vol 36 n° 4 (April 2022)  

Public [article]  inInternational journal of geographical information science IJGIS > vol 36 n° 4 (April 2022) . - pp 720 - 748 Titre : Discovering co-location patterns in multivariate spatial flow data Type de document : Article/Communication Auteurs : Jiannan Cai, Auteur ; Mei-Po Kwan, Auteur Année de publication : 2022 Article en page(s) : pp 720 - 748 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes IGN] analyse bivariée [Termes IGN] analyse de groupement [Termes IGN] analyse univariée [Termes IGN] autocorrélation spatiale [Termes IGN] Chicago (Illinois) [Termes IGN] co-positionnement [Termes IGN] données de flux [Termes IGN] données socio-économiques [Termes IGN] dynamique spatiale [Termes IGN] enquête [Termes IGN] exploration de données géographiques [Termes IGN] migration pendulaire [Termes IGN] origine - destination [Termes IGN] voisinage (relation topologique) Résumé : (auteur) Spatial flow co-location patterns (FCLPs) are important for understanding the spatial dynamics and associations of movements. However, conventional point-based co-location pattern discovery methods ignore spatial movements between locations and thus may generate erroneous findings when applied to spatial flows. Despite recent advances, there is still a lack of methods for analyzing multivariate flows. To bridge the gap, this paper formulates a novel problem of FCLP discovery and presents an effective detection method based on frequent-pattern mining and spatial statistics. We first define a flow co-location index to quantify the co-location frequency of different features in flow neighborhoods, and then employ a bottom-up method to discover all frequent FCLPs. To further establish the statistical significance of the results, we develop a flow pattern reconstruction method to model the benchmark null hypothesis of independence conditioning on univariate flow characteristics (e.g. flow autocorrelation). Synthetic experiments with predefined FCLPs verify the advantages of our method in terms of correctness over available alternatives. A case study using individual home-work commuting flow data in the Chicago Metropolitan Area demonstrates that residence- or workplace-based co-location patterns tend to overestimate the co-location frequency of people with different occupations and could lead to inconsistent results. Numéro de notice : A2022-256 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2021.1980217 Date de publication en ligne : 20/09/2021 En ligne : https://doi.org/10.1080/13658816.2021.1980217 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100229 [article]

Identification and classification of routine locations using anonymized mobile communication data / Gonçalo Ferreira in ISPRS International journal of geo-information, vol 11 n° 4 (April 2022)  

Public [article]  inISPRS International journal of geo-information > vol 11 n° 4 (April 2022) . - n° 228 Titre : Identification and classification of routine locations using anonymized mobile communication data Type de document : Article/Communication Auteurs : Gonçalo Ferreira, Auteur ; Ana Alves, Auteur ; Marco Veloso, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 228 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes IGN] analyse de groupement [Termes IGN] classification barycentrique [Termes IGN] données spatiotemporelles [Termes IGN] migration pendulaire [Termes IGN] mobilité urbaine [Termes IGN] origine - destination [Termes IGN] point d'intérêt [Termes IGN] Portugal [Termes IGN] précision sémantique [Termes IGN] statistiques d'appels détaillés [Termes IGN] téléphonie mobile Résumé : (auteur) Digital location traces are a relevant source of insights into how citizens experience their cities. Previous works using call detail records (CDRs) tend to focus on modeling the spatial and temporal patterns of human mobility, not paying much attention to the semantics of places, thus failing to model and enhance the understanding of the motivations behind people’s mobility. In this paper, we applied a methodology for identifying individual users’ routine locations and propose an approach for attaching semantic meaning to these locations. Specifically, we used circular sectors that correspond to cellular antennas’ signal areas. In those areas, we found that all contained points of interest (POIs), extracted their most important attributes (opening hours, check-ins, category) and incorporated them into the classification. We conducted experiments with real-world data from Coimbra, Portugal, and the initial experimental results demonstrate the effectiveness of the proposed methodology to infer activities in the user’s routine areas. Numéro de notice : A2022-286 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.3390/ijgi11040228 Date de publication en ligne : 29/03/2022 En ligne : https://doi.org/10.3390/ijgi11040228 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100306 [article]

Spatial modeling of migration using GIS-based multi-criteria decision analysis: A case study of Iran / Naeim Mijani in Transactions in GIS, vol 26 n° 2 (April 2022)  

Public [article]  inTransactions in GIS > vol 26 n° 2 (April 2022) . - pp 645 - 668 Titre : Spatial modeling of migration using GIS-based multi-criteria decision analysis: A case study of Iran Type de document : Article/Communication Auteurs : Naeim Mijani, Auteur ; Davoud Shahpari Sani, Auteur ; Mohsen Dastaran, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 645 - 668 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes IGN] analyse multicritère [Termes IGN] approche hiérarchique [Termes IGN] changement climatique [Termes IGN] coefficient de corrélation [Termes IGN] combinaison linéaire ponderée [Termes IGN] données démographiques [Termes IGN] données socio-économiques [Termes IGN] Iran [Termes IGN] migration humaine [Termes IGN] modélisation spatiale [Termes IGN] planification urbaine [Termes IGN] système d'information géographique Résumé : (auteur) Spatial modeling of migration and the identification of the effective parameters are imperative for planning and managing demographic, economic, social, and environmental changes on various geographical scales. The recent climate change stressors as well as inequality in terms of education and life quality have triggered internal mass migrations in Iran, causing pressure on housing, the job market, and potential slums around large cities. This study proposes a new approach to modeling migration patterns in Iran based on multi-criteria decision analysis. For this purpose, a total of 23 individual criteria embedded within four criteria groups (economic, socio-cultural, welfare, and environmental) affecting national migration were used. The analytic hierarchy process was employed to determine weights for the input factors and the weighted linear combination (WLC) model was used for the integration of criteria, based on which maps of migration potential were produced. The model applied was evaluated based on the correlation coefficient between migration potential values obtained from the WLC model and the actual net migration rate. Among the input individual criteria, unemployment, higher education centers, number of physicians, and dust storms were found to influence national migration. Furthermore, our findings reveal that the potential for migration across Iranian provinces is heterogeneous, with the spatial potential for emigration being the highest and lowest in the border and central provinces, respectively. The correlation coefficient calculated between outputs from the WLC model and the net migration rate from 2011 to 2016, was .81, indicating the relatively high performance of the proposed model in producing a migration spatial potential map. Our proposed approach, along with the results achieved, can be useful to decision-makers and planners in designing data-driven policies against inequality- and climate-induced stressors. Numéro de notice : A2022-363 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.1111/tgis.12873 Date de publication en ligne : 23/11/2021 En ligne : https://doi.org/10.1111/tgis.12873 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100582 [article]

Assessing COVID-induced changes in spatiotemporal structure of mobility in the United States in 2020: a multi-source analytical framework / Evgeny Noi in International journal of geographical information science IJGIS, vol 36 n° 3 (March 2022)  

Permalink

Changing mobility patterns in the Netherlands during COVID-19 outbreak / Sander Van Der Drift in Journal of location-based services, vol 16 n° 1 (March 2022)  

Permalink

Dynamic linkage between urbanization, electrical power consumption, and suitability analysis using remote sensing and GIS techniques / Muhammad Nasar Ahmad in Photogrammetric Engineering & Remote Sensing, PERS, vol 88 n° 3 (March 2022)  

Permalink

Early warning of COVID-19 hotspots using human mobility and web search query data / Takahiro Yabe in Computers, Environment and Urban Systems, vol 92 (March 2022)  

Permalink

Understanding the movement predictability of international travelers using a nationwide mobile phone dataset collected in South Korea / Yang Xu in Computers, Environment and Urban Systems, vol 92 (March 2022)  

Permalink

Measuring and mapping long-term changes in migration flows using population-scale family tree data / Caglar Koylu in Cartography and Geographic Information Science, vol 49 n° 2 (February 2022)  

Permalink

Novel model for predicting individuals’ movements in dynamic regions of interest / Xiaoqi Shen in GIScience and remote sensing, vol 59 n° 1 (2022)  

Permalink

SNN_flow: a shared nearest-neighbor-based clustering method for inhomogeneous origin-destination flows / Qiliang Liu in International journal of geographical information science IJGIS, vol 36 n° 2 (February 2022)  

Permalink

Atlas of global change risk of population and economic systems / Peijun Shi (2022)  

Permalink

Contextual location recommendation for location-based social networks by learning user intentions and contextual triggers / Seyyed Mohammadreza Rahimi in Geoinformatica [en ligne], vol 26 n° 1 (January 2022)  

Permalink