Centre dedocumentation
scientifique

Geographically convolutional neural network weighted regression: a method for modeling spatially non-stationary relationships based on a global spatial proximity grid / Zhen Dai in International journal of geographical information science IJGIS, vol 36 n° 11 (November 2022)  

Public [article]  inInternational journal of geographical information science IJGIS > vol 36 n° 11 (November 2022) . - pp 2248 - 2269 Titre : Geographically convolutional neural network weighted regression: a method for modeling spatially non-stationary relationships based on a global spatial proximity grid Type de document : Article/Communication Auteurs : Zhen Dai, Auteur ; Sensen Wu, Auteur ; Yuanyuan Wang, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 2248 - 2269 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes IGN] distribution spatiale [Termes IGN] modèle de régression [Termes IGN] régression géographiquement pondérée [Termes IGN] régression linéaire [Termes IGN] réseau neuronal convolutif Résumé : (auteur) Geographically weighted regression (GWR) is a classical method of modeling spatially non-stationary relationships. The geographically neural network weighted regression (GNNWR) model solves the problem of the inaccurate construction of spatial weight kernels using a spatially weighted neural network. However, when the spatial distribution of observations is uneven, the spatial proximity expression in the input of GWR and GNNWR models does not fully represent the impact of the whole research space on the estimating point. Therefore, we established a global spatial proximity grid (GSPG) to express the spatial proximity of each estimating point and proposed a spatially weighted convolutional neural network (SWCNN) to extract the relationship between the GSPG and spatial weights. Finally, we proposed a geographically convolutional neural network weighted regression (GCNNWR) model combining SWCNN and ordinary linear regression (OLR) model to estimate spatial non-stationarity. We used two case studies of simulated data and real environment data to demonstrate the advancements of the GCNNWR model. The GCNNWR model achieved higher estimation accuracy and greater predictive power than the OLR, GWR, multi-scale GWR (MGWR), and GNNWR models. Moreover, the GCNNWR model maintained its better stability and accuracy in estimating spatially non-stationary relationships when the distribution of observations was uneven. Numéro de notice : A2022-773 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2022.2100892 Date de publication en ligne : 27/09/2022 En ligne : https://doi.org/10.1080/13658816.2022.2100892 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101954 [article]

Spatial regression graph convolutional neural networks: A deep learning paradigm for spatial multivariate distributions / Di Zhu in Geoinformatica [en ligne], vol 26 n° 4 (October 2022)  

Public [article]  inGeoinformatica [en ligne] > vol 26 n° 4 (October 2022) . - pp 645 - 676 Titre : Spatial regression graph convolutional neural networks: A deep learning paradigm for spatial multivariate distributions Type de document : Article/Communication Auteurs : Di Zhu, Auteur ; Yu Liu, Auteur ; Xin Yao, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 645 - 676 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique [Termes IGN] analyse spatiale [Termes IGN] apprentissage profond [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] distribution spatiale [Termes IGN] échantillonnage [Termes IGN] intelligence artificielle [Termes IGN] régression [Termes IGN] régression géographiquement pondérée [Termes IGN] réseau neuronal de graphes Résumé : (auteur) Geospatial artificial intelligence (GeoAI) has emerged as a subfield of GIScience that uses artificial intelligence approaches and machine learning techniques for geographic knowledge discovery. The non-regularity of data structures has recently led to different variants of graph neural networks in the field of computer science, with graph convolutional neural networks being one of the most prominent that operate on non-euclidean structured data where the numbers of nodes connections vary and the nodes are unordered. These networks use graph convolution – commonly known as filters or kernels – in place of general matrix multiplication in at least one of their layers. This paper suggests spatial regression graph convolutional neural networks (SRGCNNs) as a deep learning paradigm that is capable of handling a wide range of geographical tasks where multivariate spatial data needs modeling and prediction. The feasibility of SRGCNNs lies in the feature propagation mechanisms, the spatial locality nature, and a semi-supervised training strategy. In the experiments, this paper demonstrates the operation of SRGCNNs with social media check-in data in Beijing and house price data in San Diego. The results indicate that a well-trained SRGCNN model is capable of learning from samples and performing reasonable predictions for unobserved locations. The paper also presents the effectiveness of incorporating the idea of geographically weighted regression for handling heterogeneity between locations in the model approach. Compared to conventional spatial regression approaches, SRGCNN-based models tend to generate much more accurate and stable results, especially when the sampling ratio is low. This study offers to bridge the methodological gap between graph deep learning and spatial regression analytics. The proposed idea serves as an example to illustrate how spatial analytics can be combined with state-of-the-art deep learning models, and to enlighten future research at the front of GeoAI. Numéro de notice : A2022-865 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE/INFORMATIQUE Nature : Article DOI : 10.1007/s10707-021-00454-x Date de publication en ligne : 02/11/2021 En ligne : https://doi.org/10.1007/s10707-021-00454-x Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102158 [article]

The fractional vegetation cover (FVC) and associated driving factors of modeling in mining areas / Jun Li in Photogrammetric Engineering & Remote Sensing, PERS, vol 88 n° 10 (October 2022)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 88 n° 10 (October 2022) . - pp 665 - 671 Titre : The fractional vegetation cover (FVC) and associated driving factors of modeling in mining areas Type de document : Article/Communication Auteurs : Jun Li, Auteur ; Tianyu Guo, Auteur ; Chengye Zhang, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 665 - 671 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] analyse comparative [Termes IGN] Chine [Termes IGN] couvert végétal [Termes IGN] Google Earth Engine [Termes IGN] hétérogénéité spatiale [Termes IGN] image Landsat-ETM+ [Termes IGN] image Landsat-OLI [Termes IGN] industrie minière [Termes IGN] mine [Termes IGN] Normalized Difference Vegetation Index [Termes IGN] régression géographiquement pondérée [Termes IGN] régression multiple [Termes IGN] réseau neuronal artificiel Résumé : (auteur) To determine the fractional vegetation cover (FVC) and associated driving factors of modeling in mining areas, six types of data were used as driving factors and three methods —multi-linear regression (MLR), geographically weighted regression (GWR), and geographically weighted artificial neural network (GWANN)— were adopted in the modeling. The experiments, conducted in Shengli mining areas located in Xilinhot city, China, show that the MLR model without consideration of spatial heterogeneity and spatial non-stationarity performs the worst and that the GWR model presents obvious location differences, since it predefines a linear relationship which is unable to describe FVC for some locations. The GWANN model, improving on these defects, is the most suitable model for the FVC driving process in mining areas; it outperforms the other two models, with root-mean-square error (RMSE) and mean absolute percentage error (MAPE) reaching 0.16 and 0.20. It has improvements of approximately 24% in RMSE and 33% in MAPE compared to the MLR model, and those values grow to 59% and 71% when compared with the GWR model. Numéro de notice : A2022-813 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.14358/PERS.21-00070R3 Date de publication en ligne : 01/10/2022 En ligne : https://doi.org/10.14358/PERS.21-00070R3 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101973 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
105-2022101	SL	Revue	Centre de documentation	Revues en salle	Disponible

Mixed geographically and temporally weighted regression for spatio-temporal deformation modelling / Zhijia Yang in Survey review, vol 54 n° 385 (July 2022)  

Public [article]  inSurvey review > vol 54 n° 385 (July 2022) . - pp 290 - 300 Titre : Mixed geographically and temporally weighted regression for spatio-temporal deformation modelling Type de document : Article/Communication Auteurs : Zhijia Yang, Auteur ; Wujiao Dai, Auteur ; Wenkun Yu, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 290 - 300 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Topographie [Termes IGN] auscultation d'ouvrage [Termes IGN] barrage [Termes IGN] déformation d'édifice [Termes IGN] méthode fondée sur le noyau [Termes IGN] modèle de simulation [Termes IGN] modélisation spatio-temporelle [Termes IGN] régression géographiquement pondérée [Termes IGN] surveillance d'ouvrage Résumé : (auteur) When the regression coefficient of independent variable has both global stationarity and spatio-temporal non-stationarity properties, the deformation model based on the geographically and temporally weighted regression (GTWR) will no longer be applicable. In order to resolve this problem, we propose an improved method to establish the spatio-temporal deformation model using mixed geographically and temporally weighted regression (MGTWR). In this method, both the global regression coefficient and the variable regression coefficient are selected for regression coefficient hypothesis test, and the local linear two-step estimation method is used to fit the MGTWR model. A dam deformation modelling example shows that the MGTWR model improves the average prediction accuracy by 57.6% compared to the GTWR model when the regression coefficients have both global stationarity and spatio-temporal non-stationarity properties. Numéro de notice : A2022-534 Affiliation des auteurs : non IGN Thématique : MATHEMATIQUE/POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/00396265.2021.1935578 Date de publication en ligne : 10/06/2021 En ligne : https://doi.org/10.1080/00396265.2021.1935578 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101090 [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]

A cost-effective algorithm for calibrating multiscale geographically weighted regression models / Bo Wu in International journal of geographical information science IJGIS, vol 36 n° 5 (May 2022)  

Permalink

Unmixing-based spatiotemporal image fusion accounting for complex land cover changes / Xiaolu Jiang in IEEE Transactions on geoscience and remote sensing, vol 60 n° 5 (May 2022)  

Permalink

A geographically weighted artificial neural network / Julian Haguenauer in International journal of geographical information science IJGIS, vol 36 n° 2 (February 2022)  

Permalink

Combining a class-weighted algorithm and machine learning models in landslide susceptibility mapping: A case study of Wanzhou section of the Three Gorges Reservoir, China / Huijuan Zhang in Computers & geosciences, vol 158 (January 2022)  

Permalink

Modelling spatial processes in quantitative human geography / A. Stewart Fotheringham in Annals of GIS, vol 28 n° 1 (January 2022)  

Permalink

Identifying surface urban heat island drivers and their spatial heterogeneity in China’s 281 cities: An empirical study based on multiscale geographically weighted regression / Lu Niu in Remote sensing, vol 13 n° 21 (November-1 2021)  

Permalink

Multiscale geographically and temporally weighted regression with a unilateral temporal weighting scheme and its application in the analysis of spatiotemporal characteristics of house prices in Beijing / Zhi Zhang in International journal of geographical information science IJGIS, vol 35 n° 11 (November 2021)  

Permalink

Geographical and temporal huff model calibration using taxi trajectory data / Shuhui Gong in Geoinformatica [en ligne], vol 25 n° 3 (July 2021)  

Permalink

Parallel computing for fast spatiotemporal weighted regression / Xiang Que in Computers & geosciences, vol 150 (May 2021)  

Permalink

Utilizing urban geospatial data to understand heritage attractiveness in Amsterdam / Sevim Sezi Karayazi in ISPRS International journal of geo-information, vol 10 n° 4 (April 2021)  

Permalink