Centre de documentation
scientifique

Dépouillements

STICC: a multivariate spatial clustering method for repeated geographic pattern discovery with consideration of spatial contiguity / Yuhao Kang in International journal of geographical information science IJGIS, vol 36 n° 8 (August 2022)  

Public [article]  inInternational journal of geographical information science IJGIS > vol 36 n° 8 (August 2022) . - pp 1518 - 1549 Titre : STICC: a multivariate spatial clustering method for repeated geographic pattern discovery with consideration of spatial contiguity Type de document : Article/Communication Auteurs : Yuhao Kang, Auteur ; Kunlin Wu, Auteur ; Song Gao, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 1518 - 1549 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes IGN] analyse de groupement [Termes IGN] analyse multivariée [Termes IGN] champ aléatoire de Markov [Termes IGN] distribution spatiale [Termes IGN] matrice de covariance [Termes IGN] matrice de Toeplitz [Termes IGN] motif séquentiel [Termes IGN] régionalisation (segmentation) Résumé : (auteur) Spatial clustering has been widely used for spatial data mining and knowledge discovery. An ideal multivariate spatial clustering should consider both spatial contiguity and aspatial attributes. Existing spatial clustering approaches may face challenges for discovering repeated geographic patterns with spatial contiguity maintained. In this paper, we propose a Spatial Toeplitz Inverse Covariance-Based Clustering (STICC) method that considers both attributes and spatial relationships of geographic objects for multivariate spatial clustering. A subregion is created for each geographic object serving as the basic unit when performing clustering. A Markov random field is then constructed to characterize the attribute dependencies of subregions. Using a spatial consistency strategy, nearby objects are encouraged to belong to the same cluster. To test the performance of the proposed STICC algorithm, we apply it in two use cases. The comparison results with several baseline methods show that the STICC outperforms others significantly in terms of adjusted rand index and macro-F1 score. Join count statistics is also calculated and shows that the spatial contiguity is well preserved by STICC. Such a spatial clustering method may benefit various applications in the fields of geography, remote sensing, transportation, and urban planning, etc. Numéro de notice : A2022-591 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2022.2053980 Date de publication en ligne : 30/03/2022 En ligne : https://doi.org/10.1080/13658816.2022.2053980 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101282 [article]

Location-aware neural graph collaborative filtering / Shengwen Li in International journal of geographical information science IJGIS, vol 36 n° 8 (August 2022)  

Public [article]  inInternational journal of geographical information science IJGIS > vol 36 n° 8 (August 2022) . - pp 1550 - 1574 Titre : Location-aware neural graph collaborative filtering Type de document : Article/Communication Auteurs : Shengwen Li, Auteur ; Chenpeng Sun, Auteur ; Renyao Chen, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 1550 - 1574 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique web [Termes IGN] comportement [Termes IGN] données localisées des bénévoles [Termes IGN] filtrage d'information [Termes IGN] jeu de données [Termes IGN] noeud [Termes IGN] point d'intérêt [Termes IGN] réseau neuronal de graphes Résumé : (auteur) Collaborative filtering (CF) is initiated by representing users and items as vectors and seeks to describe the relationship between users and items at a profound level, thus predicting users’ preferred behavior. To address the issue that previous research ignored higher-order geographical interactions hidden in users’ historical behaviors, this paper proposes a location-aware neural graph collaborative filtering model (LA-NGCF), which incorporates location information of items for improving prediction performance. The model characterizes the interactions between items based on spatial decay law from a graph perspective and designs two strategies to capture the interaction effects of users and items considering node heterogeneity. An optimized loss function with spatial distances of items is also developed in the model. Extensive experiments are conducted on three publicly available real-world datasets to examine the effectiveness of our model. Results show that LA-NGCF achieves competitive performances compared with several state-of-the-art models, which suggests that location information of items is beneficial for improving the performance of personalized recommendations. This paper offers an approach to incorporate weighted interactions between items into CF algorithms and enriches the methods of utilizing geographical information for artificial intelligence applications. Numéro de notice : A2022-592 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2022.2073594 Date de publication en ligne : 11/05/2022 En ligne : https://doi.org/10.1080/13658816.2022.2073594 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101292 [article]

Uncertainty interval estimates for computing slope and aspect from a gridded digital elevation model / Carlos López-Vázquez in International journal of geographical information science IJGIS, vol 36 n° 8 (August 2022)  

Public [article]  inInternational journal of geographical information science IJGIS > vol 36 n° 8 (August 2022) . - pp 1601 - 1628 Titre : Uncertainty interval estimates for computing slope and aspect from a gridded digital elevation model Type de document : Article/Communication Auteurs : Carlos López-Vázquez, Auteur Année de publication : 2022 Article en page(s) : pp 1601 - 1628 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications photogrammétriques [Termes IGN] géomorphométrie [Termes IGN] incertitude des données [Termes IGN] modèle numérique de surface [Termes IGN] modèle numérique de terrain [Termes IGN] pente Résumé : (auteur) The first order derivatives of a Digital Elevation Model (DEM) defined over a regular grid are usually computed without an uncertainty estimate. The standard procedure involves a compact 3 × 3 window. Using a Taylor expansion, an uncertainty interval for each partial derivative as a function of the cell size was devised using two estimates, either of different resolution or of different order. The intervals for slope and aspect can be derived afterwards. We carried out an experiment comparing some different estimates of the slope and aspect over a synthetic surface representative of a real topography and amenable to offer an exact derivative. The partial derivatives were numerically estimated with four different procedures: the Simple procedure defined by Jones over a 2 × 2 window, the Evans–Young procedure using a centered difference over a 3 × 3 window, and using a 5 × 5 window both with an extrapolated Evans–Young procedure and the expression due to Florinsky. The results confirm that intervals for both slope and aspect always included the exact value even after drastically increasing the cell size. Finally, a real case with an integer-valued DEM was considered, illustrating the combined effect of Representation and Truncation error. Numéro de notice : A2022-623 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2022.2063294 Date de publication en ligne : 07/06/2022 En ligne : https://doi.org/10.1080/13658816.2022.2063294 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101367 [article]

Cost distances and least cost paths respond differently to cost scenario variations: a sensitivity analysis of ecological connectivity modeling / Paul Savary in International journal of geographical information science IJGIS, vol 36 n° 8 (August 2022)  

Public [article]  inInternational journal of geographical information science IJGIS > vol 36 n° 8 (August 2022) . - pp 1652-1676 Titre : Cost distances and least cost paths respond differently to cost scenario variations: a sensitivity analysis of ecological connectivity modeling Type de document : Article/Communication Auteurs : Paul Savary, Auteur ; Jean-Christophe Foltête, Auteur ; Stéphane Garnier, Auteur Année de publication : 2022 Article en page(s) : pp 1652-1676 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes IGN] analyse de sensibilité [Termes IGN] chemin le moins coûteux, algorithme du [Termes IGN] connexité (topologie) [Termes IGN] coût Résumé : (auteur) Biodiversity conservation measures designed to ensure ecological connectivity depend on the reliable modeling of species movements. Least-cost path modeling makes it possible to identify the most likely dispersal paths within a landscape and provide two items of ecological relevance: (i) the spatial location of these least-cost paths (LCPs) and (ii) the accumulated cost along them (’cost distance’, CD). This spatial analysis requires that cost values be assigned to every type of land cover. The sensitivity of both LCPs and CDs to the cost scenarios has not been comprehensively assessed across realistic landscapes and diverging cost scenarios. We therefore assessed it in diverse landscapes sampled over metropolitan France and with widely diverging cost scenarios. The spatial overlap of the LCPs was more sensitive to the cost scenario than the CD values were. In addition, highly correlated CD matrices can be derived from very different cost scenarios. Although the range of the cost values and the properties of each cost scenario significantly influenced the outputs of LCP modeling, landscape composition and configuration variables also explained their variations. Accordingly, we provide guidelines for the use of LCP modeling in ecological studies and conservation planning. Numéro de notice : A2022-614 Affiliation des auteurs : non IGN Thématique : BIODIVERSITE/GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2021.2014852 Date de publication en ligne : 21/12/2021 En ligne : https://doi.org/10.1080/13658816.2021.2014852 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101368 [article]