Graph-based spatial co-location pattern mining: integrate geospatial analysis and logical reasoning DOI Creative Commons
Jinghan Wang,

Tinghua Ai,

Hao Wu

et al.

International Journal of Digital Earth, Journal Year: 2024, Volume and Issue: 17(1)

Published: Aug. 13, 2024

Spatial co-location patterns reflect the inherent correlations among geographical elements. Mining of POIs can provide valuable insights for urban planning and resource management. Generally, mining comprises two steps: proximity relationship determination (geospatial analysis) frequent pattern recursion (logical reasoning). Previous methods often separate these serializing relationships to enumerate sequences. However, this approach suffers from limited flexibility intuitiveness: as continuous spatial contexts are segmented into numerous small parts, it fails adequately represent geographic hinders effective visualization logical reasoning. Facing challenges, study proposes a novel graph-based method (GSCM), which leverages graphs integrate geospatial analysis Initially, establish adjacency relationships, GSCM constructs adaptive neighborhood graph, dynamically adjusts thresholds accommodate heterogeneity. Subsequently, Apriori recursive process is realized on graph structure. By leveraging searching, pruning, growing, potential growth directions identified, enhancing both efficiency intuition recursion. Through experiments conducted large-scale POI datasets Wuhan, compared with existing baseline methods, verifying its uncover in complex contexts.

Language: Английский

Analysis of the Surface Urban Heat Island Effect and the Spatiotemporal Heterogeneity of Its Driving Factors DOI
Xin Rao, Haifu Cui, Jiaying Dong

et al.

Transactions in GIS, Journal Year: 2025, Volume and Issue: 29(1)

Published: Feb. 1, 2025

ABSTRACT The surface urban heat island (SUHI) effect presents a significant challenge in environments. However, there is spatiotemporal variability the SUHI and its drivers, which often overlooked. To address this issue, study employs geographically temporally weighted regression (GTWR) model to analyze heterogeneity of driving factors. findings reveal following: (1) SUHIs central area Wuhan are located mainly on both sides Yangtze Han Rivers, most notably Qingshan Industrial Zone; (2) city center, land temperature (LST) strongly positively correlated with bare soil index (BSI), normalized difference built‐up (NDBI), vegetation (NDVI), nighttime light (NTL); (3) clear temporal disparities exist between LST NDBI, NDWI, NTL factors displaying notable variations; (4) comprehensive analysis has yielded quantitative relationships associated drivers. In summary, it been proven that differences Therefore, impact should be considered when studying mitigation effect.

Language: Английский

Citations

0
Resilient high-end equipment manufacturing supply chain design with irreplaceable suppliers: An IFTOPSIS-MOMIP hybrid model DOI
Handong Zheng, Xin Ye, Rongsheng Chen

et al.

Transportation Research Part E Logistics and Transportation Review, Journal Year: 2025, Volume and Issue: 195, P. 103914 - 103914

Published: Feb. 5, 2025

Language: Английский

Citations

0
Central Place Theory Based on Mobile Signal Data: The Case of Urban Parks in Beijing and Changsha DOI Creative Commons
Ning Wen, Hang Yin, Zhanhong Ma

et al.

Land, Journal Year: 2025, Volume and Issue: 14(4), P. 673 - 673

Published: March 22, 2025

The Central Place Theory (CPT) proposed the basic concepts of central places and their service areas. Urban parks provide a wide variety ecosystem services to residents. Most studies on focus urban commercial facilities; however, it remains unclear whether exhibit patterns places, what features areas, hierarchical structures. Based mobile signaling data, we identified dominant influence structures Beijing Changsha. We also analyzed factors influencing structure park services, as well number visitors areas at each level parks. found that visits by residents in Changsha clear structure. Parks occupy top attract large demonstrate strong capacity extensive coverage. area infrastructure attributes are significantly correlated with outcomes but entirely different results Beijing. Box plot analysis visitor numbers reveals for these two aspects differ. Overall, both cities’ centrality providing residents; there is considerable difference cities. These conclusions important theoretical support government officials better understand characteristics offer practical guidance optimizing planning, enhancing efficiency, formulating policies promote equitable access green spaces.

Language: Английский

Citations

0
Graph-based spatial co-location pattern mining: integrate geospatial analysis and logical reasoning DOI Creative Commons
Jinghan Wang,

Tinghua Ai,

Hao Wu

et al.

International Journal of Digital Earth, Journal Year: 2024, Volume and Issue: 17(1)

Published: Aug. 13, 2024

Spatial co-location patterns reflect the inherent correlations among geographical elements. Mining of POIs can provide valuable insights for urban planning and resource management. Generally, mining comprises two steps: proximity relationship determination (geospatial analysis) frequent pattern recursion (logical reasoning). Previous methods often separate these serializing relationships to enumerate sequences. However, this approach suffers from limited flexibility intuitiveness: as continuous spatial contexts are segmented into numerous small parts, it fails adequately represent geographic hinders effective visualization logical reasoning. Facing challenges, study proposes a novel graph-based method (GSCM), which leverages graphs integrate geospatial analysis Initially, establish adjacency relationships, GSCM constructs adaptive neighborhood graph, dynamically adjusts thresholds accommodate heterogeneity. Subsequently, Apriori recursive process is realized on graph structure. By leveraging searching, pruning, growing, potential growth directions identified, enhancing both efficiency intuition recursion. Through experiments conducted large-scale POI datasets Wuhan, compared with existing baseline methods, verifying its uncover in complex contexts.

Language: Английский

Citations

1