Geographical Analysis最新文献

{"title":"On the Distribution of Spatial Polarization Indices","authors":"Sergio J. Rey","doi":"10.1111/gean.70064","DOIUrl":"https://doi.org/10.1111/gean.70064","url":null,"abstract":"<div>\u0000 \u0000 <p>This paper develops a statistical framework for inference on recently developed spatial polarization indices and clarifies their relationship to spatial inequality and dependence. The framework builds on a graph-theoretic decomposition of polarization into global, meso, and local components and accommodates an asymmetry common in regional economic data: low-income areas often form cohesive clusters, whereas high-income areas are more spatially fragmented. The principal contributions are a graph-preserving randomization procedure and asymptotic results for the spatial polarization index. These methods permit assessment of the significance and robustness of observed polarization patterns while connecting spatial statistics, inequality decomposition, and graph theory. A series of Monte Carlo experiments examines the properties of the inferential methods. Two case studies focusing on polarization in Mexico and the United States provide empirical illustrations.</p>\u0000 </div>","PeriodicalId":12533,"journal":{"name":"Geographical Analysis","volume":"59 1","pages":""},"PeriodicalIF":2.4,"publicationDate":"2026-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149177048","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Spatially Weighted Relative Deprivation Index: Incorporating Spatial Structure Into Regional Inequality Measurement","authors":"Kyungjae Lee","doi":"10.1111/gean.70060","DOIUrl":"https://doi.org/10.1111/gean.70060","url":null,"abstract":"<div>\u0000 \u0000 <p>Regional inequality is conventionally assessed based on the distribution of economic outcomes across regions. However, regional disparities are spatially structured because regional economic outcomes are interdependent across space. Existing approaches generally capture either the spatial dimension of inequality at an aggregate level or unit-specific disadvantage without incorporating spatial relevance. This study proposes a Spatially Weighted Relative Deprivation (SWRD) index that combines the one-sided upward-gap rule of relative deprivation (RD) with an empirically calibrated spatial weighting structure. Using real gross regional domestic product (GRDP) for 229 Korean districts from 2015 to 2021, the study estimates the distance decay of spatial dependence and constructs annual SWRD values. The empirical comparison shows that SWRD produces spatial patterns and regional rankings that differ from conventional RD. Spatial permutation tests indicate that high SWRD values are unlikely under random spatial reassignment. Monte Carlo simulations on a uniform lattice further show that the divergence between RD and SWRD increases with stronger spatial dependence, steeper distance decay, and greater dispersion and right skewness. These findings show that incorporating spatial structure can change assessments of regional disadvantage under varying spatial and distributional conditions.</p>\u0000 </div>","PeriodicalId":12533,"journal":{"name":"Geographical Analysis","volume":"59 1","pages":""},"PeriodicalIF":2.4,"publicationDate":"2026-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149177047","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ML-SAS: A Machine-Learning-Based Spatial Autocorrelation Statistic for Mixed-Type Data","authors":"Woohyung Kim,&nbsp;Sang-Il Lee","doi":"10.1111/gean.70062","DOIUrl":"https://doi.org/10.1111/gean.70062","url":null,"abstract":"<div>\u0000 \u0000 <p>Existing measures of multivariate spatial autocorrelation often rely on covariance structures or fixed distances that are difficult to apply to nonlinear and mixed-type attributes. This paper proposes the Machine-Learning-Based Spatial Autocorrelation Statistic (ML-SAS), which combines a spatial weights matrix with an attribute-similarity matrix learned from unsupervised random-forest path proximities. Global and local statistics are defined within a generalized matrix-correlation framework, with analytical randomization moments as theoretical references and rank-based permutation tests for inference. Simulations assess correspondence with classical statistics, sensitivity to forest specifications and proximity definitions, null calibration, and local detection under continuous and nonlinear mixed-type processes. Path-based ML-SAS was stable across the tested forest settings and less sensitive than terminal-node proximity. Under the spatial null, the empirical probability of any rejection was 0.040. In a continuous multivariate design, ML-SAS was more selective than Multivariate Local Geary. In a nonlinear mixed-type design, adding a nominal attribute substantially increased recall and F1 relative to continuous-only ML-SAS, and leave-one-variable-out analysis identified that attribute as the largest contributor to changes in the local similarity surface. In Dutch municipalities, adding ordered urbanity changed 23 local classifications. ML-SAS provides a complementary framework for jointly analyzing continuous and categorical spatial attributes.</p>\u0000 </div>","PeriodicalId":12533,"journal":{"name":"Geographical Analysis","volume":"58 4","pages":""},"PeriodicalIF":2.4,"publicationDate":"2026-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149146245","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Scale-Conditioned Geometry: How Measurement Resolution Induces Distance, Proximity, and Spatial Dependence","authors":"Eric Vaz","doi":"10.1111/gean.70061","DOIUrl":"https://doi.org/10.1111/gean.70061","url":null,"abstract":"<p>Scale is central to inference in natural and social systems, and geography and ecology have treated it as an explicit object of theory for decades. This paper builds on that work with a formal view in which scale is a degree of freedom of description, parameterizing both the mappings between representations and the metric defining distance and neighborhood. Distance is induced by the representation and can change with resolution even when the underlying system is unchanged. In simulated autocorrelated fields aggregated across seven block sizes (30 Monte Carlo replications), Moran's <i>I</i> declines by a factor of 3.4 while a correlation-threshold range proxy remains comparatively stable. An explicit metric on the family of representations (Fused Gromov–Wasserstein) shows that scale and zoning are distinct, measurable directions. A change-of-support null describes the change expected from information loss under a single correlation structure; a mixed-scale scenario departs from it at six of seven scales, which rejects that null without by itself establishing a change in coupling. Two observational datasets, each analyzed at a single support, show that the induced metric changes global and local dependence. These results motivate a scale-explicit workflow that treats proximity and dependence as conditional on representation.</p>","PeriodicalId":12533,"journal":{"name":"Geographical Analysis","volume":"58 4","pages":""},"PeriodicalIF":2.4,"publicationDate":"2026-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/gean.70061","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149145973","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Capturing Non-Linear Neighborhood Structure: An Autoencoder Approach to Census-Based Dimensionality Reduction for Residential Differentiation","authors":"Alex Singleton,&nbsp;Owen Goodwin,&nbsp;Stef De Sabbata","doi":"10.1111/gean.70059","DOIUrl":"https://doi.org/10.1111/gean.70059","url":null,"abstract":"<p>Dimensionality reduction is fundamental to applied spatial data analysis, condensing high-dimensional indicators into parsimonious representations for mapping and modeling. Principal component analysis (PCA) remains a dominant approach, yet its linearity assumptions constrain its capacity to capture the complex, non-linear dependencies characteristic of spatial socio-economic data. We evaluate the effectiveness of autoencoders as a flexible, parametric alternative for constructing composite measures of neighborhood structure. Through encoder-decoder architectures, AEs learn non-linear representations that better reflect underlying data complexity, enable projection of new observations without refitting, and provide reconstruction-based diagnostics that enhance transparency. We demonstrate the approach using small-area data from the 2021 Census of England and Wales, evaluating how effectively AEs summarize spatial variability and recover composite dimensions of residential differentiation compared with PCA.</p>","PeriodicalId":12533,"journal":{"name":"Geographical Analysis","volume":"58 4","pages":""},"PeriodicalIF":2.4,"publicationDate":"2026-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/gean.70059","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149146724","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"M-SGWR: Multiscale Attribute-Similarity and Geographically Weighted Regression","authors":"M. Naser Lessani,&nbsp;Zhenlong Li,&nbsp;Manzhu Yu,&nbsp;Helen Greatrex,&nbsp;Chan Shen","doi":"10.1111/gean.70058","DOIUrl":"https://doi.org/10.1111/gean.70058","url":null,"abstract":"<p>The first law of geography is a cornerstone of spatial analysis, emphasizing that nearby locations tend to be more strongly related and similar. However, defining what constitutes “near” and “related” remains challenging because different phenomena operate across distinct spatial dimensions, including physical, social, and network-based spaces. Conventional local regression models, such as GWR and MGWR, represent nearness and relatedness primarily through geographic proximity. In an era of globalization and digital connectivity, however, geographic proximity alone may not adequately characterize relationships among locations, as many phenomena are shaped by connections that extend beyond physical distance. To address this limitation, we propose a new model, termed M-SGWR, that characterizes relationships among locations in two dimensions: geographic space and predictor-specific attribute space. For each predictor, geographic and attribute-similarity weight matrices are constructed separately and combined using an optimized parameter, <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mi>α</mi>\u0000 </mrow>\u0000 <annotation>$$ alpha $$</annotation>\u0000 </semantics></math>, which determines their relative contributions to local model estimation. Analogous to the predictor-specific bandwidths used in MGWR, the optimal <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mi>α</mi>\u0000 </mrow>\u0000 <annotation>$$ alpha $$</annotation>\u0000 </semantics></math> varies across predictors, allowing M-SGWR to identify geographically dominant, mixed, or attribute-dominant relationships, including similarities among geographically distant locations. Results from two simulation experiments and one empirical application demonstrate that M-SGWR consistently outperforms GWR, SGWR, and MGWR across the evaluated goodness-of-fit measures.</p>","PeriodicalId":12533,"journal":{"name":"Geographical Analysis","volume":"58 4","pages":""},"PeriodicalIF":2.4,"publicationDate":"2026-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/gean.70058","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149047933","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Beyond the Border Wars: Representation, Scale, and Multi-Member Districts","authors":"Christopher S. Fowler,&nbsp;Linda L. Fowler","doi":"10.1111/gean.70057","DOIUrl":"https://doi.org/10.1111/gean.70057","url":null,"abstract":"<p>Proposed redistricting reforms often focus on fixing gerrymandered maps or restructuring elections to boost proportionality. Recent work shows that, averaged across all 50 states, multi-member districts paired with proportional ranked-choice voting can deliver near-proportional outcomes while curbing the gains available to a partisan map-drawer. We use the case of Pennsylvania to show that the effect of any given reform depends on how the size and location of a state's population clusters align with the size of its districts, a geographic interaction that resists one-size-fits-all prescription. Moreover, complex relationships among population clusters, district size, and administrative units like counties may limit the benefits of multi-member districts. Enlarging districts to elect multiple representatives increases the heterogeneity of district populations, increases competitiveness, and broadens opportunities for effective representation across most of the state. However, proportionality and opportunities for Black voters to elect preferred candidates move unevenly. We argue that the match between district magnitude and cluster size must be considered for reforms to succeed.</p>","PeriodicalId":12533,"journal":{"name":"Geographical Analysis","volume":"58 4","pages":""},"PeriodicalIF":2.4,"publicationDate":"2026-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/gean.70057","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148994139","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Congruence and Compatibility in Functional Regional Taxonomy: Principles and Applications","authors":"Marián Halás","doi":"10.1111/gean.70055","DOIUrl":"https://doi.org/10.1111/gean.70055","url":null,"abstract":"<p>The article connects several concepts that were previously used and evaluated separately in functional regional taxonomy and in the delineation of functional regions. Typically, functional regions are not defined based on absolute values of population flows. Instead, they are delineated using interaction measures, which are normalizations of population flows. In the resulting system of functional regions, it is possible to determine a membership index for each basic spatial unit, expressing the degree to which that unit belongs to the functional region in which it is located. The membership index used should be in congruence with the interaction measure applied. This means they should be based on the same normalization method. Using the example of two different states, two different datasets, and two different interaction measures with their corresponding membership indices, we demonstrate the necessity of congruence: interaction measure—functional region boundaries—membership indices. An important part of the article's outputs is the visual representation of this congruence through map outputs. The results confirm that different interaction measures yield significantly different delineations of functional regions. Only when the interaction measure and the membership index are in congruence are the procedures' logical correctness and the results' compatibility maintained.</p>","PeriodicalId":12533,"journal":{"name":"Geographical Analysis","volume":"58 4","pages":""},"PeriodicalIF":2.4,"publicationDate":"2026-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/gean.70055","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148942410","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Network-Constrained Spatiotemporal Scan Statistic for Identifying Geographic Flow Hotspots","authors":"Zhuoting Fu,&nbsp;Xiaorui Yan,&nbsp;Tao Pei,&nbsp;Ci Song,&nbsp;Jie Chen,&nbsp;Dayu Cheng,&nbsp;Xiaotong Wang,&nbsp;Yuqing Wang","doi":"10.1111/gean.70056","DOIUrl":"https://doi.org/10.1111/gean.70056","url":null,"abstract":"<div>\u0000 \u0000 <p>Geographic flows represent the movement of geographic objects between locations at different times. Flow hotspots reflect aggregated movements within specific spatiotemporal ranges. Accurately identifying these hotspots helps reveal their underlying causes and provides targeted insights. Among existing methods, scan statistics are widely used due to their flexible windows and unified significance testing. However, traditional Euclidean cylindrical windows are inadequate for road networks. Spatiotemporal scanning windows of network-constrained flows must account for network topology and origin–destination temporal precedence. To address this issue, this study proposes a novel spatiotemporal scanning window that integrates network topology and temporal constraints and develops the scan statistic under completely spatiotemporal randomness (CSTR) and global time permutation (GTP) null models. Constructed via the Cartesian product of origin and destination network-constrained prisms, the window adaptively extends along road networks to precisely capture flow distribution. Synthetic experiments demonstrate that our method outperforms baseline methods in identifying hotspots within complex scenarios. Case studies show that the CSTR model effectively identifies dominant macroscopic tidal travel patterns (such as commuting hotspots), whereas the GTP model successfully overcomes the interference from inhomogeneous backgrounds to accurately capture fine-grained flow hotspots during off-peak hours and between specific transit hubs.</p>\u0000 </div>","PeriodicalId":12533,"journal":{"name":"Geographical Analysis","volume":"58 4","pages":""},"PeriodicalIF":2.4,"publicationDate":"2026-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148848640","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Spatial Clustering Approach of Economic Activities: An Application to the Agribusiness Sector in Brazil's Midwest Region","authors":"Gilvan Santos do Rosario Junior,&nbsp;Ticiana Grecco Zanon Moura,&nbsp;Mauro Ferrante","doi":"10.1111/gean.70054","DOIUrl":"https://doi.org/10.1111/gean.70054","url":null,"abstract":"<p>The spatial distribution of economic activities is central to regional economics. However, empirical tools for comparing industries based on the similarity of their spatial distributions remain limited. Traditional cluster analysis typically ignores geographical distance and connectivity, while spatial methods focus on clustering places rather than economic activities. This paper addresses this methodological gap by proposing a framework for clustering economic activities based on the similarity of their spatial distributions, explicitly incorporating geographical space. The Wasserstein distance is employed with a geographically informed cost matrix, that is, the Shimbel matrix, to measure the effort required to transform one activity's spatial distribution into another. This approach is compared with traditional non-spatial distance metrics through an illustrative example and then applied to 272 agribusiness activities across 466 municipalities in Brazil's Midwest region from 2013 to 2021. The results reveal four main clusters: one spread throughout the region and others concentrated in northern, southern, or eastern areas, consistent with regional endowments, historical trajectories, and agro-industrial linkages. The case study suggests that the approach offers a useful complementary tool for identifying co-distributed activities and spatially similar industrial patterns, with implications for regional development analysis, place-based policy design and future studies of economic linkages and shock exposure.</p>","PeriodicalId":12533,"journal":{"name":"Geographical Analysis","volume":"58 4","pages":""},"PeriodicalIF":2.4,"publicationDate":"2026-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/gean.70054","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148615490","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}