The limits of GIS: Towards a GIS of place

In this article we reflect back on our decade‐long collaboration on the geographies of the Holocaust to argue for a GIS of place. Our previous work on ghettoization in Budapest and on the spatio‐temporal patterns of Jewish persecution in Italy had a marked spatial dimension, both in the research questions we set out to answer and the methods we used, which were largely quantitative. During the course of our research, we progressively came to realize that a spatial perspective favors the voice of the perpetrator and that to fully comprehend and understand the geography of the Holocaust, we needed to engage with the voice of the victim, extend the set of methods and tools used, and broaden our epistemology. While proposing a fully‐fledged model of a qualitative GIS of the places and spaces of the Holocaust is beyond the scope of this article, we: (a) argue for the integration of social network analysis, corpus linguistics, and spatio‐temporal methods and for a mixed‐methods analytical approach and (b) note how the topological and relational foundations we identify as fundamental to a GIS of place parallel the long‐standing call for an “integrated history” of the Holocaust.     

核密度估计法支持下的网络空间POI点可视化与分析

城市空间POI点的分布模式、分布密度在基础设施规划、城市空间分析中具有重要意义,表达该特征的核密度法(kernel density estimation)由于顾及了地理学第一定律的区位影响,比其他密度表达方法(如样方密度、基于Voronoi图密度)占优。然而,传统的核密度计算方法往往基于二维延展的欧氏空间,忽略了城市网络空间中设施点的服务功能及相互联系发生于网络路径距离而非欧氏距离的事实。本研究针对该缺陷,给出了网络空间核密度计算模型,分析了核密度方法在置入网络结构中受多种约束条件的扩展模式,讨论了衰减阈值及高度极值对核密度特征表达的影响。通过实际多种POI点分布模式(随机型、稀疏型、区域密集型、线状密集型)下的核密度分析试验,讨论了POI基础设施在城市区域中的分布特征、影响因素、服务功能。     

Making direction a first‐class citizen of Tobler's first law of geography

Waldo Tobler frequently reminded us that the law named after him was nothing more than calling for exceptions. This article discusses one of these exceptions. Spatial relations between points are frequently modeled as vectors in which both distance and direction are of equal prominence. However, in Tobler's first law of geography, such a relation is described only from the perspective of distance by relating the decreasing similarity of observations in some attribute space to their increasing distance in geographic space. Although anisotropic versions of many geographic analysis techniques, such as directional semivariograms, anisotropy clustering, and anisotropic point pattern analysis, have been developed over the years, direction remains on the level of an afterthought. We argue that, compared to distance, directional information is still under‐explored and anisotropic techniques are substantially less frequently applied in everyday GIS analysis. Commonly, when classical spatial autocorrelation indicators, such as Moran's I, are used to understand a spatial pattern, the weight matrix is only built from distance, without direction being considered. Similarly, GIS operations, such as buffering, do not take direction into account either, with distance in all directions being treated equally. In reality, meanwhile, particularly in urban structures and when processes are driven by the underlying physical geography, direction plays an essential role. In this article we ask whether the development of early GIS, data (sample) sparsity, and Tobler's law lead to a theory‐induced blindness for the role of direction. If so, is it possible to envision direction becoming a first‐class citizen of equal importance to distance instead of being an afterthought only considered when the deviation from a perfect circle becomes too obvious to be ignored?     

Extracting urban functional regions from points of interest and human activities on location‐based social networks

Data about points of interest (POI) have been widely used in studying urban land use types and for sensing human behavior. However, it is difficult to quantify the correct mix or the spatial relations among different POI types indicative of specific urban functions. In this research, we develop a statistical framework to help discover semantically meaningful topics and functional regions based on the co‐occurrence patterns of POI types. The framework applies the latent Dirichlet allocation (LDA) topic modeling technique and incorporates user check‐in activities on location‐based social networks. Using a large corpus of about 100,000 Foursquare venues and user check‐in behavior in the 10 most populated urban areas of the US, we demonstrate the effectiveness of our proposed methodology by identifying distinctive types of latent topics and, further, by extracting urban functional regions using K‐means clustering and Delaunay triangulation spatial constraints clustering. We show that a region can support multiple functions but with different probabilities, while the same type of functional region can span multiple geographically non‐adjacent locations. Since each region can be modeled as a vector consisting of multinomial topic distributions, similar regions with regard to their thematic topic signatures can be identified. Compared with remote sensing images which mainly uncover the physical landscape of urban environments, our popularity‐based POI topic modeling approach can be seen as a complementary social sensing view on urban space based on human activities.     

Discovering Spatial Interaction Communities from Mobile Phone Data

In the age of Big Data, the widespread use of location‐awareness technologies has made it possible to collect spatio‐temporal interaction data for analyzing flow patterns in both physical space and cyberspace. This research attempts to explore and interpret patterns embedded in the network of phone‐call interaction and the network of phone‐users’ movements, by considering the geographical context of mobile phone cells. We adopt an agglomerative clustering algorithm based on a Newman‐Girvan modularity metric and propose an alternative modularity function incorporating a gravity model to discover the clustering structures of spatial‐interaction communities using a mobile phone dataset from one week in a city in China. The results verify the distance decay effect and spatial continuity that control the process of partitioning phone‐call interaction, which indicates that people tend to communicate within a spatial‐proximity community. Furthermore, we discover that a high correlation exists between phone‐users’ movements in physical space and phone‐call interaction in cyberspace. Our approach presents a combined qualitative‐quantitative framework to identify clusters and interaction patterns, and explains how geographical context influences communities of callers and receivers. The findings of this empirical study are valuable for urban structure studies as well as for the detection of communities in spatial networks.     

Geographical impacts on social networks from perspectives of space and place: an empirical study using mobile phone data

Space and place are two fundamental concepts in geography. Geographical factors have long been known as drivers of many aspects of people’s social networks. But whether and how space and place affect social networks differently are still unclear. The widespread use of location-aware devices provides a novel source for distinguishing the mechanisms of their impacts on social networks. Using mobile phone data, this paper explores the effects of space and place on social networks. From the perspective of space, we confirm the distance decay effect in social networks, based on a comparison between synthetic social ties generated by a null model and actual social ties derived from real-world data. From the perspective of place, we introduce several measures to evaluate interactions between individuals and inspect the trio relationship including distance, spatio-temporal co-occurrence, and social ties. We found that people’s interaction is a more important factor than spatial proximity, indicating that the spatial factor has a stronger impact on social networks in place compared to that in space. Furthermore, we verify the hypothesis that interactions play an important role in strengthening friendships.     

Street‐level Spatial Interpolation Using Network‐based IDW and Ordinary Kriging

This study proposes network‐based spatial interpolation methods to help predict unknown spatial values along networks more accurately. It expands on two of the commonly used spatial interpolation methods, IDW (inverse distance weighting) and OK (ordinary kriging), and applies them to analyze spatial data observed on a network. The study first provides the methodological framework, and it then examines the validity of the proposed methods by cross‐validating elevations from two contrasting patterns of street network and comparing the MSEs (Mean Squared Errors) of the predicted values measured with the two proposed network‐based methods and their conventional counterparts. The study suggests that both network‐based IDW and network‐based OK are generally more accurate than their existing counterparts, with network‐based OK constantly outperforming the other methods. The network‐based methods also turn out to be more sensitive to the edge effect, and their performance improves after edge correction. Furthermore, the MSEs of standard OK and network‐based OK improve as more sample locations are used, whereas those of standard IDW and network‐based IDW remain stable regardless of the number of sample locations. The two network‐based methods use a similar set of sample locations, and their performance is inherently affected by the difference in their weight distribution among sample locations.     

Network Density Estimation: A GIS Approach for Analysing Point Patterns in a Network Space

Human activities and more generally the phenomena related to human behaviour take place in a network‐constrained subset of the geographical space. These phenomena can be expressed as locations having their positions configured by a road network, as address points with street numbers. Although these events are considered as points on a network, point pattern analysis and the techniques implemented in a GIS environment generally consider events as taking place in a uniform space, with distance expressed as Euclidean and over a homogeneous and isotropic space. Network‐spatial analysis has developed as a research agenda where the attention is drawn towards point pattern analytical techniques applied to a space constrained by a road network. Little attention has been put on first order properties of a point pattern (i.e. density) in a network space, while mainly second order analysis such as nearest neighbour and K‐functions have been implemented for network configurations of the geographical space. In this article, a method for examining clusters of human‐related events on a network, called Network Density Estimation (NDE), is implemented using spatial statistical tools and GIS packages. The method is presented and compared to conventional first order spatial analytical techniques such as Kernel Density Estimation (KDE). Network Density Estimation is tested using the locations of a sample of central, urban activities associated with bank and insurance company branches in the central areas of two midsize European cities, Trieste (Italy) and Swindon (UK).     

Spatial optimization of rural settlement relocation by incorporating inter‐village social connections under future policy scenarios

Social connections between villages can represent farmers’ interests and thus benefit participatory rural relocation planning. With rural development, however, these connections will change and may weaken the adaptation of relocation plans to future rural systems. As yet, most studies still use empirical social connections to guide relocation planning, while a few have incorporated predicted connections in the context of rural development into relocation decisions. Meanwhile, spatial optimization approaches have seldom been adopted to solve this geographical decision issue. Accordingly, our study proposes a novel spatial relocation framework that incorporates changed inter‐village social connections under future rural development scenarios. Empirical inter‐village connections and their policy‐induced changes in central China were explored using social network analysis. An integration of particle swarm optimization and geographic information systems was adopted to identify the relocation solutions with maximum inter‐village connections and maximum spatial land use compactness, and to examine how connection changes under different policy scenarios influenced relocation outcomes. The results demonstrate the significance of incorporating policy‐induced social connections into relocation plans, and most importantly, show the negative relations between changed social connections and the migration distance/direction of relocated settlements. Our study is expected to improve the adaptation of relocation plans to future rural development.     

Evaluating Local Non-Stationarity when Considering the Spatial Variation of Large-scale Autocorrelation

Multi‐scale effects of spatial autocorrelation may be present in datasets. Given the importance of detecting local non‐stationarity in many theoretical as well as applied studies, it is necessary to “remove” the impact of large‐scale autocorrelation before common techniques for local pattern analysis are applied. It is proposed in this paper to employ the regionalized range to define spatially varying sub‐regions within which the impact of large‐scale autocorrelation is minimized and the local patterns can be investigated. A case study is conducted on crime data to detect crime hot spots and cold spots in San Antonio, Texas. The results confirm the necessity of treating the non‐stationarity of large‐scale spatial autocorrelation prior to any action aiming at detecting local autocorrelation.     

Mapping Large Spatial Flow Data with Hierarchical Clustering

It is challenging to map large spatial flow data due to the problem of occlusion and cluttered display, where hundreds of thousands of flows overlap and intersect each other. Existing flow mapping approaches often aggregate flows using predetermined high‐level geographic units (e.g. states) or bundling partial flow lines that are close in space, both of which cause a significant loss or distortion of information and may miss major patterns. In this research, we developed a flow clustering method that extracts clusters of similar flows to avoid the cluttering problem, reveal abstracted flow patterns, and meanwhile preserves data resolution as much as possible. Specifically, our method extends the traditional hierarchical clustering method to aggregate and map large flow data. The new method considers both origins and destinations in determining the similarity of two flows, which ensures that a flow cluster represents flows from similar origins to similar destinations and thus minimizes information loss during aggregation. With the spatial index and search algorithm, the new method is scalable to large flow data sets. As a hierarchical method, it generalizes flows to different hierarchical levels and has the potential to support multi‐resolution flow mapping. Different distance definitions can be incorporated to adapt to uneven spatial distribution of flows and detect flow clusters of different densities. To assess the quality and fidelity of flow clusters and flow maps, we carry out a case study to analyze a data set of 243,850 taxi trips within an urban area.     

Extracting human emotions at different places based on facial expressions and spatial clustering analysis

The emergence of big data enables us to evaluate the various human emotions at places from a statistical perspective by applying affective computing. In this study a novel framework for extracting human emotions from large‐scale georeferenced photos at different places is proposed. After the construction of places based on spatial clustering of user‐generated footprints collected from social media websites, online cognitive services are utilized to extract human emotions from facial expressions using state‐of‐the‐art computer vision techniques. Two happiness metrics are defined for measuring the human emotions at different places. To validate the feasibility of the framework, we take 80 tourist attractions around the world as an example and a happiness ranking list of places is generated based on human emotions calculated over 2 million faces detected from greater than 6 million photos. Different kinds of geographical contexts are taken into consideration to find out the relationship between human emotions and environmental factors. Results show that much of the emotional variation at different places can be explained by a few factors such as openness. The research offers insights into integrating human emotions to enrich the understanding of sense of place in geography and in place‐based GIS.     

Home range and habitat: Using platial characteristics to define urban areas from the bottom up

The spatial representation of a city is typically formed by top‐down jurisdictional boundaries. A parallel approach would be to consider representing a city based on platial characteristics, that is, a bottom‐up landscape created through individual and collectively derived representations. This study contributes to this discourse through the exploratory examination of the ecology notions of home range and habitat applied to humans in an urban context. Using spatial data collected through a WebGIS platform, we employ a spatial definition of sense of place and social capital to understand the platial nature of the city and, simultaneously, defining home range and habitat as platial notions. We found spatial variability among individual home range and habitat and the difficulty of traditional administrative boundaries to represent these areas. This research defines and presents home range and habitat to partially describe the emergent nature of platial theory and explores their operationalization at the urban level.     

Extracting spatial patterns in bicycle routes from crowdsourced data

Much is done nowadays to provide cyclists with safe and sustainable road infrastructure. Its development requires the investigation of road usage and interactions between traffic commuters. This article is focused on exploiting crowdsourced user‐generated data, namely GPS trajectories collected by cyclists and road network infrastructure generated by citizens, to extract and analyze spatial patterns and road‐type use of cyclists in urban environments. Since user‐generated data shows data‐deficiencies, we introduce tailored spatial data‐handling processes for which several algorithms are developed and implemented. These include data filtering and segmentation, map‐matching and spatial arrangement of GPS trajectories with the road network. A spatial analysis and a characterization of road‐type use are then carried out to investigate and identify specific spatial patterns of cycle routes. The proposed analysis was applied to the cities of Amsterdam (The Netherlands) and Osnabrück (Germany), proving its feasibility and reliability in mining road‐type use and extracting pattern information and preferences. This information can help users who wish to explore friendlier and more interesting cycle patterns, based on collective usage, as well as city planners and transportation experts wishing to pinpoint areas most in need of further development and planning.     

Multi‐scale approach to mining significant spatial co‐location patterns

Spatial co‐location pattern mining aims to discover a collection of Boolean spatial features, which are frequently located in close geographic proximity to each other. Existing methods for identifying spatial co‐location patterns usually require users to specify two thresholds, i.e. the prevalence threshold for measuring the prevalence of candidate co‐location patterns and distance threshold to search the spatial co‐location patterns. However, these two thresholds are difficult to determine in practice, and improper thresholds may lead to the misidentification of useful patterns and the incorrect reporting of meaningless patterns. The multi‐scale approach proposed in this study overcomes this limitation. Initially, the prevalence of candidate co‐location patterns is measured statistically by using a significance test, and a non‐parametric model is developed to construct the null distribution of features with the consideration of spatial auto‐correlation. Next, the spatial co‐location patterns are explored at multi‐scales instead of single scale (or distance threshold) discovery. The validity of the co‐location patterns is evaluated based on the concept of lifetime. Experiments on both synthetic and ecological datasets show that spatial co‐location patterns are discovered correctly and completely by using the proposed method; on the other hand, the subjectivity in discovery of spatial co‐location patterns is reduced significantly.     

Mapping fine‐scale urban housing prices by fusing remotely sensed imagery and social media data

The accurate mapping of urban housing prices at a fine scale is essential to policymaking and urban studies, such as adjusting economic factors and determining reasonable levels of residential subsidies. Previous studies focus mainly on housing price analysis at a macro scale, without fine‐scale study due to a lack of available data and effective models. By integrating a convolutional neural network for united mining (UMCNN) and random forest (RF), this study proposes an effective deep‐learning‐based framework for fusing multi‐source geospatial data, including high spatial resolution (HSR) remotely sensed imagery and several types of social media data, and maps urban housing prices at a very fine scale. With the collected housing price data from China's biggest online real estate market, we produced the spatial distribution of housing prices at a spatial resolution of 5 m in Shenzhen, China. By comparing with eight other multi‐source data mining techniques, the UMCNN obtained the highest housing price simulation accuracy (Pearson R = 0.922, OA = 85.82%). The results also demonstrated a complex spatial heterogeneity inside Shenzhen's housing price distribution. In future studies, we will work continuously on housing price policymaking and residential issues by including additional sources of spatial data.     

Network Density and the Delimitation of Urban Areas

This paper examines network analysis for urban areas. The research is focused on the problem of definition and visualisation of network geography and network spaces at different scales. The urban scale of analysis is examined and different spatial indices are considered. The built environment of the city is considered as a reference environment for a road network density index. The latter is implemented in order to study the spatial interactions between network phenomena and spaces and to provide further elements for the analysis of urban shape. The study is focused in particular on understanding spatial patterns drawn by networks and in helping with the delimitation of city centres. Different approaches are used to obtain the two indices: a grid–based analysis and a spatial density estimator based on Kernel Density Estimation. The two methodologies are analysed and compared using point data for the urban road network junctions and street numbers as house location identifiers in the Trieste (Italy) Municipality area. The density analysis is also used on road network junctions' data for the city of Swindon (UK) in order to test the methodology on a different urban area.     

Event pattern analysis: Spatial clustering of sequential events and temporal change of events over time

This article develops a method for analyzing spatial and temporal event patterns. Events in this article refer to zero-dimensional objects in the spatiotemporal dimension, which represent the occurrence of crimes, traffic accidents, earthquakes, and so forth. The spatial clustering of sequential events and the increase and decrease in events over time are discussed. These patterns are often observed and analyzed in various academic fields, such as criminology, epidemiology, and geography. However, analytical methods for these patterns have not yet been fully developed. To fill the research gap, this article proposes a new method for analyzing these event patterns. Two statistical measures are utilized, one represents the degree of the spatial clustering of sequential events, and the other evaluates the increase and decrease of events over time. The method is applied to the analysis of the spatial and temporal patterns of the openings of new shops and restaurants in Shibuya-ku, Tokyo. The results gave us interesting empirical findings and indicated the soundness of the method.     

Support Vector Machine for Spatial Variation

Large, multivariate geographic datasets have been used to characterize geographic space with the help of spatial data mining tools. In our study, we explore the sufficiency of the Support Vector Machine (SVM), a popular machine‐learning technique for unsupervised classification and clustering, to help recognize hidden patterns in a college admissions dataset. Our college admissions dataset holds over 10,000 students applying to an undisclosed university during one undisclosed year. Students are qualified almost exclusively by their standardized test scores and school records, and a known admissions decision is rendered based on these criteria. Given that the university has a number of political, social and geographic econometric factors in its admissions decisions, we use SVM to find implicit spatial patterns that may favor students from certain geographic regions. We first explore the characteristics of the applicants in the college admissions case study. Next, we explain the SVM technique and our unique ‘threshold line’ methodology for both discrete (regional) and continuous (k‐neighbors) space. We then analyze the results of the regional and k‐neighbor tests in order to respond to the methodological and geographic research questions.