Search

Due to the increasingly complex objects and massive information involved in spatial statistics analysis, least squares support vector regression (LS-SVR) with a good stability and high calculation speed is widely applied in regression problems of geospatial objects. According to Tobler’s First Law of Geography, near things are more related than distant things. However, very few studies have focused on the spatial dependence between geospatial objects via SVR. To comprehensively consider the spatial and attribute characteristics of geospatial objects, a geospatial LS-SVR model for geospatial data regression prediction is proposed in this paper. The 0–1 type and numeric-type spatial weight matrices are introduced as dependence measures between geospatial objects and fused into a single regression function of the LS-SVR model. Comparisons of the results obtained with the proposed and conventional models and other traditional models indicate that fusion of the spatial weight matrix can improve the prediction accuracy. The proposed model is more suitable for geospatial data regression prediction and enhances the ability of geospatial phenomena to explain geospatial data.

Traffic forecasting plays a vital role in intelligent transportation systems and is of great significance for traffic management. The main issue of traffic forecasting is how to model spatial and temporal dependence. Current state-of-the-art methods tend to apply deep learning models, these methods are unexplainable and ignore the a priori characteristics of traffic flow. To address these issues, a temporal directed graph convolution network (T-DGCN) is proposed. A directed graph is first constructed to model the movement characteristics of vehicles, and based on this, a directed graph convolution operator is used to capture spatial dependence. For temporal dependence, we couple a keyframe sequence and transformer to learn the tendencies and periodicities of traffic flow. Using a real-world dataset, we confirm the superior performance of the T-DGCN through comparative experiments. Moreover, a detailed discussion is presented to provide the path of reasoning from the data to the model design to the conclusions.

Accurate real-time traffic forecasting is a core technological problem against the implementation of the intelligent transportation system. However, it remains challenging considering the complex spatial and temporal dependencies among traffic flows. In the spatial dimension, due to the connectivity of the road network, the traffic flows between linked roads are closely related. In the temporal dimension, although there exists a tendency among adjacent time points, the importance of distant time points is not necessarily less than that of recent ones, since traffic flows are also affected by external factors. In this study, an attention temporal graph convolutional network (A3T-GCN) was proposed to simultaneously capture global temporal dynamics and spatial correlations in traffic flows. The A3T-GCN model learns the short-term trend by using the gated recurrent units and learns the spatial dependence based on the topology of the road network through the graph convolutional network. Moreover, the attention mechanism was introduced to adjust the importance of different time points and assemble global temporal information to improve prediction accuracy. Experimental results in real-world datasets demonstrate the effectiveness and robustness of the proposed A3T-GCN. We observe the improvements in RMSE of 2.51–46.15% and 2.45–49.32% over baselines for the SZ-taxi and Los-loop, respectively. Meanwhile, the Accuracies are 0.95–89.91% and 0.26–10.37% higher than the baselines for the SZ-taxi and Los-loop, respectively.

Tourism networks are an important research part of tourism geography. Despite the significance of transportation in shaping tourism networks, current studies have mainly focused on the “daily behavior” of urban travel at the expense of tourism travel, which has been regarded as an “exceptional behavior”. To fill this gap, this study proposes a framework for exploring the spatial and temporal characteristics of urban tourism travel by taxi. We chose Shenzhen, a densely populated mega-city in China with abundant tourism resources, as a case study. First, we extracted tourist trips from taxi trajectories and used kernel density estimation to analyze the spatial aggregation characteristics of tourist trip origins. Second, we investigated the spatial dependence of tourist trips using local spatial autocorrelation analysis (Getis-Ord Gi*). Third, we explored the correlations between the tourist trip origins and urban geographic contextual factors (e.g., catering services and transportation facilities) using a geographically weighted regression model. The results show the following: (1) the trends between the coverage of tourist travel networks and the volume of tourist trips are similar, (2) the spatial interaction intensity of urban tourism has grouping and hierarchical characteristics, and (3) the spatial distribution of tourist trips by taxi is uneven and influenced by the distribution of urban morphology, tourism resources, and the preferences of taxi pick-up passengers. Our proposed framework and revealed spatial and temporal patterns have implications for urban tourism traffic planning, tourism product development, and tourist flow control in tourist attractions.

Homicide rates have been increasing worldwide, especially in Latin America, where it is considered one of the most lethal of the continents. Despite that, the occurrence of homicides are not homogeneous in time and space on the continent or in the Brazilian cities. Therefore, the main objective of this study is to present a spatial analysis of homicides in the state of Pernambuco, Brazil, between the years of 2016 and 2019, by the use of an exploratory analysis of spatial homicide data with five variables that could explain its occurrence. In addition to that, it was applied the Global and Local Moran&rsquo, s Index, Ordinary Least Squares (OLS) regression, and Geographically Weighted Regression (GWR), all implemented in the Geographic Information System (GIS) software. Thus, the distribution of clusters revealed a spatial autocorrelation for homicide rates, confirming a spatial dependence. This data also showed the polarization of the rate between the coast and the interior of the state of Pernambuco.

To examine to what extent spatial inequalities in childhood obesity are attributable to spatial inequalities in socioeconomic characteristics across a country, we aimed to investigate the spatial associations of socioeconomic characteristics and childhood obesity. We first explored spatial patterns of childhood obesity prevalence, and subsequently investigated the spatial associations of socioeconomic factors and childhood obesity prevalence across England by selecting and estimating appropriate spatial regression models. As the data used are geospatial data, we used two newly developed specifications of spatial regression models to investigate the spatial association of socioeconomic factors and childhood obesity prevalence. As a result, among the two newly developed specifications of spatial regression models, the fast random effects specification of eigenvector spatial filtering (FRES-ESF) model appears to outperform the matrix exponential spatial specification of spatial autoregressive (MESS-SAR) model. Empirical results indicate that positive spatial dependence is found to exist in childhood obesity prevalence across England, and that socioeconomic factors are significantly associated with childhood obesity prevalence across England. In England, children living in areas with lower socioeconomic status are at higher risk of obesity. This study suggests effectively reducing spatial inequalities in socioeconomic status will plays a vital role in mitigating spatial inequalities in childhood obesity prevalence.

The proportion of tenants will undoubtedly rise in Poland, where at present, the ownership housing model is very dominant. As a result, the rental housing market in Poland is currently under-researched in comparison with owner-occupancy. In order to narrow this research gap, this study attempts to identify the determinants affecting rental prices in Cracow. The latter were obtained from the internet platform otodom.pl using the web scraping technique. To identify rent determinants, ordinary least squares (OLS) regression and spatial econometric methods were used. In particular, traditional spatial autoregressive model (SAR) and spatial autoregressive geographically weighted regression (GWR-SAR) were employed, which made it possible to take into account the spatial heterogeneity of the parameters of determinants and the spatially changing spatial autocorrelation of housing rents. In-depth analysis of rent determinants using the GWR-SAR model exposed the complexity of the rental market in Cracow. Estimates of the above model revealed that many local markets can be identified in Cracow, with different factors shaping housing rents. However, one can identify some determinants that are ubiquitous for almost the entire city. This concerns mainly the variables describing the area of the flat and the age of the building. Moreover, the Monte Carlo test indicated that the spatial autoregressive parameter also changes significantly over space.

Properties of spatially explicit data are often ignored or inadequately handled in machine learning for spatial domains of application. At the same time, resources that would identify these properties and investigate their influence and methods to handle them in machine learning applications are lagging behind. In this survey of the literature, we seek to identify and discuss spatial properties of data that influence the performance of machine learning. We review some of the best practices in handling such properties in spatial domains and discuss their advantages and disadvantages. We recognize two broad strands in this literature. In the first, the properties of spatial data are developed in the spatial observation matrix without amending the substance of the learning algorithm; in the other, spatial data properties are handled in the learning algorithm itself. While the latter have been far less explored, we argue that they offer the most promising prospects for the future of spatial machine learning.

Considering the multiscale characteristics of the human visual system and any natural scene, the spatial autocorrelation of remotely sensed imagery, and the multilevel spatial structure of ground targets in remote sensing images, an information-measurement approach based on a single-level geometrical mapping model can only reflect partial feature information at a single level (e.g., global statistical information and local spatial distribution information). The single mapping model cannot validly characterize the information of the multilevel and multiscale features of the spatial structures inherent in remotely sensed images. Additionally, the validity, practicability, and application range of the results of single-level mapping models are greatly limited in practical applications. In this paper, we present the multilevel geometrical mapping entropy (MGME) model to evaluate the information content of related attribute characteristics contained in remotely sensed images. Subsequently, experimental images with different types of objects, including reservoir area, farmland, water area (i.e., water and trees), and mountain area, were used to validate the performance of the proposed method. Experimental results show that the proposed method can not only reflect the difference in the information of images in terms of spectrum features, spatial structural features, and visual perception but also eliminates the inadequacy of a single-level mapping model. That is, the multilevel mapping strategy is feasible and valid. Additionally, the vector set of the MGME method and its standard deviation (Std) value can be used to further explore and study the spatial dependence of ground scenes and the difference in the spatial structural characteristics of different objects.

Gunshot detection technology (GDT) has been increasingly adopted by law enforcement agencies to tackle the problem of underreporting of crime via 911 calls for service, which undoubtedly affects the quality of crime mapping and spatial analysis. This article investigates the spatial and temporal patterns of gun violence by comparing data collected from GDT and 911 calls in Louisville, Kentucky. We applied hot spot mapping, near repeat diagnosis, and spatial regression approaches to the analysis of gunshot incidents and their associated neighborhood characteristics. We observed significant discrepancies between GDT data and 911 calls for service, which indicate possible underreporting of firearm discharge in 911 call data. The near repeat analysis suggests an increased risk of gunshots in nearby locations following an initial event. Results of spatial regression models validate the hypothesis of spatial dependence in frequencies of gunshot incidents and crime underreporting across neighborhoods in the study area, both of which are positively associated with proportions of African American residents, who are less likely to report a gunshot. This article adds to a growing body of research on GDT and its benefits for law enforcement activity. Findings from this research not only provide new insights into the spatiotemporal aspects of gun violence in urban areas but also shed light on the issue of underreporting of gun violence.

High crowd mobility is a characteristic of transportation hubs such as metro/bus/bike stations in cities worldwide. Forecasting the crowd flow for such places, known as station-level crowd flow forecast (SLCFF) in this paper, would have many benefits, for example traffic management and public safety. Concretely, SLCFF predicts the number of people that will arrive at or depart from stations in a given period. However, one challenge is that the crowd flows across hundreds of stations irregularly scattered throughout a city are affected by complicated spatio-temporal events. Additionally, some external factors such as weather conditions or holidays may change the crowd flow tremendously. In this paper, a spatio-temporal U-shape network model (ST-Unet) for SLCFF is proposed. It is a neural network-based multi-output regression model, handling hundreds of target variables, i.e., all stations&rsquo, in and out flows. ST-Unet emphasizes stations&rsquo, spatial dependence by integrating the crowd flow information from neighboring stations and the cluster it belongs to after hierarchical clustering. It learns the temporal dependence by modeling the temporal closeness, period, and trend of crowd flows. With proper modifications on the network structure, ST-Unet is easily trained and has reliable convergency. Experiments on four real-world datasets were carried out to verify the proposed method&rsquo, s performance and the results show that ST-Unet outperforms seven baselines in terms of SLCFF.

An in-depth analysis of urban road network distribution plays a critical role in understanding the urbanization process. However, effective ways to quantitatively analyze the spatial paradigms of road networks are still lacking, and few studies have utilized road networks to rapidly identify urban areas of a region. Thus, using a fast-developing region in the south-eastern costal region of China, Fuzhou City, as a case, we introduced kernel density estimation (KDE) to characterize road networks and quantified the area&rsquo, s spatial heterogeneity using exploratory spatial data analysis (ESDA) and semivariance analysis (SA). The results show that there is an uneven spatial distribution of the networks both at the regional and downtown levels. At the regional level, there is a conspicuous polarization in the road distribution, with the KDE being much higher in the urban areas than in the rural areas, at the downtown level, the KDE gradually decreases from the center to the periphery. Quantitatively, the ranges of the spatial dependence of the networks are approximately 25 km for the entire study region and 12 km for the downtown area. Additionally, the spatial variations vary among different directions, with greater variations in the northeast&ndash, southwest and the southeast&ndash, northwest directions compared with the other directions, which is in line with the urban sprawl policy of the study area. Both the qualitative and quantitative results show that the distribution of road networks has a clear urban&ndash, rural dual structure, which indicates that road networks can be an active tool in identifying the urban areas of a region. To this end, we propose a quick and easy method to delimit urban areas using KDE. The extraction results of KDE are better than those of the index-based built-up index (IBI), indicating the effectivity and feasibility of our proposed method to identify the urban areas in the region. This research sheds new light on urbanization development research.

The spatial variation of geographical phenomena is a classical problem in spatial data analysis and can provide insight into underlying processes. Traditional exploratory methods mostly depend on the planar distance assumption, but many spatial phenomena are constrained to a subset of Euclidean space. In this study, we apply a method based on a hierarchical Bayesian model to analyse the spatial variation of network-constrained phenomena represented by a link attribute in conjunction with two experiments based on a simplified hypothetical network and a complex road network in Shenzhen that includes 4212 urban facility points of interest (POIs) for leisure activities. Then, the methods named local indicators of network-constrained clusters (LINCS) are applied to explore local spatial patterns in the given network space. The proposed method is designed for phenomena that are represented by attribute values of network links and is capable of removing part of random variability resulting from small-sample estimation. The effects of spatial dependence and the base distribution are also considered in the proposed method, which could be applied in the fields of urban planning and safety research.

Due to the emergence of new big data technology, mobility data such as flows between origin and destination areas have increasingly become more available, cheaper, and faster. These improvements to data infrastructure have boosted spatial and temporal modeling of OD (origin-destination) flows, which require the consideration of spatial dependence and heterogeneity. Both ordinary least square (OLS) and negative binomial (NB) regression methods have been used extensively to calibrate OD flow models by processing flow data as different types of dependent variables. This paper aims to compare both global and local spatial interaction modeling of OD flows between traditional and geographically weighted OLS (GWOLSR) and NB (GWNBR) modeling methods. From this study with empirical data it is concluded that GWNBR outperforms GWOLSR in reducing spatial autocorrelation and in detecting spatial non-stationarity. Although, it is noted that both local modeling methods show improvement when compared against the equivalent global models.

Considering the importance of spatial issues in transport planning, the main objective of this study was to analyze the results obtained from different approaches of spatial regression models. In the case of spatial autocorrelation, spatial dependence patterns should be incorporated in the models, since that dependence may affect the predictive power of these models. The results obtained with the spatial regression models were also compared with the results of a multiple linear regression model that is typically used in trips generation estimations. The findings support the hypothesis that the inclusion of spatial effects in regression models is important, since the best results were obtained with alternative models (spatial regression models or the ones with spatial variables included). This was observed in a case study carried out in the city of Porto Alegre, in the state of Rio Grande do Sul, Brazil, in the stages of specification and calibration of the models, with two distinct datasets.

It is generally acknowledged that the urban environment presents different types of risk factors, but how the structural effects of areas influence the risk levels in neighboring areas has been less widely investigated. This research assesses the local effects of burglary contributory factors on burglary over small areas in a large metropolitan region. A comparative framework is developed for analyzing the effects of geographic dependence on burglary rates, and for assessing how such dependence conditions the community context and the urban land use. A local indicators spatial autocorrelation analysis assesses burglaries over five years (2011–2015) to identify risk clusters. Thereafter, effects of different variables (e.g., unemployment, building density) on burglary frequency are estimated in a series of regression models while controlling for changes in the risk levels of nearby surrounding areas. Results uncover strong evidence that the configuration of the surroundings influences risk. After controlling for area-based interaction, patterns are identified that contrast with the previous literature, such as lower burglary frequency in areas with higher tenancy in social housing units. Together the findings demonstrate that the spatial arrangement of areas is as crucial as contextual crime factors, particularly when assessing the risk for small areas.