Geospatial Big Data Research Articles

Extracting the pickpocketing information implied in the built environment by treating it as the anomalies

The practice of crime risk mapping, enabled by the utilization of geospatial big data such as street view images, has received significant research attention. However, in situations where available data is scarce, mapping models may suffer from underfitting and generate inaccurate spatial pattern estimations of crime risk. The covert nature of pickpocketing crimes results in limited observed areas relevant to such criminal events, leading to insufficient coverage of geospatial data. Moreover, the location of crime is also influenced by socio-economic characteristics that may introduce biases into crime risk estimates. These factors render it challenging for the model to capture a valid crime risk pattern, potentially yielding misleading conclusions. Therefore, effectively extracting crime risk with limited data remains a challenge, especially when relying on easily accessible, widespread, and unbiased geospatial data. To address this challenge, we propose a novel crime risk assessment framework based on deep anomaly detection techniques, assuming that urban landscape anomalies carry deep crime risk information. We take Shenzhen as the study area and map the distribution of pickpocketing risk using street view images, accurately revealing the spatial aggregation of pickpocketing crime risk. Our findings indicate that pickpocketing crime in China is caused by regional economic conditions, built environment factors, and human routine activities. This study provides valuable insights for policing and prevention strategies aimed at addressing pickpocketing crimes in large Chinese cities. By leveraging our proposed crime risk assessment framework, decision-makers can allocate resources more efficiently and develop targeted interventions to mitigate crime risks.

Unravelling urban governance challenges: Objective assessment and expert insights on livability in Longgang District, Shenzhen

With the advancement of urbanization, the assessment of urban livability has garnered widespread attention due to its importance for sustainable urban development. In the data era, the availability of geospatial big data has facilitated the objective livability assessments. However, a purely objective assessment fails to reveal the contradictions inherent in the urban governance or aid policymakers in understanding the challenges they face. Therefore, this study selected Longgang District in Shenzhen, a district with ambitions for livability, as a pilot area for assessment in a complementary way. Firstly, by drawing upon previous indicators, this research collected data from multiple sources, and conducted a comprehensive assessment of communities in Longgang, considering aspects of safety, health, convenience, and comfort. It was found that while most communities achieved high scores in livability, certain areas exhibited poor performance in terms of flooding, pollution, and public facilities, showing significant spatial variations. Generally, there is a hierarchical spatial differentiation in livability, gradually decreasing from the center to the outer areas. To uncover the urban governance challenges behind these spatial findings, thematic analysis was conducted, and semi-structured interviews were carried out with 10 local experts. Four challenges were specifically identified: the lack of supportive policies in flooding governance, difficulty in monitoring pollution, the absence of long-term planning in public facility governance, and disputes over the governance of low livability areas known as 'urban villages'. This study provides an exploratory research approach for assessing livability, and offers insights for future urban governance.

Population Spatialization Based on Convolutional Neural Network and Multi-Source Geospatial Big Data

This article adopts a more refined method to create a population spatial distribution model for Guizhou Province in 2021. Firstly, we divide the population data of Guizhou Province into different characteristic regions. Then, we use these regions as independent variables and population as dependent variables for analysis using convolutional neural network (CNN). In addition, we also introduced multi-source spatiotemporal data such as Points of Interest (POI), nighttime lighting, and Digital Elevation Model (DEM) for modeling to further enhance the accuracy and accuracy of the model. Through this method, we successfully generated the population spatial data of Guizhou Province in 2021 with a resolution of 1km. These data intuitively display the spatial distribution of the population in Guizhou Province, and have important reference value for policy makers, researchers, and planners.In addition, in order to verify the accuracy of our model, we evaluated and compared the accuracy of the model results. The results show that our model has high accuracy in expressing the spatial distribution of population, andcan accurately reflect the spatial distribution of population at different scales.In summary, this article successfully created a population spatial distribution model for Guizhou Province in 2021 using multiple spatiotemporal big data and multiple linear statistical regression methods, and evaluated and compared the accuracy of the model results. These results have important practical significance for understanding the population distribution, formulating land use planning and public policies in Guizhou Province.

Associations between greenspace characteristics and population emotion perceptions in three dimensions

Introduction: Mental disorders are considered to be the most significant threat to public health. Mitigation effects of urban green spaces have been widely documented. However, the conclusions are inconsistent because of the representativeness of the original data.Method: We measured the mental perception of urban green spaces using geospatial big data instead of field observation or questionnaire data. Street view data were applied to calculate urban green space characteristics in three dimensions.Results: The positive mental perception percentage around the chosen urban parks increased as the buffer diameter decreased. The temporal variations of positive mental perceptions around the selected urban parks exhibited an obvious peak-trough shape. The spatial associations between the positive mental perception percentage and urban green space characteristics varied geographically. The spatial associations became less similar as the spatial buffer diameter decreased. At the same spatial scale level, the green view played a dominant role in the spatial distribution of positive mental perceptions.Discussion: Shrinking the deviations of urban green space characteristics and increasing the mean and maximum values of urban green space characteristics will favor the improvement of public mental health. This study provides a reference for explaining ecological scientific questions using spatiotemporal big data. It also provides insights into the mechanisms underlying the relationship between ecological processes and public health.

Investigating the Spatial Heterogeneity and Influencing Factors of Urban Multi-Dimensional Network Using Multi-Source Big Data in Hangzhou Metropolitan Circle, Eastern China

Exploring the spatial heterogeneity of urban multi-dimensional networks and influencing factors are of great significance for the integrated development of metropolitan circle. This study took Hangzhou metropolitan circle as an example, using multi-source geospatial big data to obtain urban population, transportation, goods, capital, and information flow information among sub-cities. Then, spatial visualization analysis, social network analysis, and geographical detector were applied to analyze the differences in spatial structure of multiple urban networks and influencing factors in Hangzhou metropolitan circle, respectively. The results showed that (1) the network connections of population, traffic, goods, and capital flows transcended geographical proximity except that of information flow, and population and traffic flow networks were found to be more flattened in Hangzhou metropolitan circle than in other urban networks; (2) the comprehensive urban network of Hangzhou metropolitan circle was imbalanced across sub-cities, presenting hierarchical and unipolar characteristics; and (3) the influence of traffic distance on the network spatial structure of Hangzhou metropolitan was stronger than the geographical distance, and the interactions between traffic distance and socioeconomic factors would further enhance the regional differentiation of the network spatial structure. This study could provide scientific reference for constructing a coordinated and integrated development pattern in a metropolitan circle.

An interconnected IoT-inspired network architecture for data visualization in remote sensing domain

Geospatial Data Analytics (GDA) is a futuristic platform for analyzing and processing volumetric data in remote sensing and GIS applications. GDA utilizes the Internet of Spatial Things (IoST), mist, fog, and cloud computing architecture as a backend tool for analyzing and processing big geospatial data. This paper introduces utilizing these interconnected network architectures of cloud, fog, and mist to process a large volume of geospatial data. Also, the paper presents a flexible, interconnected distributed network system, i.e., IoST-mist-fog-cloud GIS architecture, to analyze and manage geospatial data. The proposed system helps cloud platforms when MIST devices are trying to cut down on latency and boost throughput at the edge of the IoST tier. It also performs the geospatial crime data visualization of the total number of stolen vehicles from 2001 to 2011 from all the states of India as a case study by using the proposed model. It explains the mathematical and analytical queueing model of the proposed system. In addition, it performs a performance evaluation and experimental findings on the proposed architecture and uses graphs to represent the various arithmetic outcomes. The experimentation result proves the proposed interconnected network architecture's efficacy in terms of reliability and efficiency.

Understanding Road Traffic Evolution in an Urbanizing Context through Statistical and Geospatial Analysis

Urbanization, an accelerated process, is inherently coupled with complex issues, including the evolution of road traffic systems. This diversity in urbanization and transport infrastructure largely hinges on economic status and geographic positioning across cities. Leveraging the capabilities of remote sensing and Geographic Information Systems (GIS) in processing geospatial big data, this paper evaluates the urbanization level (UL) and road traffic level (RTL) in 212 prefecture-level cities using statistical and geospatial grid data. We aim to dissect the impact of UL on RTL, thus highlighting the specific challenges and opportunities across regions and pinpointing optimal urban development models. Our findings demonstrate (1) rapid development in UL across all cities, juxtaposed with a surge and then stagnation in RTL; (2) a positive correlation between UL and RTL that grows over time but weakens in later stages; (3) differentiated development models in different city tiers and regions; and (4) region-specific development models and optimization policies aimed at enhancing the symbiosis of urbanization and road traffic. This study underscores the pivotal role of the integration of statistical and geospatial data in understanding the dynamic intersection of urbanization and road traffic systems.

Association between immigrant concentration and mental health service utilization in the United States over time: A geospatial big data analysis.

Immigrants (foreign-born United States [US] citizens) generally have lower utilization of mental health services compared with US-born counterparts, but extant studies have not investigated the disparities in mental health service utilization within immigrant population nationwide over time. Leveraging mobile phone-based visitation data, we estimated the average mental health utilization in contiguous US census tracts in 2019, 2020, and 2021 by employing two novel outcomes: mental health service visits and visit-to-need ratio (i.e., visits per depression diagnosis). We then investigated the tract-level association between immigration concentration and mental health service utilization outcomes using mixed-effects linear regression models that accounted for spatial lag effects, time effects, and covariates. This study reveals spatial and temporal disparities in mental health service visits and visit-to-need ratio among different levels of immigrant concentration across the US, both before and during the pandemic. Tracts with higher concentrations of Latin American immigrants showed significantly lower mental health service utilization visits and visit-to-need ratio, particularly in the US West. Tracts with Asian and European immigrant concentrations experienced a more significant decline in mental health service utilization visits and visit-to-need ratio from 2019 to 2020 than those with Latin American concentrations. Meanwhile, in 2021, tracts with Latin American concentrations had the least recovery in mental health service utilization visits. The study highlights the potential of geospatial big data for mental health research and informs public health interventions.

Population Spatialization based on Random Forest Model and Multi-source Geospatial big data

Population spatialization research is an important approach to achieve fine-grained management of urban space and coordinated development of rural resources and the environment. By converting administrative-level population data into a finer grid scale, it allows for in-depth analysis of the spatial distribution characteristics of population density and geographic heterogeneity within a region. Currently, in China, a population census is conducted every ten years, with the township as the smallest statistical unit. However, due to advancements in computer science and geography, the level of precision in data can no longer meet the requirements of modern geographical research. Population spatialization, based on national population statistics, utilizes techniques such as multi-source data fusion and data mining to decompose large-scale population data into corresponding grid-based data, enabling more accurate spatial representation of national population statistics and facilitating the understanding of population distribution patterns. This study used administrative boundary data for 88 counties in Guizhou Province in 2021, county-level population data from the 2021 China County Statistical Yearbook, and diverse geospatial data from Guizhou in 2017. Nine spatial variables that impact the spatial distribution of the study area's population, such as points of interest and nighttime light indices, were extracted. A random forest method was used to construct a population spatialization model and simulate population distribution.

Delineating Peri-Urban Areas Using Multi-Source Geo-Data: A Neural Network Approach and SHAP Explanation

Delineating urban and peri-urban areas has often used information from multiple sources including remote sensing images, nighttime light images, and points-of-interest (POIs). Human mobility from big geo-spatial data could also be relevant for delineating peri-urban areas but its use is not fully explored. Moreover, it is necessary to assess how individual data sources are associated with identification results. Aiming at these gaps, we apply a neural network model to integrate indicators from multi-sources including land cover maps, nighttime light imagery as well as incorporating information about human movement from taxi trips to identify peri-urban areas. SHapley Additive exPlanations (SHAP) values are used as an explanation tool to assess how different data sources and indicators may be associated with delineation results. Wuhan, China is selected as a case study. Our findings highlight that socio-economic indicators, such as nighttime light intensity, have significant impacts on the identification of peri-urban areas. Spatial/physical attributes derived from land cover images and road density have relative low associations. Moreover, taxi intensity as a typical human movement dataset may complement nighttime light and POIs datasets, especially in refining boundaries between peri-urban and urban areas. Our study could inform the selection of data sources for identifying peri-urban areas, especially when facing data availability issues.

Mapping fine-resolution nested social-ecological system archetypes to reveal archetypical human-environmental interactions

Scaling up case-based knowledge to understand human-environmental interactions is key to addressing the sustainability challenges we face in the Anthropocene. Mapping social-ecological system (SES) archetypes has emerged as a promising tool in identifying these interactions in a spatially explicit manner and developing transferrable sustainability solutions based on context-specific challenges. However, state-of-the-art SES archetype mapping is mainly bound to administrative borders. Lack of spatial details in SES maps does not always capture the panorama of SES configurations and hidden mechanisms. Empowered by multiple open-access geospatial big data streams, this study mapped two-tier nested SES archetypes at 1 km fine resolution in the Beijing-Tianjin-Hebei (BTH) urban agglomeration with high validation accuracy. Global SES archetypes derived from top-down rule-based classification revealed broad social-ecological configurations and social-ecological gradients across SESs. Meanwhile, regional SES sub-archetypes generated by bottom-up hierarchical clustering presented detailed SES characteristics that helped to identify location-specific sustainability challenges. Additionally, by scrutinizing the relationships among SES variables, we identified empirical evidence supporting the existence of four archetypical human-environmental interactions in an urban agglomeration area, manifesting as telecoupling between human and environment, human dependence on the environment, human adaption to the environment, and human modification and conservation of the environment. Generally, fine-resolution SES archetypes demonstrate great potential in supporting the recognition of local needs and gaps in existing policies, and further promoting sustainable landscape management in the BTH region and similar regions.

The impact of social isolation on sleep disturbances – evidence from geospatial big data during COVID-19

The impact of social isolation on sleep disturbances – evidence from geospatial big data during COVID-19

A site selection framework for urban power substation at micro‐scale using spatial optimization strategy and geospatial big data

AbstractThe world is facing more energy crises due to extreme weather and the rapidly growing demand for electricity. Siting new substations and optimizing the location of existing ones are necessary to address the energy crisis. The current site selection lacks consideration of spatial and temporal heterogeneity in urban power demand, which results in unreasonable energy transfer and waste, leading to power outages in some areas. Aiming to maximize the grid coverage and transformer utilization, we propose a multi‐scene micro‐scale urban substation siting framework (UrbanPS): (1) The framework uses multi‐source big data and the machine learning model to estimate fine‐scale power consumption for different scenarios; (2) the region growing algorithm is used to divide the power supply area of substations; and the (3) location set coverage problem and genetic algorithm are introduced to optimize the substation location. The UrbanPS was used to perform siting optimization of 110 kV terminal substations in Pingxiang City, Jiangxi Province. Results show that the coverage and utilization rate of the optimization results under different power consumption scenarios are close to 99%. We also found that the power can be saved by dynamic regulation of substation operation.

Revealing intra-urban hierarchical spatial structure through representation learning by combining road network abstraction model and taxi trajectory data

ABSTRACT The unprecedented urbanization in China has dramatically changed the urban spatial structure of cities. With the proliferation of individual-level geospatial big data, previous studies have widely used the network abstraction model to reveal the underlying urban spatial structure. However, the construction of network abstraction models primarily focuses on the topology of the road network without considering individual travel flows along with the road networks. Individual travel flows reflect the urban dynamics, which can further help understand the underlying spatial structure. This study therefore aims to reveal the intra-urban hierarchical spatial structure by integrating the road network abstraction model and individual travel flows. To achieve this goal, we 1) quantify the spatial interaction relatedness of road segments based on the Word2Vec model using large volumes of taxi trip data, then 2) characterize the road abstraction network model according to the identified spatial interaction relatedness, and 3) implement a community detection algorithm to reveal sub-regions of a city. Our results reveal three levels of hierarchical spatial structures in the Wuhan metropolitan area. This study provides a data-driven approach to the investigation of urban spatial structure via identifying traffic interaction patterns on the road network, offering insights to urban planning practice and transportation management.

A COMPARATIVE STUDY OF METHODS FOR DRIVE TIME ESTIMATION ON GEOSPATIAL BIG DATA: A CASE STUDY IN USA

Abstract. Travel time estimation is crucial for several geospatial research studies, particularly healthcare accessibility studies. This paper presents a comparative study of six methods for drive time estimation on geospatial big data in the USA. The comparison is done with respect to the cost, accuracy, and scalability of these methods. The six methods examined are Google Maps API, Bing Maps API, Esri Routing Web Service, ArcGIS Pro Desktop, OpenStreetMap NetworkX (OSMnx), and Open Source Routing Machine (OSRM). Our case study involves calculating driving times of 10,000 origin-destination (OD) pairs between ZIP code population centroids and pediatric hospitals in the USA. We found that OSRM provides a low-cost, accurate, and efficient solution for calculating travel time on geospatial big data. Our study provides valuable insight into selecting the most appropriate drive time estimation method and is a benchmark for comparing the six different methods. Our open-source scripts are published on GitHub (https://github.com/wybert/Comparative-Study-of-Methods-for-Drive-Time-Estimation) to facilitate further usage and research by the wider academic community.

GEOSPATIAL BIG DATA ANALYTICS FOR SUSTAINABLE SMART CITIES

Abstract. Growing urbanization cause environmental problems such as vast amount of carbon emissions and pollution all over the world.Smart Infrastructure and Smart Environment are two significant components of the smart city paradigm that can create opportunities for ensuring energy conservation, preventing ecological degradation, and using renewable energy sources. Since a great portion of the data contains location information, geospatial intelligence is a key technology for sustainable smart cities. We need a holistic framework for the smart governance of cities by utilizing key technological drivers such as big data, Geographic Information Systems (GIS), cloud computing, Internet of Things (IoT). Geospatial Big Data applications offer predictive data science tools such as grid computing and parallel computing for efficient and fast processing to build a sustainable smart city ecosystem. Effective management of big data in storage, visualization, analytics, and analysis stages can foster green building, green energy, and net zero targets of countries. Parallel computing systems have the ability to scale up analysis on geospatial big data platforms which is key for ocean, atmosphere, land, and climate applications. In this study, it is aimed to create the necessary technical infrastructure for smart city applications with a holistic big data management approach. Thus, a smart city model framework is developed for Smart Environment and Smart Governance components and performance comparison of Dask-GeoPandas and Apache Sedona parallel processing systems are carried out. Apache Sedona performed better on the performance test during read, write, join and clustering operations.

Fine‐scale simulation of spatial population distribution by coupling GA–ABM and big data: A case study of Dongguan, China

AbstractCapturing spatial population distribution can offer useful information for urban planning to promote reasonable population distribution and allocate urban resource. Agent‐based model (ABM) based on the modeling idea of “bottom‐up” can offer the ability to simulate the complex individual behaviors that generate spatial population distribution. Previous ABMs were unable to be extended for simulation of spatial population distribution at a fine scale due to the shortage of fine characterization of the urban environment and the calibration of agents' behavior. This study filled these gaps by proposing a genetic algorithm‐ABM (GA–ABM) for fine‐scale simulation of spatial population distribution in a manufacturing metropolis. In this model, the employment and residential choice behaviors of agents were defined by the labor economic theory and discrete selection model. Multisource geospatial big data such as enterprise points‐of‐interest big data and building footprints data were used to finely characterize the labor market and urban environment to reflect the impact of agents' employment choices on their residential decision. Furthermore, the grid‐scale population investigation big data were combined with the GA to calibrate the agents' residential decision behaviors. The proposed model was used in Dongguan, the typical manufacturing metropolis in China. As a comparison, the expert‐experience‐based method‐ABM (EEBM–ABM) was also conducted by using the same data set. Through the comparison of the results produced by these two models, it was demonstrated that the model coefficient calibrated by GA could effectively reflect the agents' residential decisions. The calibrated GA–ABM is more capable than EEBM–ABM in simulating spatial population distribution in a manufacturing metropolis. Hence, the proposed model can be used to simulate spatial population distribution in a manufacturing metropolis which helps the urban planner to conduct scientific urban planning.

The green quality of urban spatial development: A multi-dimensional and multi-regional model using big data

Spatial development involves multi-dimensional and multi-regional objectives that might be competing, while few studies have examined these issues simultaneously. We proposed a comprehensive model to assess the green quality of urban spatial development (GQUSD), focusing on the synergy of multi-dimensional objectives and the balance of multi-regional interests. The metropolitan city of Hangzhou was taken as an example. We included land consumption, vegetation loss and infrastructure cost as the inputs and the density of production and living activities as the outputs of spatial development. We developed a categorical Data Envelope Analysis (DEA) using geospatial big data and stratified optimization to evaluate the synergy of inputs-outputs at the finer level of spatial grids. Resultsshow a “sandwich” structure of the GQUSD in Hangzhou when considering green space and vegetation loss, and characterize four spatial typologies of agglomerated development, limited development, blinded development and low-potential development through the Bivariate Local Indicator of Spatial Association (LISA) analysis. The “sandwich” structure is shaped by spatial processes of socio-economic agglomeration, industrial-driven sprawl, new-town development and suburbanization of high-end sectors. We also find green inequality in the spatial development of Hangzhou where vegetation costs were higher in manufactural industrial sites and low-income communities. We provide urban planning strategies to balance competing interests across regions, objectives, functions and communities for green growth and sustainable goals.

COVID-19 contact tracking based on person reidentification and geospatial data

Efficient contact tracing is a crucial step in preventing the spread of COVID-19. However, the current methods rely heavily on manual investigation and truthful reporting by high-risk individuals. Mobile applications and Bluetooth-based contact tracing methods have also been adopted, but privacy concerns and reliance on personal data have limited their effectiveness. To address these challenges, in this paper, a geospatial big data method that combines person reidentification and geospatial information for contact tracing is proposed. The proposed real-time person reidentification model can identify individuals across multiple surveillance cameras, and the surveillance data is fused with geographic information and mapped onto a 3D geospatial model to track movement trajectories. After real-world verification, the proposed method achieves a first accuracy rate of 91.56%, a first-five accuracy rate of 97.70%, and a mean average precision of 78.03% with an inference speed of 13 ms per image. Importantly, the proposed method does not rely on personal information, mobile phones, or wearable devices, avoiding the limitations of existing contact tracing schemes and providing significant implications for public health in the post-COVID-19 era.

Assessing Progress and Interactions toward SDG 11 Indicators Based on Geospatial Big Data at Prefecture-Level Cities in the Yellow River Basin between 2015 and 2020

Rapid urbanization brings a series of dilemmas to the development of human society. To address urban sustainability, Sustainable Development Goal 11 (SDG 11) is formulated by the United Nations (UN). Quantifying progress and interactions toward SDG 11 indicators is essential to achieving Sustainable Development Goals (SDGs). However, it is limited by a lack of data in many countries, particularly at small scales. To address the gap, this study used systematic methods to calculate the integrated index of SDG 11 at prefecture-level cities with different economic groups in the Yellow River Basin based on Big Earth Data and statistical data, analyzed its spatial aggregation characteristics using spatial statistical analysis methods, and quantified synergies and trade-offs among indicators under SDG 11. We found the following results: (1) except for SDG 11.1.1, the performance of the integrated index and seven indicators improved from 2015 to 2020. (2) In GDP and disposable income groups, the top 10 cities had higher values, whereas the bottom 10 cities experienced greater growth rates in the integrated index. However, the indicators’ values and growth rates varied between the two groups. (3) There were four pairs of indicators with trade-offs that were required to overcome and eight pairs with synergies that were crucial to be reinforced and cross-leveraged in the future within SDG 11 at a 0.05 significance level. Our study identified indicators that urgently paid attention to the urban development of the Yellow River Basin and laid the foundation for local decision-makers to more effectively implement the 2030 Agenda for Sustainable Development (the 2030 Agenda).