Application Of Spatial Data Research Articles

Summary characteristics for multivariate function‐valued spatial point process attributes

SummaryPrompted by modern technologies in data acquisition, the statistical analysis of spatially distributed function‐valued quantities has attracted a lot of attention in recent years. In particular, combinations of functional variables and spatial point processes yield a highly challenging instance of such modern spatial data applications. Indeed, the analysis of spatial random point configurations, where the point attributes themselves are functions rather than scalar‐valued quantities, is just in its infancy, and extensions to function‐valued quantities still remain limited. In this view, we extend current existing first‐ and second‐order summary characteristics for real‐valued point attributes to the case where, in addition to every spatial point location, a set of distinct function‐valued quantities are available. Providing a flexible treatment of more complex point process scenarios, we build a framework to consider points with multivariate function‐valued marks, and develop sets of different cross‐function (cross‐type and also multi‐function cross‐type) versions of summary characteristics that allow for the analysis of highly demanding modern spatial point process scenarios. We consider estimators of the theoretical tools and analyse their behaviour through a simulation study and two real data applications.

Identifying popular, rejected and neglected children in Chinese preschool: An exploratory study on the educational application of spatial positioning data

Amidst the rapid advancement of Internet of Things (IoT) technology and the burgeoning field of Multimodal Learning Analytics (MMLA), this study employs spatial positioning technology as a case study to investigate the potential of multimodal data in assessing children's social development. This study combines the spatial positioning data of preschool children collected during free play sessions in natural educational settings and the spatial metrics constructed based on observational studies to establish and validate a sociometric status Decision Tree classification model. The findings suggest that the model can overall accurately identify children with three distinct sociometric statuses, albeit with some variability in efficacy across different sociometric groups and age groups. Notably, the model demonstrates a high hitting rate in identifying the potentially neglected children, providing valuable support for educators in understanding and fostering children's developmental needs. This study also highlights the advantages of emerging technology and multimodal data application in child development assessment.

Crop Type Classification using Sentinel 2A-Derived Normalized Difference Red Edge Index (NDRE) and Machine Learning Approach

Satellite remote sensing (RS) enables the extraction of vital information on land cover and crop type. Land cover and crop type classification using RS data and machine learning (ML) techniques have recently gained considerable attention in the scientific community. This study aimed to enhance remote sensing research using high-resolution satellite imagery and a ML approach. To achieve this objective, ML algorithms were employed to demonstrate whether it was possible to accurately classify various crop types within agricultural areas using the Sentinel 2A-derived Normalized Difference Red Edge Index (NDRE). Five ML classifiers, namely Support Vector Machines (SVM), Random Forest (RF), Decision Tree (DT), K-Nearest Neighbors (KNN), and Multi-Layer Perceptron (MLP), were implemented using Python programming on Google Colaboratory. The target land cover classes included cereals, fallow, forage, fruits, grassland-pasture, legumes, maize, sugar beet, onion-garlic, sunflower, and watermelon-melon. The classification models exhibited strong performance, evidenced by their robust overall accuracy (OA). The RF model outperformed, with an OA rate of 95% and a Kappa score of 92%. It was followed by DT (88%), KNN (87%), SVM (85%), and MLP (82%). These findings showed the possibility of achieving high classification accuracy using NDRE from a few Sentinel 2A images. This study demonstrated the potential enhancement of the application of high-resolution satellite RS data and ML for crop type classification in regions that have received less attention in previous studies.

Inversion of extinction coefficient for scattering media based on range-gated detection

The extinction coefficient is an important parameter for describing light transmitting properties in the scattering medium. However, the single-point detection way and the large inversion error of the existing techniques cannot satisfy the need for spatial analysis and data application. A novel approach for inversion of extinction coefficient based on range-gated detection utilizing backward scattering of medium is proposed, and an inversion algorithm for extinction coefficient is established utilizing the backscattering signal of multiple adjacent spatial slices of the medium. The method can simultaneously invert transverse multiple-points extinction coefficient and longitudinal profile of extinction coefficient. Further, experiments are conducted in the scattering medium including fog and smoke based on the fabricated range-gated extinction-coefficient detection and inversion system, and the results demonstrate that inversion with the error less than 5% can be achieved at different detection distances, different concentrations and different kinds of scattering mediums. This approach offers a convenient, rapid and accurate means to acquire extinction coefficients, laying the foundation for the development of efficient environmental monitoring and high-quality defogging imaging.

An algorithm for constructing spatial vector data storage based on KD-tree and density estimation

With the widespread application of spatial vector data in various fields, this paper proposes a novel algorithm for constructing spatial vector data storage. The algorithm is based on KD-tree and density estimation techniques, aiming to improve the storage efficiency and query performance of large-scale spatial vector data. The algorithm first efficiently organizes spatial vector data using KD-tree, and then performs density estimation based on the Locality Sensitive Hashing (LSH) algorithm. Algorithm optimizations for spatial partitioning are applied to the KD-tree construction algorithm, reducing the search range during queries and improving retrieval speed. By testing with Green Tide data, the algorithm based on KD-tree and density estimation demonstrates higher query efficiency and better scalability across multiple test datasets. Particularly, when dealing with large-scale datasets characterized by non-uniform data distributions, this algorithm significantly improves data retrieval speed while maintaining low storage overhead.

Robust Variable Selection with Exponential Squared Loss for the Spatial Error Model

With the widespread application of spatial data in fields like econometrics and geographic information science, the methods to enhance the robustness of spatial econometric model estimation and variable selection have become a central focus of research. In the context of the spatial error model (SEM), this paper introduces a variable selection method based on exponential square loss and the adaptive lasso penalty. Due to the non-convex and non-differentiable nature of this proposed method, convex programming is not applicable for its solution. We develop a block coordinate descent algorithm, decompose the exponential square component into the difference of two convex functions, and utilize the CCCP algorithm in combination with parabolic interpolation for optimizing problem-solving. Numerical simulations demonstrate that neglecting the spatial effects of error terms can lead to reduced accuracy in selecting zero coefficients in SEM. The proposed method demonstrates robustness even when noise is present in the observed values and when the spatial weights matrix is inaccurate. Finally, we apply the model to the Boston housing dataset.

Estimating of heavy metal concentration in agricultural soils from hyperspectral satellite sensor imagery: Considering the sources and migration pathways of pollutants

The evolution of hyperspectral remote sensing and artificial intelligence technologies has led to a surge in their application for predicting Soil Heavy Metal Concentrations (SHMC). Nevertheless, the preponderance of existing research within this sphere centers around data procured from ground-based and airborne hyperspectral sources. Studies that employ satellite-based methodologies typically rely on medium spatial resolution hyperspectral or multispectral satellite data. The application of high spatial and spectral resolution satellite data, such as that obtained from GaoFen-5 (GF-5), remains conspicuously underexplored. Furthermore, the impact of geographical environmental factors (GEFs) on the accuracy of predictions has been infrequently considered. In the context of this backdrop, the present study introduces stacking models designed to estimate SHMC. This approach integrates reflectance spectral features (SFs) derived from GF-5 hyperspectral imagery and GEFs, including topography and pollution sources. The results demonstrate a notable improvement in the predictive accuracy of SHMC using our Stacking model, as compared to single models. The incorporation of GEFs into the method results in a varying degree of reduction in the Root Mean Square Error (RMSE), along with an enhancement in the R2 on the training set. The predictive performance improvement is most prominent for Cd and As, with the RMSE decreasing by 52% and 48%, respectively. Notably, apart from Pb, there is an improvement in performance for all elements within the test set. This study confirms the effectiveness of integrating GEFs into SHMC prediction models to enhance accuracy. Applying this technique to predict soil pollution at a regional scale and to demarcate heavily polluted areas can yield satisfactory results. In the future, we plan to apply this technique to other research areas or datasets to expand its universality. Furthermore, we aim to delve more deeply into the potential of GEFs to enhance the predictive capacity of SHMC.

Application of Geographic Information Systems in the Study of COVID-19 in Morocco

Introduction: The 2019 coronavirus disease (COVID-19) was first identified as a respiratory disease that originated in Wuhan, Hubei Province, China. The WHO declared the COVID-19 outbreak a public health emergency of international concern on 30 January 2020. Morocco reported its first coronavirus case on 2 March 2020. During the week of 9-15 March 2020, Morocco took steps to limit the spread of the epidemic. This article describes the use of spatial data applications in epidemiological research in Morocco, specifically its response to the COVID-19 epidemic. Methods: To conduct this study, we relied on the use and analysis of data provided by the Moroccan Ministry of Health for the study period from May to July 2021, as well as the geographical and administrative map of the Kingdom of Morocco. Spatial analysis of COVID-19 was performed using ArcGIS 10.8 and QGIS, a geographic information processing software. Health data for the 12 regions of the Moroccan territory were presented in the number of COVID-19 cases as a discrete quantitative variable and over time as a continuous time variable. Results: According to a map created using GIS, the concentration of COVID-19 cases appeared to be highest in the Casablanca Settat region. Depending on the number of documented COVID-19 cases, regions were ranked as follows: Casablanca-Settat> Rabat-Sale-Kenitra> Marrakech-Safi > Fes-Meknes > Tangier-Tetouan-Alhouceima>Oriental>Souss-Massa > Béni Mellal-Khenifra> Draa-Tafilalet> Laayoune-Sakia El Hamra >Guelmim-Oued Noun > Dakhla-Oued Eddahab. The increase in cases in major cities was due to several factors, including demographic, social and environmental factors. This demonstrated the need to consider demographic contributions to environmental health. Demographic factors helped us understand the health of our environment empirically. Geography improved health decision-making and accountability. Incorporating the geographic context of the spread of COVID-19 helped decision-makers understand the impact of location on strategies and goals to combat this pandemic. Conclusion: This study identified areas with high and low COVID-19 clusters and hotspots. The produced maps can serve as an excellent management tool to control and effectively eliminate the COVID-19 pandemic, contributing to investments in epidemiological surveillance programs.

Machine learning‐based peak ground acceleration models for structural risk assessment using spatial data analysis

AbstractPredicting peak time‐domain ground‐motion parameters, such as peak ground acceleration (PGA), peak ground velocity, and peak ground displacement at a specific location, is challenging because of the limited number of recorded ground motions and the complexity of ground‐motion prediction equations. This study presents a novel approach that integrates a geographic information system with a spatial data analysis‐based machine learning PGA prediction model to overcome these challenges and predict PGA classes as a function of the PGA of the respective seismic stations, interstation distance of the seismic stations, and time‐average shear‐wave velocity in the upper 30 m of the target station. The proposed spatial data analysis‐based machine learning approach demonstrated the ability to generate satisfactory results in a short period. To account for the spatial dependencies of the variables, a feature selection method for spatial data using mutual information‐based feature selection was proposed, which provides a well‐prepared spatial matrix for machine learning algorithms. This study evaluates the performance of the model using various machine learning algorithms, including Random Forest, Naïve Bayes, K‐Nearest Neighbors, Decision Tree, AdaptiveBoost, Random Undersampling Boost, Extreme Gradient Boost (XGBoost), and Categorical Boost (CatBoost). Among these, XGBoost and CatBoost performed better than the other methods and yielded fairly accurate results. The models were validated using K‐Fold cross‐validation, and the Wilcoxon signed‐rank test was used for comparison. The spatial data analysis‐based machine learning models, particularly XGBoost and CatBoost, achieved high‐accuracy rates in classifying the PGA levels of 99.1% and 98.9%, respectively. Hyperparameters for the XGBoost model were tuned through GridSearchCV. Tree‐based models outperformed parametric models, indicating complex non‐linear spatial relationships, and by combining spatial feature selection with machine learning models demonstrated improved performance. Additionally, real‐time applications of spatial data analysis‐based machine learning PGA prediction models were used to estimate the seismic vulnerability of postulated concrete box‐girder bridges in San Fernando, thus providing insights into damage probabilities based on predicted PGA values.

Application of Spatial Data in Three-dimensional Computer Graphics

Digital three-dimensional modeling technologies are actively developing in all areas of industry and business. Three-dimensional models allow you to get visual information about complex objects, phenomena, processes and technical systems, and the scale of modeling can reach entire cities or enterprises. Because, when modeling the environment (cities, enterprises, complex technical systems), there is a spatial component, and there is a tendency to integrate technologies from different areas within one 3D model. Thus, within the framework of this article, the mechanism of using spatial data in the framework of computer graphics applications is considered. The main areas of application of three-dimensional modeling technologies and the trends of their further development are considered in detail. The main terms and definitions that underlie geoinformation technologies that allow processing spatial data are given. Using the example of computer graphics Blender, an example of the use of spatial data for the construction of terrain is given.

Mining Geomatics

This paper attempts to define a name for an area of science and technology that encompasses the acquisition, processing and application of spatial data in the mining industry. A comparative study of the evolution of spatial data exchange methods between Geographic Information Systems (GISs) and General Mining Planning (GMP) software is carried out to define the problem and name it. Subsequent modifications of the acronym GIS towards the specialisation of its application in mining are then reviewed. This is followed by the identification of three terminological postulates designed to formulate constraints and rules for the creation of a new definition. The subsequent analysis identifies the nomenclatural basis of the research area of geomatics and determines its applicability in the context of mining. The results of the research made it possible to formulate a new definition of “mining geomatics”. The final section of the article presents an initial proposal for an inventory of the basic concepts of mining geomatics in the form of a Body of Knowledge for mining geomatics.

Correct Calculation of the Existing Longitudinal Profile of a Forest/Skid Road Using GNSS and a UAV Device

The increasing importance of utilizing new technologies, such as GNSS (Global navigation satellite system) devices, total stations, drones, scanners, etc., in forestry has become evident with the development of these tools. Combined with precise GNSS devices, UAVs represent an efficient tool that facilitates field measurements and reduces time spent in the field while also providing highly accurate data. To accurately determine the application of spatial data for calculating the longitudinal slope of forest/logging roads in a research project, measurements based on UAVs were conducted and compared with GNSS data. GNSS data were considered the reference values for the studied area, assuming that satellite positions and internet signals were good. An accurate longitudinal slope was necessary to define fuel consumption on forest/logging roads and slopes throughout the project and to verify the calculation method that could be applied for such or similar terrain conditions and overgrowth. The main goal of this research phase was not to study fuel consumption but to obtain an accurate longitudinal profile of forest/skid roads on rocky terrain that is not overgrown or poorly grown. The study put forth two hypotheses, one of which was ultimately confirmed, while the other was refuted. The results show no significant differences when comparing the absolute elevation of the points in the profiles for defining the longitudinal slope of the road using the program for designing forest/skid roads. While applying such a method of data collection to create the main projects for the (re)construction of forest/skid roads, there are significant deviations in earthwork masses. There was a difference of over 22.64% in one of the types of earthwork excavation on the designed forest road, so the method implemented in the research does not give sufficiently accurate results.

Spatially Contextualizing Rural Land Transformation in Peri-Urban Area: A case of Jalandhar City, Punjab (India)

The advent of market liberalization in 1990 brought various forms of transformation, principally land transformation, to Indian cities and their respective peri-urban areas. The Jalandhar city and surrounding rural area from an agrarian state (Punjab) of India provide exemplified setting in this respect. A period of 30 years (1991-2021) has been selected to assess land transformation's magnitude, intensity, and direction. The applicability of different spatial data and methodologies helped analyze the facets of land transformation in quantitative and qualitative terms. The results highlight a massive rural land transformation due to the development of various urban corridors and institutional & commercial set-ups in the city fringe by converting and usurping prime agricultural land and increasing land fragmentation. The built-up class has seen a growth of more than 200 per cent in these decades at the cost of 22 per cent of cropland and other studied classes.

Robust Variable Selection with Exponential Squared Loss for the Spatial Durbin Model

With the continuous application of spatial dependent data in various fields, spatial econometric models have attracted more and more attention. In this paper, a robust variable selection method based on exponential squared loss and adaptive lasso is proposed for the spatial Durbin model. Under mild conditions, we establish the asymptotic and "Oracle" properties of the proposed estimator. However, in model solving, nonconvex and nondifferentiable programming problems bring challenges to solving algorithms. To solve this problem effectively, we design a BCD algorithm and give a DC decomposition of the exponential squared loss. Numerical simulation results show that the method is more robust and accurate than existing variable selection methods when noise is present. In addition, we also apply the model to the 1978 housing price dataset in the Baltimore area.

Application of spatial data and 3S robotic technology in digital city planning

This article uses spatial data and 3S (Spatial, Surveying, and Remote Sensing) technology to enhance digital city planning. The methodology integrates WebGIS Big data, statistical feature extraction techniques, and strategic planning to create a comprehensive framework for digital urban planning. Spatial information point calibration ensures accurate spatial positioning during the planning process. At the same time, data fusion and fuzzy C-means clustering analysis are utilized to detect and analyze WebGIS data within the digital city planning context. The proposed model incorporates a piecewise fitting method within the Big data integration scheduling framework for digital city spatial planning. A C/S (Client/Server) architecture and ARM-embedded technology have been developed to establish a robust digital city planning system to support this approach. This system encompasses modules for WebGIS information collection, bus control, database management, human-machine interaction, and data processing terminals. Simulation results demonstrate that the method significantly reduces delays in digital city planning and design. When analyzing a data scale of 100, the method exhibits an 83.4% lower delay than the fuzzy method. Although delays increase with larger data scales, even at a scale of 400, the method still offers a 43.1% reduction compared to the fuzzy method. Across varying data scales, the proposed method consistently maintains approximately 60% lower latency than the rough set method. This method showcases superior intelligence and exhibits strong capabilities in accessing and scheduling WebGIS data effectively.

Application of Spatial Data Mining in the Process of Discovering Interesting and Previously Unknown, but Potentially Useful, Patterns from Large Spatial Datasets

Spatial data mining has been typically used in the Geographical Information system from physical datasets and locations to real-world events. One of the procedures generally used in capital data mining is vector data representation. Vector data is the most commonly used data across the world. Information in this format consists of tips, angles, and quadrilaterals. It is the simplest method of analysing the data where the vector data consists of tips correlate pairs to indicate a physical location in the world. These points can be joined in a particular way to form closed areas marked as quadrilaterals. Vector data is extremely useful for storing and representing data that has discrete boundaries such as international borders, streets, buildings, and many more. Modern technologies such as Google use geological information and open street maps to represent the data in vector data stricture wise. Keyword : Spatial data mining, Vector data, Information system, Security, Data

Application of Spatial Data Mining to national mines inventories for exploration and land planning of high place-value mineral resources. The case of aggregates in Spain

Countries' mine inventories usually include information related to exploited rock type or mineral, amount of resources, owner, location, mining rights associated, etc. All this information is a vast dataset that in the last couple of decades has been included in digital cartography in official websites, some of them freely available. This information is usually exploited as individual registers classified by substance, location, etc., but when analyzed as a whole and combined with other economic, social, and environmental variables, valuable information can be obtained. If the variable time is included in the study, these databases can reveal the evolution of mining activity in recent decades.This study analyzes the distribution of aggregates quarries in Spain, as a case study, relating their location to different socio-geographical features such as urban areas, environmentally protected areas, or population density, by means of Spatial Data Mining (SDM) tools. Aggregates are used as construction materials and are the largest non-energy extractive industry, being the second most consumed product by human beings after water. Due to the low unit value and high volume of consumption, aggregates are considered a high place-value commodity. By combining the information of aggregates in the Spanish mines inventory with geological, social, demographic, environmental, and administrative information, and using SDM techniques, relevant conclusions can be obtained such as the delineation of areas in the land use planning to be dedicated to aggregates exploitation, or the identification of priority zones for exploration for mining companies. This information could serve policy makers and land use planners in making data-driven decisions and mining companies in determining areas with the highest profit potential to develop their operations.

Cluster analysis and geospatial mapping of antibiotic resistant Escherichia coli O157 in southwest Nigerian communities

Geospatial spread and antibiotic-resistant relatedness of Escherichia coli O157, which are important virulent serotypes causing severe complications leading to high intestinal morbidity and occasional mortality in several communities in southwest Nigeria, were evaluated.Biotyped Escherichia coli strains (n = 508) from subjects with diarrhea and related intestinal infections, various domestic water sources and food animal products were evaluated for antibiotic resistance relatedness, conjugative activity, virulence factor and biofilm production. Antibiotic resistance of Escherichia coli O157 encoded with stx was mapped for geospatial spread.Detected stx-encoded Escherichia coli O157 (7.56%) of human strains were significantly higher compared to water and food animal strains (p = 0.001) with high conjugative and transformative activity (OR(95%CI) = 34.65(94.5); p = 0.023). Water- Escherichia coli O157 reveal significant median resistance to ciprofloxacin, gentamycin (p < 0.05) and human diarrheagenic strains showed >60% resistance to doxycycline (MIC50 8 μg/mL and MIC90 128 μg/mL; p = 0.018), tetracycline (MIC50 4 μg/mL and MIC90 64 μg/mL), ciprofloxacin (MIC50 2 μg/mL and MIC90 128 μg/mL) and gentamycin (MIC50 4 μg/mL and MIC90 256 μg/mL). Strains from human diarrhea, UTI, colitis, cattle, fish, sheep, ground waters, streams, and rivers characterized with biofilm, hemolysin, protease productions, R-plasmid (≈14.30kbp) and MARI (0.84) were highly related. Principal component analysis (score plot) revealed a significant association between resistant human diarrheic strains with cattle and poultry strains. A high population of heterogeneous stx-encoded diarrheagenic and colitis strains was predominant in urban settings spreading with food animal and water Escherichia coli O157 strains.Human diarrheagenic Escherichia coli O157 were highly related to antibiotic resistance and virulence pattern with water and animal products strains. Strategic interventions through the implementation of One Health approach and population-target antimicrobial stewardship are needed to mitigate the increasing intestinal morbidity and reduction of mortality impact. Regular application of spatial data on clonal dissemination is important for monitoring, surveillance of antimicrobial resistance and transmission of zoonotic food-borne Escherichia coli O157 pathogens.

ROADMAP FOR INTEROPERABLE 3D DATA MODELS IN OGC APIS AND OTHER DATA EXCHANGE APPROACHES

Abstract. Many data exchange standards for 3D spatial data applications exist, ranging from the general Geography Markup Language (GML) underpinning CityGML to specific models for business application domains, such as BuildingSMART Industry Foundation Classes (BIM/IFC). There are a number of different approaches to modelling 3D objects, and in general the geometry aspects of these can be readily understood in the context of the visualisation needs of different applications. The topology, or relationships between elements of these objects, on the other hand is either not directly supported by such geometry models or implemented in different ways by different standards. We discuss limitations of existing standards for describing topological relationships in particular. In some cases topology information is embedded in geometry objects using identifiers for vertices, edges and faces, but in general there is scope to develop a standardised model for describing alternatives for topology and 3D geometry representations. A limited set of such models allows for interoperability via transformations between different representations. The ISO 19107 Spatial Schema provides an adequate conceptual model for these concerns, so we present the argument that a profile of this comprehensive model be defined for the limited set of such representation options required for Smart Cities and other similar applications.

Understanding the Geography of Rape through the Integration of Data: Case Study of a Prolific, Mobile Serial Stranger Rapist Identified through Rape Kits.

Environmental criminological research on rape series is an understudied field due largely to deficiencies in official and publicly available data. Additionally, little is known about the spatial patterns of rapists with a large number of stranger rapes. With a unique integration and application of spatial, temporal, behavioral, forensic, investigative, and personal history data, we explore the geography of rape of a prolific, mobile serial stranger rapist identified through initiatives to address thousands of previously untested rape kits in two U.S. urban, neighboring jurisdictions. Rape kit data provide the opportunity for a more complete and comprehensive understanding of stranger rape series by linking crimes that likely never would have been linked if not for the DNA evidence. This study fills a knowledge gap by exploring the spatial offending patterns of extremely prolific serial stranger rapists. Through the lens of routine activities theory, we explore the motivated offender, the lack of capable guardianship (e.g., built environment), and the targeted victims. The findings have important implications for gaining practical and useful insight into rapists’ use of space and behavioral decision-making processes, effective public health interventions and prevention approaches, and urban planning strategies in communities subjected to repeat targeting by violent offenders.