Spatiotemporal Analytics

Description

This book introduces readers to spatiotemporal analytics that are extended from spatial statistics. Spatiotemporal analytics help analysts to quantitatively recognize and evaluate the spatial patterns and their temporal trends of a set of geographic events or objects. Spatiotemporal analyses are very important in geography, environmental sciences, economy, and many other domains. Spatiotemporal Analytics explains in very simple terms the concepts of spatiotemporal data and statistics, theories, and methods used. Each chapter introduces a case study as an example application for an in-depth learning process. The software used and the codes provided enable readers not only to learn statistics but also to use them effectively in their projects. • Provides a comprehensive understanding of spatiotemporal analytics to readers with minimum knowledge in statistics. • Written in simple, understandable language with step-by-step instructions. • Includes numerous examples for all theories and methods explained in the book covering a wide range of applications from different disciplines. • Each application includes a software code needed to follow the instructions. • Each chapter also has a set of prepared PowerPoint slides to help spatiotemporal analytics instructors explain the content. Undergraduate and graduate students who use Geographic Information Systems or study Geographical Information Science will find this book useful. The subject matter is also pertinent to an array of disciplines such as agriculture, anthropology, archaeology, architecture, biology, business administration and management, civic engineering, criminal justice, epidemiology, geography, geology, marketing, political science, and public health. Cover Half Title Title Page Copyright Page Table of Contents Editor Contributors Chapter 1 Introduction to Spatiotemporal Analytics 1.1 From Spatial Analytics to Spatiotemporal Analytics 1.2 Spatial Dependency and Spatiotemporal Dependency Among Geographic Events or Objects 1.3 Space–Time Dependency 1.4 Concluding Remarks References Chapter 2 Spatiotemporal Centrography and Dispersion 2.1 Introduction 2.2 Review of Relevant Literature 2.3 Analytical Methods 2.3.1 Centrography of Spatiotemporal Points 2.3.1.1 Spatiotemporal Mean Center 2.3.1.2 Weighted Spatiotemporal Mean Center 2.3.1.3 Changes in Spatiotemporal Mean Centers 2.3.2 Dispersion of Spatiotemporal Points 2.3.2.1 Standard Spatiotemporal Distance 2.3.2.2 Standard Spherical Volume 2.4 Application Example 2.5 Software and Usage 2.5.1 Hardware/Software Requirements 2.5.2 Software Usage for Spatiotemporal Mean Centers 2.5.3 Software Usage for Standard Spatiotemporal Distance 2.6 Concluding Remarks References Chapter 3 Spatiotemporal Quadrat Analytics 3.1 Introduction 3.2 Review of Relevant Literature 3.3 Analytical Methods 3.4 Application Example 3.5 Software and Usage 3.5.1 Hardware/Software Requirements 3.5.2 Software Usage for Spatiotemporal Quadrat Analysis 3.6 Concluding Remarks References Chapter 4 Spatiotemporal Nearest Neighbor Analytics 4.1 Introduction 4.2 Nearest Neighbor Index 4.3 Spatiotemporal Nearest Neighbor Index 4.3.1 The Time Dimension 4.3.2 Space–Time Nearest Neighbor Index 4.3.3 STNNI Application 4.3.4 Some Final Remarks 4.4 Software and Usage 4.4.1 Installation and Uninstallation 4.4.1.1 Install QGIS and NNI Plugin 4.4.1.2 Uninstall 4.4.2 Run STNNI and NNI Scripts 4.4.2.1 Space–Time Nearest Neighborhood Index 4.4.2.2 Spatial Nearest Neighborhood Index 4.5 Concluding Remarks References Appendix Chapter 5 Spatiotemporal Ripley's K and L Functions 5.1 Introduction 5.2 Concept and Methods 5.2.1 Spatial Ripley's K Function 5.2.2 Spatiotemporal Ripley's K Function 5.3 An Example Application References Chapter 6 Spatiotemporal Autocorrelation Analytics 6.1 Introduction 6.2 Methodology 6.2.1 Spatial Autocorrelation Moran's I 6.2.2 Temporal Autocorrelation 6.2.2.1 Global Temporal Moran's I[sub(t)] 6.2.2.2 Localized Temporal Moran's I 6.2.3 Spatiotemporal Autocorrelation (Temporal and Spatial Moran's I) 6.2.3.1 Global Spatiotemporal Moran's Index 6.2.3.2 Localized Spatiotemporal Moran's Index 6.3 Example Application 6.3.1 Disease Patterns 6.3.2 Simulation Experiments 6.3.2.1 Monte Carlo Simulation Process 6.3.2.2 Sensitivity and Temporal and Spatial Trend Analysis 6.4 Software and User Manual 6.4.1 Moran's I Tool User Manual 6.4.2 Demonstration of Software Results 6.4.3 Supplementary Explanation References Chapter 7 Spatiotemporal G Statistical Analytics 7.1 Introduction 7.2 The Getis – Ord G[sub(i)] and G[sub(i)]* Statistics 7.2.1 Space–Time Weight Matrix 7.2.2 Space–Time G[sub(i)] and G[sub(i)]* 7.3 Space–Time Crime Pattern in Chicago 7.3.1 Software and Usage 7.3.2 Hardware/Software Requirements 7.3.3 Software Usage for ST G[sub(i)] and G[sub(i)]* Analysis 7.4 Concluding Remarks References Chapter 8 Spatiotemporal Kernel Density Estimation 8.1 Introduction 8.2 Methods 8.2.1 Classic Spatiotemporal Kernel Density Estimation (CL_STKDE) 8.2.2 Conditional Spatiotemporal Kernel Density Estimation (CN_STKDE) 8.2.3 Integrative Spatiotemporal Kernel Density Estimation (IN_STKDE) 8.2.4 Validation Measurement 8.2.4.1 Hit Rate 8.2.4.2 Compactness Index 8.3 Example Application 8.4 Software and User Manual References Chapter 9 Spatiotemporally Weighted Regression 9.1 Introduction 9.2 Methodology 9.2.1 OLS Model 9.2.2 GWR Model 9.2.3 GTWR Model 9.3 Application Examples 9.3.1 House Price Estimation 9.3.2 Environmental Pollution Monitoring 9.3.3 Transportation Management 9.3.4 Crime Analysis – Based Urban Planning 9.4 Software and Usage 9.4.1 Installation and Uninstallation 9.4.1.1 How to Install GTWR Add-in 9.4.1.2 Uninstall 9.4.2 Run GTWR 9.4.2.1 Data Input 9.4.2.2 Setting 9.4.2.3 Output 9.4.2.4 Error 9.4.3 Some Notes 9.4.3.1 Data Requirements 9.4.3.2 Model Test 9.4.3.3 Spatiotemporal Distance 9.5 Concluding Remarks References Chapter 10 Spatiotemporal Bayesian Regression 10.1 Introduction to Bayesian Inference 10.1.1 Disease Mapping 10.1.2 Adding a Temporal Component 10.1.3 Parametric Time Trend 10.1.4 Exceedance Probabilities and Hotspot Identification 10.2 Example Applications 10.2.1 Example 1: Modeling Drug Overdose Incident 10.2.1.1 Defining Spatial Adjacency 10.2.1.2 Mapping the Relative Risk 10.2.1.3 Spatial Risk 10.2.1.4 Spatiotemporal Trend and Exceedance Probabilities 10.2.2 Example Application 2: Predictive Distribution of Spatiotemporal Bayesian Model 10.2.2.1 Predictive Distribution of Spatiotemporal Bayesian Model 10.2.2.2 Parameter Estimation via MCMC 10.2.2.3 Application Example 2 10.3 Concluding Remarks References Chapter 11 Spatiotemporal Process Analytics and Simulations 11.1 Introduction to Space–Time Network Simulations 11.2 Network Complexity 11.3 Classifying Network Diffusion Processes 11.4 Spatiotemporal Simulation with Agent-Based Modeling (ABM) 11.5 Application Example 11.5.1 Modeling the Spatiotemporal Network of a Dengue Fever Outbreak 11.6 Concluding Remarks References Chapter 12 Spatiotemporal Analytical Unit Problems 12.1 Introduction 12.2 Review of Relevant Literature 12.3 Analytical Methods 12.3.1 Modifiable Areal-Temporal Unit Problem (MATUP) 12.3.1.1 Spatiotemporal Scale 12.3.1.2 Spatiotemporal Divisions 12.3.1.3 Spatiotemporal Boundaries 12.3.2 Research Method 12.4 Application Example 12.4.1 Data 12.4.2 The Scale Effect of Space–Time Unit 12.4.3 Effects by Different Division Schemes 12.4.4 Effects of the Spatiotemporal Boundary 12.5 Software and Usage 12.6 Concluding Remarks References Index