Intelligence for Future Cities : Planning Through Big Data and Urban Analytics

This book contains a selection of the best papers presented at the Computational Urban Planning and Urban Management (CUPUM) conference, held in June 2023 at McGill University in Montreal, Quebec. Major themes of this book are smart cities, urban big data, and shared mobility. This book also contains chapters with cutting-edge research on urban modeling, walkability and bikeability analysis, and planning support systems (PSS). Preface Contents 1 Introduction 1.1 Overview of the Book 1.1.1 Digital Cities 1.1.2 Mobility Futures 1.1.3 Fine-Scale Urban Analysis 1.2 Intelligence for Future Cities Reference Part I Digital Cities 2 Hybrid Smartness: Seeking a Balance Between Top-Down and Bottom-Up Smart City Approaches 2.1 Introduction 2.2 The Idea of Smartening Cities-Exploring Smart Cities’ Terms and Concepts Over Time 2.3 Early Ideas: Top-Down Smartness 2.4 The Emergence of Bottom-Up Smartness 2.5 Towards Hybrid Smartness: The Need for a Socio-Technical Approach 2.6 Reflections on Current Smart Realities 2.7 Final Remarks−Rethinking Planning at Large 2.8 Conclusion References 3 Interpreting the Smart City Through Topic Modeling 3.1 Introduction 3.2 Literature Review 3.3 Application of Human-Centered Topic Modeling 3.3.1 Modeling 3.3.2 Topic Comparison 3.4 Results 3.4.1 Modeling of Grant Applications 3.4.2 Modeling of Finalists’ Proposals 3.4.3 Comparing the First Round to the Finalists’ Round 3.5 Discussion 3.5.1 What Constitutes the Canadian Smart “City”? 3.5.2 What Constitutes the Canadian “Smart” City? 3.5.3 What Is the Utility of Topic Modelling for Abductive Inquiry About Smart Cities? 3.6 Conclusion References 4 The Venue Code: Digital Surveillance, Spatial (Re)organization, and Infrastructural Power During the Covid Pandemic in China 4.1 Digital Surveillance and Infrustructures in China 4.2 Methodology 4.3 Organizational Structure 4.4 Definition, Piloting, and Incorporation 4.5 Spatial (Re)organization 4.6 Logistics and Technologies 4.7 Conclusion References 5 The Platformization of Public Participation: Considerations for Urban Planners Navigating New Engagement Tools 5.1 Background 5.1.1 Urban Technology Platforms 5.1.2 Public Participation in Planning 5.1.3 Convenor Platforms as Mediators of Public Participation 5.2 The Rise of Participatory Convenor Platforms 5.3 The Platformization of Public Participation: Questions for Planning Practice and Research 5.4 Conclusions References Part II Mobility Futures 6 Shared Micro-mobility: A Panacea or a Patch for Our Urban Transport Problems? 6.1 Shared Micro-mobility: The New Kid on the Block 6.1.1 The Three Generations of Shared Micro-mobility 6.1.2 Contribution and Disruption to Cities 6.2 Shared Micro-mobility Transforming Cities: The Research Landscape 6.2.1 Shared Micro-mobility Transforming the Urban Economy 6.2.2 Shared Micro-mobility Transforming Urban Sustainability 6.2.3 Shared Micro-mobility Transforming Urban Accessibility 6.2.4 Shared Micro-mobility Transforming Urban Lifestyles 6.3 What Does and Doesn’t The Data Tell? An Empirical Demonstration 6.3.1 Study Area 6.3.2 Data 6.3.3 Building a Typology of Shared Micro-mobility Trips 6.3.4 People: The Missing Puzzle 6.4 Two Scenarios of Shared Micro-mobility: A Panacea or a Patch for Urban Transport Problems? 6.4.1 Scenario 1: A Shared Micro-mobility Paradise 6.4.2 Scenario 2: When the Hype is Over 6.5 Conclusion: Making Shared Micro-mobility Work for Cities References 7 Understanding Bikeability: Insight into the Cycling-City Relationship Using Massive Dockless Bike-Sharing Records in Beijing 7.1 Introduction 7.2 Methodology 7.2.1 Research Design 7.2.2 Variables and Data 7.3 Results 7.3.1 Data Processing and Preliminary Tests 7.3.2 Regression Analysis and Results 7.4 Conclusions and Discussion References 8 Disclosing the Impact of Micro-level Environmental Characteristics on Dockless Bikeshare Trip Volume: A Case Study of Ithaca 8.1 Introduction 8.2 Literature Review 8.2.1 Perceived Built Environment and Cycling Behavior 8.2.2 SVI, CV, and ML for Micro-level Environment Characteristics 8.3 Dataset and Methodology 8.3.1 Study Area 8.3.2 Methods 8.3.3 Data Collection and Processing 8.3.4 Correlation Analysis 8.4 Results 8.4.1 Trip Volumes 8.4.2 Strength of Association by Attribute Groups 8.4.3 OLS Regression Results and Performances 8.5 Discussion 8.5.1 Micro-level Environment Characteristics 8.5.2 Conventional Macro-level Environment Characteristics 8.6 Conclusion Appendix References 9 A Planning Support System for Boosting Bikeability in Seoul 9.1 Introduction 9.2 Literature Review 9.2.1 Bikeability Index 9.2.2 Planning Support Systems 9.2.3 Research Gap and Contribution 9.3 Methodology 9.3.1 Methodology Summary 9.3.2 Development of the Model’s Dataset 9.3.3 Development of the Models: Poisson and GWR 9.4 Results and Discussion 9.4.1 Centrality Indices Using UNA Tool 9.4.2 Spatial Validation Tests: Autocorrelation, Dependence, and Heterogeneity 9.4.3 Geographically Weighted Regression Model 9.5 Bikeability Index-Based Planning Support System 9.6 Conclusion and Policy Implications References 10 Integrating Big Data and a Travel Survey to Understand the Gender Gap in Ride-Hailing Usage: Evidence from Chengdu, China 10.1 Introduction 10.2 Background 10.2.1 Gendered Travel Needs and Behavior 10.2.2 Gender Gap in the Age of Ride-Hailing 10.3 Case Study and Data 10.3.1 Case Study City: Chengdu 10.3.2 Data Sources 10.4 Methodology 10.4.1 Measurement of Activity Space 10.4.2 Built Environment and Socioeconomic Status 10.4.3 Models 10.5 Results 10.5.1 Gendered Ride-Hailing Usage Seeing from Travel Survey 10.5.2 Spatial Variations in Ride-Hailing Usage Seeing from Big Data 10.5.3 Gendered Activity Space 10.5.4 Ride-Hailing Usage, Gender, and Influencing Factors 10.6 Conclusions and Discussion References 11 Urban Airspace Route Planning for Advanced Air Mobility Operations 11.1 Introduction and Motivation 11.1.1 Literature Review 11.2 AAM and eVTOLs 11.2.1 eVTOL Aircraft Capabilities 11.2.2 Concept Overview 11.3 Use Case: Atlanta Airport City 11.3.1 Inner Aerotropolis Network 11.3.2 Ensuring Synergies with Existing Airport 11.3.3 Airport Shuttle Network 11.3.4 Demand 11.4 Conclusions and Recommendation 11.4.1 Conclusion 11.4.2 Future Work References Part III Fine-Scale Urban Analysis 12 “Eyes on the Street”: Estimating Natural Surveillance Along Amsterdam’s City Streets Using Street-Level Imagery 12.1 Introduction 12.2 Method 12.3 Data 12.4 Results 12.5 Discussion 12.6 Conclusion References 13 Automatic Evaluation of Street-Level Walkability Based on Computer Vision Techniques and Urban Big Data 13.1 Introduction 13.1.1 Background 13.1.2 Related Studies 13.1.3 Current Gaps and Research Objectives 13.2 Methodology 13.2.1 Constructing a Walkability Index for Automatic Evaluation 13.2.2 Measuring Walkability 13.2.3 Accessing the Relative Importance of Variables 13.3 Experimental Results 13.3.1 Objective Walkability in Kowloon West 13.3.2 Subjective Walkability in Kowloon West 13.4 Discussion 13.4.1 Can the Proposed Measurement Method Produce a Low-Cost, Fast, and Reliable Walkability Evaluation? 13.4.2 Do the Proposed Walkability Index and Its Methods Have High Applicability and Generalization Potential? 13.4.3 What Are the Advantages of Applying Multiple AI Techniques in Walkability Evaluations? 13.5 Conclusion References 14 Promoting Sustainable Travel Through a Web-Based Tourism Support System 14.1 Introduction 14.2 Related Work 14.3 System Design 14.3.1 System Overview 14.3.2 Design of Each System 14.4 Database Creation of the System 14.4.1 Data Used in the System 14.4.2 Inference of Tourism Congestion 14.4.3 Calculation of the Feature Values of Tourist Attractions 14.4.4 Database Creation 14.5 System Development 14.5.1 System Frontend 14.5.2 System Backend 14.5.3 System Interface 14.6 System Operation 14.6.1 Operation Overview 14.6.2 Operation Results 14.7 System Evaluation 14.7.1 Overview of the Web Questionnaire Survey for Users 14.7.2 Evaluation Result 14.7.3 Identification of Improvement Measures 14.8 Conclusion References 15 Applying the AURIN Walkability Index at the Metropolitan and Local Levels by Sex and Age in Australia 15.1 Introduction 15.2 Literature Review 15.2.1 Included Criteria and Attributes 15.2.2 Socio-Demographic Profiling 15.2.3 Scale of the Analysis/Geography 15.2.4 Unit of Analysis 15.2.5 Method of Visualisation 15.3 Methodology 15.3.1 Study Area 15.3.2 AURIN Walkability Index (AWI) 15.3.3 Correlation of the AWI with Observed Data of “Walking to Work” 15.4 Analysis and Findings 15.4.1 At the National Level 15.4.2 At the Metropolitan Level 15.5 Discussion and Conclusion References 16 Predicting Urban Heat Island Mitigation with Random Forest Regression in Belgian Cities 16.1 Introduction 16.2 Methodology 16.3 Study Area and Dataset 16.4 Parameters Influencing LST 16.4.1 Building Density 16.4.2 Building Volume Index 16.4.3 Sky View Factor 16.4.4 Solar Radiation 16.4.5 Normalized Difference Vegetation Index (NDVI) 16.4.6 Normalized Difference Built-Up Index (NDBI) 16.4.7 Frontal Area Index (FAI) 16.4.8 Height Variation (HV) 16.4.9 Average Height (AH) 16.4.10 Distance to Water 16.5 Land Surface Temperature (LST) 16.6 Data Processing 16.7 RF Regression 16.8 Simulating Green Roofs 16.9 Results 16.9.1 Model Results and Accuracy 16.9.2 Variable Importance at Optimal Ntree and Mtry 16.9.3 Comparing Predicted and Observed Values of LST 16.9.4 Prediction After Green Roofs 16.10 Discussion and Conclusions References 17 A Framework to Probe Uncertainties in Urban Cellular Automata Modelling Using a Novel Framework of Multilevel Density Approach: A Case Study for Wallonia Region, Belgium 17.1 Introduction 17.2 Background 17.2.1 Approaches in Evaluating Uncertainty Based on Scale Effects: A Multiscale Approach 17.2.2 Scenario Description and Impacts of Uncertainty on Transition Rules 17.3 Materials and Methods 17.3.1 Study Area 17.3.2 Conceptual Framework 17.4 Observation and Assessments 17.5 Conclusion References Index