Regionalization refers to the process of partitioning geographic space into regions that are internally similar yet distinct from each other. This process is fundamental for understanding complex spatial relationships and how areas interact with each other. Spatial networks provide a rich source of data (e.g., flows of people, goods or information) that can be used to generate regions. How to extract useful information from the spatial networks for better regionalization has been a longstanding topic of interest, and methods such as community detection and node clustering have been well studied. However, nowadays, many regionalization tasks remain confined to domain-specific datasets and traditional methods, while the rapid growth of the big data era and Artificial Intelligence (AI) methods has created more opportunities for improved regionalization. This dissertation focuses on how to utilize mobility-based spatial networks and Geospatial Artificial Intelligence (GeoAI) methods for better regionalization. This dissertation will start by demonstrating how spatial networks can be applied to delineate Rational Service Areas (RSAs) in the public health domain. Existing RSAs are usually developed based on the local knowledge of public health needs and are created through time-intensive manual work by health service officials. In this dissertation, a data-driven and spatially constrained community detection method based on aggregated human mobility flow data is proposed to automate the process of establishing the statewide RSAs in GIS software. The proposed method outperforms other baselines in the multiple metrics and shows the promising potential of mobility-based regionalization in the public health domain. Then, the dissertation improves the existing community detection method by proposing GeoAI-enhanced models based on Graph Convolutional Networks and Graph Attention Networks. The methods identify regions by considering attribute similarity, geographic adjacency and spatial interactions. The methods are compared with multiple baselines and perform best when one wants to maximize node attribute similarity and spatial interaction intensity simultaneously within the communities. It is applied to the shortage area delineation problem in public health and demonstrates its promise in solving regionalization problems. Lastly, the dissertation improves the interpretability of the proposed GeoAI methods. Most of the AI methods are considered black boxes, meaning that humans cannot understand the internal process, leading to low transparency and trustworthiness of the AI-generated results. However, geographic research often requires an explanation and discussion of why certain predictions are generated to understand the processes underlying the observed data. To promote the application of GeoAI methods to regionalization, the dissertation applies an explainable AI model to the proposed GeoAI-based community detection method. The explanations provide important node features and subgraph structures that contribute the most to each prediction. By examining individual and aggregated explanations, community activity spaces are compared, and potential regional patterns are discovered to support the reasoning of regionalization results. In summary, this dissertation aims to provide valuable insights into how human mobility data and GeoAI methods can be applied to regionalization tasks in spatial networks. It proposes a framework for automatic area delineation using mobility data that can be expanded to other use cases. Then, it improves the existing regionalization methods by introducing GeoAI models to combine node attributes and edge connections. Thirdly, it provides insights into how GeoAI models can be interpreted and explained to better understand the underlying geographic phenomena.

This book is a collection of seminal position essays by leading researchers on new development in Geographic Information Sciences (GIScience), covering a wide range of topics and representing a variety of perspectives. The authors propose enrichments and extensions to the conceptual framework of GIScience; discuss a series of transformational methodologies and technologies for analysis and modeling; elaborate on key issues in innovative approaches to data acquisition and integration, across earth sensing to social sensing; and outline frontiers in application domains, spanning from natural science to humanities and social science, e.g., urban science, land use and planning, social governance, transportation, crime, and public health, just name a few. The book provides an overview of the strategic directions on GIScience research and development. It will benefit researchers and practitioners in the field who are seeking a high-level reference regarding those directions.

This comprehensive handbook covers Geospatial Artificial Intelligence (GeoAI), which is the integration of geospatial studies and AI machine (deep) learning and knowledge graph technologies. It explains key fundamental concepts, methods, models, and technologies of GeoAI, and discusses the recent advances, research tools, and applications that range from environmental observation and social sensing to natural disaster responses. As the first single volume on this fast-emerging domain, Handbook of Geospatial Artificial Intelligence is an excellent resource for educators, students, researchers, and practitioners utilizing GeoAI in fields such as information science, environment and natural resources, geosciences, and geography. Features Provides systematic introductions and discussions of GeoAI theory, methods, technologies, applications, and future perspectives Covers a wide range of GeoAI applications and case studies in practice Offers supplementary materials such as data, programming code, tools, and case studies Discusses the recent developments of GeoAI methods and tools Includes contributions written by top experts in cutting-edge GeoAI topics This book is intended for upper-level undergraduate and graduate students from different disciplines and those taking GIS courses in geography or computer sciences as well as software engineers, geospatial industry engineers, GIS professionals in non-governmental organizations, and federal/state agencies who use GIS and want to learn more about GeoAI advances and applications.

This book is the second in a two-volume series that introduces the field of spatial data science. It moves beyond pure data exploration to the organization of observations into meaningful groups, i.e., spatial clustering. This constitutes an important component of so-called unsupervised learning, a major aspect of modern machine learning. The distinctive aspects of the book are both to explore ways to spatialize classic clustering methods through linked maps and graphs, as well as the explicit introduction of spatial contiguity constraints into clustering algorithms. Leveraging a large number of real-world empirical illustrations, readers will gain an understanding of the main concepts and techniques and their relative advantages and disadvantages. The book also constitutes the definitive user’s guide for these methods as implemented in the GeoDa open source software for spatial analysis. It is organized into three major parts, dealing with dimension reduction (principal components, multidimensional scaling, stochastic network embedding), classic clustering methods (hierarchical clustering, k-means, k-medians, k-medoids and spectral clustering), and spatially constrained clustering methods (both hierarchical and partitioning). It closes with an assessment of spatial and non-spatial cluster properties. The book is intended for readers interested in going beyond simple mapping of geographical data to gain insight into interesting patterns as expressed in spatial clusters of observations. Familiarity with the material in Volume 1 is assumed, especially the analysis of local spatial autocorrelation and the full range of visualization methods. Luc Anselin is the Founding Director of the Center for Spatial Data Science at the University of Chicago, where he is also Stein-Freiler Distinguished Service Professor of Sociology and the College, as well as a member of the Committee on Data Science. He is the creator of the GeoDa software and an active contributor to the PySAL Python open-source software library for spatial analysis. He has written widely on topics dealing with the methodology of spatial data analysis, including his classic 1988 text on Spatial Econometrics. His work has been recognized by many awards, such as his election to the U.S. National Academy of Science and the American Academy of Arts and Science.

Providing an authoritative assessment of the current landscape of spatial analysis in the social sciences, this cutting-edge Handbook covers the full range of standard and emerging methods across the social science domain areas in which these methods are typically applied. Accessible and comprehensive, it expertly answers the key questions regarding the dynamic intersection of spatial analysis and the social sciences.

This nine-volume set LNCS 14104 – 14112 constitutes the refereed workshop proceedings of the 23rd International Conference on Computational Science and Its Applications, ICCSA 2023, held at Athens, Greece, during July 3–6, 2023. The 350 full papers and 29 short papers and 2 PHD showcase papers included in this volume were carefully reviewed and selected from a total of 876 submissions. These nine-volumes includes the proceedings of the following workshops: Advances in Artificial Intelligence Learning Technologies: Blended Learning, STEM, Computational Thinking and Coding (AAILT 2023); Advanced Processes of Mathematics and Computing Models in Complex Computational Systems (ACMC 2023); Artificial Intelligence supported Medical data examination (AIM 2023); Advanced and Innovative web Apps (AIWA 2023); Assessing Urban Sustainability (ASUS 2023); Advanced Data Science Techniques with applications in Industry and Environmental Sustainability (ATELIERS 2023); Advances in Web Based Learning (AWBL 2023); Blockchain and Distributed Ledgers: Technologies and Applications (BDLTA 2023); Bio and Neuro inspired Computing and Applications (BIONCA 2023); Choices and Actions for Human Scale Cities: Decision Support Systems (CAHSC-DSS 2023); and Computational and Applied Mathematics (CAM 2023).

Starting around the late 1950s, several research communities began relating the geometry of graphs to stochastic processes on these graphs. This book, twenty years in the making, ties together research in the field, encompassing work on percolation, isoperimetric inequalities, eigenvalues, transition probabilities, and random walks. Written by two leading researchers, the text emphasizes intuition, while giving complete proofs and more than 850 exercises. Many recent developments, in which the authors have played a leading role, are discussed, including percolation on trees and Cayley graphs, uniform spanning forests, the mass-transport technique, and connections on random walks on graphs to embedding in Hilbert space. This state-of-the-art account of probability on networks will be indispensable for graduate students and researchers alike.

Increasingly, human beings are sensors engaging directly with the mobile Internet. Individuals can now share real-time experiences at an unprecedented scale. Social Sensing: Building Reliable Systems on Unreliable Data looks at recent advances in the emerging field of social sensing, emphasizing the key problem faced by application designers: how to extract reliable information from data collected from largely unknown and possibly unreliable sources. The book explains how a myriad of societal applications can be derived from this massive amount of data collected and shared by average individuals. The title offers theoretical foundations to support emerging data-driven cyber-physical applications and touches on key issues such as privacy. The authors present solutions based on recent research and novel ideas that leverage techniques from cyber-physical systems, sensor networks, machine learning, data mining, and information fusion. Offers a unique interdisciplinary perspective bridging social networks, big data, cyber-physical systems, and reliability Presents novel theoretical foundations for assured social sensing and modeling humans as sensors Includes case studies and application examples based on real data sets Supplemental material includes sample datasets and fact-finding software that implements the main algorithms described in the book

This textbook is a comprehensive introduction to applied spatial data analysis using R. Each chapter walks the reader through a different method, explaining how to interpret the results and what conclusions can be drawn. The author team showcases key topics, including unsupervised learning, causal inference, spatial weight matrices, spatial econometrics, heterogeneity and bootstrapping. It is accompanied by a suite of data and R code on Github to help readers practise techniques via replication and exercises. This text will be a valuable resource for advanced students of econometrics, spatial planning and regional science. It will also be suitable for researchers and data scientists working with spatial data.