Natural hazards, such as wildfires, earthquakes, and floods can cause damage to roads, which can disrupt the operational efficiency of the network. To rank the roads in order of vulnerability, many studies compute shortest-path measures, such as centrality to quantify structural importance. However, computing these measures is computationally inefficient, especially when recomputing is required after the network structure changes. Recent advancements have enabled the centrality-based ranking problem to be quickly solved on large networks using graph neural networks (GNNs). Although these methods have shown success in other domains for the centrality-based ranking task, they require large amounts of labeled training data and have been rarely explored to address the specific properties of road networks. To overcome these challenges, we propose a fast, data efficient machine learning framework called PathVGAE to learn to rank structurally important roads. PathVGAE leverages a Variational Graph Autoencoder (VGAE) architecture to generate expressive path-based embeddings explicitly for ranking, which are then mapped to a final ranking score prediction. Experimental results show that our model can quickly and accurately rank each road in a network given little data, making it a potentially valuable tool for disruption vulnerability analysis.

The rise in natural disasters and climate-induced events, such as wildfires, hurricanes, and flooding, has significantly affected urban life. These events can disrupt daily activity and flows of individuals and goods on road and transit networks. To enhance urban resilience against disasters, it’s crucial to study and understand road network vulnerability, utilizing data-driven insights to inform planning and preparedness efforts. The aim of this paper is to develop a data-driven exploratory approach to assess vulnerability in road networks in response to a disruption. To accomplish this, we compare the centrality of road segments before, during, and after disaster, considering the network topological structure and movement activity as it is observed through large tracking data of cellphone traces on the network. The novelty of our approach lies in inferring the impact from movement data, instead of manually removing links from the network. The results obtained from this study suggest that incorporating movement data into the assessment of network functionality provides a more realistic estimation of the road network vulnerability in response to a disruption, compared to solely using network topology.

Data driven insights are integral to new forms of knowledge generation in data rich settings. Specifically, in an era of new access to movement data, researchers have opportunities to leverage exis...

Social issues, AI, and climate change are just a few of the disruptive focuses impacting science. The field of GIScience is well positioned to respond to accelerating disruptions due to the interdisciplinary nature of the field and the ability of GIScience approaches to be used in support of decision-making. This manuscript aims to start a conversation that will establish a research agenda for GIScience in an age of disruptions. We outline three guiding principles: (1) focusing on the relevance and real-world impact of research, (2) adopting systems-based thinking and contextual approaches and (3) emphasizing inclusive practices. We then outline prioritized research areas organized by what topics are important focal areas (Data and Infrastructure, Artificial Intelligence, and Causality and Generalizability), and what approaches to science we should be attentive to (Impactful Open Science, Collaborative and Convergent Science, and through Diverse Participation and Partnerships). We conclude with a call to increase impact by balancing slow science with practical and policy-oriented research. We also recognize that while broad adoption of spatial approaches is a signal of GIScience's success, we should continue to work together to advance core knowledge centered on spatial thinking and approaches.

The widespread use of Global Navigation Satellite System (GNSS) trackers has significantly enhanced the availability of vehicle tracking data, providing researchers with critical insights into human mobility. Map matching, a key preprocessing step in movement analysis, matches vehicle tracking data to road segments but often introduces errors that can affect subsequent analyses. Existing map-matching methods, categorized into classic spatially generalizable methods and region-specific deep-learning-based methods, both have limitations. Region-specific deep learning methods, while more accurate, do not transfer well across different geographical regions. Moreover, the temporal adaptability of both approaches—their ability to handle GNSS signals of varying sampling intervals—has not been thoroughly examined. To overcome these limitations, we introduce Medark, a novel framework for detecting and rectifying errors in classic map-matching methods while preserving spatial generalizability. The proposed model is trained using a transfer-learning approach with synthetic trajectories generated in Ann Arbor and Los Angeles at various sampling intervals and a real vehicle trajectory dataset from Ann Arbor. Our experimental results validate the effectiveness of Medark. This framework can be integrated with any map-matching method to improve accuracy and produce high-quality trajectories for further analysis.

Siting decisions can influence access, logistics, supply chains and transportation and other qualities, making them critical to the success of a service system. Often access to resources or opportunities is the primary concern, but other performance characteristics can be equally important. This paper considers access combined with service coverage in site selection as a bi-objective spatial optimization model. Specifically, the access objective aims to minimize demand proximity to its closest sited facility and the coverage objective seeks to maximize demand within a service distance standard. Solution of the problem is challenging due to the nature of facility location, where siting may occur anywhere in continuous space. Further complicating matters is the need to identify tradeoffs, or nondominated solutions, as the problem involves two objectives being simultaneously optimized. This research introduces a heuristic approach to solve a multi-facility, bi-objective location-allocation problem involving facility location in continuous space, where access and coverage are simultaneously considered. A unique case study is reported involving the strategic positioning of outfielders in baseball, where fielder access and coverage to batted balls are fundamentally important. The heuristic is found to perform exceptionally well, identifying the best range of solutions for this problem from which strategic placement of fielders can be planned.

The COVID-19 pandemic resulted in profound changes in mobility patterns and altered travel behaviors locally and globally. As a result, movement metrics have widely been used by researchers and policy makers as indicators to study, model, and mitigate the impacts of the COVID-19 pandemic. However, the veracity and variability of these mobility metrics have not been studied. This paper provides a systematic review of mobility and social distancing metrics available to researchers during the pandemic in 2020 in the United States. Twenty-six indices across nine different sources are analyzed and assessed with respect to their spatial and temporal coverage as well as sample representativeness at the county-level. Finally global and local indicators of spatial association are computed to explore spatial and temporal heterogeneity in mobility patterns. The structure of underlying changes in mobility and social distancing is examined in different US counties and across different data sets. We argue that a single measure might not describe all aspects of mobility perfectly.

There has not been a time in the history of GIScience when movement analytics and mobility insights have played such an important role in policymaking as in today’s global responses to the COVID-19...

There is long-standing scientific interest in understanding purposeful movement by animals and humans. Traditionally, collecting data on individual moving entities was difficult and time-consuming, limiting scientific progress. The growth of location-aware and other geospatial technologies for capturing, managing and analyzing moving objects data are shattering these limitations, leading to revolutions in animal movement ecology and human mobility science. Despite parallel transitions towards massive individual-level data collected automatically via sensors, there is little scientific cross-fertilization across the animal and human divide. There are potential synergies from converging these separate domains towards an integrated science of movement. This paper discusses the data-driven revolutions in the animal movement ecology and human mobility science, their contrasting worldviews and, as examples of complementarity, transdisciplinary questions that span both fields. We also identify research challenges that should be met to develop an integrated science of movement trajectories.

“We would like to dedicate this special issue to the memory of Professor Rein Ahas (1966 – 2018), a pioneer of computational movement analysis and mobility analytics, who sadly and very unexpectedl...

Computational Movement Analysis focuses on the characterization of the trajectory of individuals across space and time. Various analytic techniques, including but not limited to random walks, Brownian motion models, and step selection functions have been used for modeling movement. These fall under the rubric of signal models which are divided into deterministic and stochastic models. The difficulty of applying these models to the movement of dynamic objects (e.g. animals, humans, vehicles) is that the spatiotemporal signal produced by their trajectories a complex composite that is influenced by the Geography through which they move (i.e. the network or the physiography of the terrain), their behavioral state (i.e. hungry, going to work, shopping, tourism, etc.), and their interactions with other individuals. This signal reflects multiple scales of behavior from the local choices to the global objectives that drive movement. In this research, we propose a stochastic simulation model that incorporates contextual factors (i.e. environmental conditions) that affect local choices along its movement trajectory. We show how actual global positioning systems observations can be used to parameterize movement and validate movement models and argue that incorporating context is essential in modeling movement.

The study of movement is progressing rapidly as a subdiscipline in Geographic Information Science (GIScience). At the fulcrum of this new research area in GIScience are movement observations. Movem...

This article describes a novel approach for finding similar trajectories, using trajectory segmentation based on movement parameters (MPs) such as speed, acceleration, or direction. First, a segmentation technique is applied to decompose trajectories into a set of segments with homogeneous characteristics with respect to a particular MP. Each segment is assigned to a movement parameter class (MPC), representing the behavior of the MP. Accordingly, the segmentation procedure transforms a trajectory to a sequence of class labels, that is, a symbolic representation. A modified version of edit distance called normalized weighted edit distance (NWED) is introduced as a similarity measure between different sequences. As an application, we demonstrate how the method can be employed to cluster trajectories. The performance of the approach is assessed in two case studies using real movement datasets from two different application domains, namely, North Atlantic Hurricane trajectories and GPS tracks of couriers in London. Three different experiments have been conducted that respond to different facets of the proposed techniques and that compare our NWED measure to a related method.