Abstract
Pattern discovery in geo-spatiotemporal data (such as traffic and weather data) is about finding patterns of collocation, co-occurrence, cascading, or cause and effect between geospatial entities. Using simplistic definitions of spatiotemporal neighborhood (a common characteristic of the existing general-purpose frameworks) is not semantically representative of geo-spatiotemporal data. We therefore introduce a new geo-spatiotemporal pattern discovery framework which defines a semantically correct definition of neighborhood; and then provides two capabilities, one to explore propagation patterns and the other to explore influential patterns. Propagation patterns reveal common cascading forms of geospatial entities in a region. Influential patterns demonstrate the impact of temporally long-term geospatial entities on their neighborhood. We apply this framework on a large dataset of traffic and weather data at countrywide scale, collected for the contiguous United States over two years. Our important findings include the identification of 90 common propagation patterns of traffic and weather entities (e.g., rain --> accident --> congestion), which results in identification of four categories of states within the US; and interesting influential patterns with respect to the "location", "duration", and "type" of long-term entities (e.g., a major construction --> more traffic incidents). These patterns and the categorization of the states provide useful insights on the driving habits and infrastructure characteristics of different regions in the US, and could be of significant value for applications such as urban planning and personalized insurance.
Introduction
Traditional spatiotemporal data mining often relies on simplistic definitions of a neighborhood—usually just a circular spatial buffer and a shared window of time. This approach fails to capture real-world semantics. For example, a car crash on the northbound side of a divided highway rarely affects southbound traffic, yet a standard algorithm would group them together. Similarly, a heavy snowstorm might end at noon, but its impact on traffic (slush, ice, slow speeds) lasts for hours afterward, breaking the "temporal overlap" rule many models require.
To address these shortcomings, we propose a framework that uses a more rigorous, semantically aware definition of spatiotemporal neighborhoods, allowing for the discovery of patterns that represent actual causal chains rather than random coincidences.
Methodology
The framework splits pattern discovery into two distinct tracks:
Short-term (Propagation) Patterns
The goal is to find "cascading" events. We first identify Child-Parent Relationships (e.g., Event A happens near Event B, and A starts before B). These relationships are organized into Relation Trees. We then use the SLEUTH algorithm, a frequent tree-mining technique, to find common subtrees across the entire country. This reveals "recipes" for traffic chaos, such as Rain → Accident → Heavy Congestion.
Long-term (Influential) Patterns
This track examines "long" entities, defined as the top 1% of durations (roughly >5 hours). We compare the frequency of traffic incidents in a neighborhood during a long-term event (like a major construction project) against the periods immediately before and after that event. Two-sample t-tests across six different scenarios are used to determine if the long-term entity had a statistically significant impact on its surroundings.
Datasets
The study utilizes a massive, real-world dataset collected over two years (August 2016 – August 2018) across the contiguous United States:
- Traffic Data: 13.1 million entities (accidents, congestion, construction, etc.) collected via the MapQuest API.
- Weather Data: 2.2 million entities (rain, snow, fog, etc.) from nearly 2,000 airport weather stations.
The authors have made this integrated "LSTW" dataset publicly available for the research community.
Key Results and Insights
The framework identified 90 unique propagation patterns and categorized US states into four distinct clusters based on driving habits and infrastructure characteristics.
- Weather as a Catalyst: 50 out of the 90 most common short-term patterns were initiated by a weather event. Weather-induced traffic issues are more frequent in the morning, while general traffic-induced congestion peaks in the afternoon.
- The "Construction Paradox": After very long construction projects (over 28 hours), traffic flow often became smoother than it was before the construction started. This suggests road infrastructure improvements or permanent driver adaptation to alternative routes.
- State-Level "Personalities": Cluster 1 (e.g., Ohio, Minnesota) features states where weather impacts are well-mitigated by effective road crews. Cluster 2 (e.g., Pennsylvania, North Carolina) sees significantly more weather-related chain reactions. California (Cluster 4) stands alone with unique, complex congestion and fog-related patterns.
- Driver Adaptation: For long-term entities lasting more than 40 hours, the impact on traffic often diminishes, suggesting that drivers adjust their habits to "the new normal."
Conclusion
While these patterns provide national and state-level insights, future work aims to analyze top-tier cities to see how urban density changes propagation rules. Additionally, refining "lagging impact" models will help predict how long a region remains affected after major weather events conclude.
Summary updated