# Short and Long-term Pattern Discovery Over Large-Scale Geo-Spatiotemporal Data

## TL;DR

This paper introduces a semantically accurate geo-spatiotemporal pattern discovery framework that identifies propagation and influential patterns in large-scale traffic and weather data, revealing regional behaviors and infrastructure impacts.

## Contribution

It proposes a new neighborhood definition for geo-spatiotemporal data and applies it to large-scale US traffic and weather data, uncovering meaningful propagation and influential patterns.

## Key findings

- Identified 90 propagation patterns in US traffic and weather data.
- Categorized US states into four groups based on pattern analysis.
- Revealed influential patterns related to long-term entities affecting local regions.

## 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.