Anomaly Detection of Mobility Data with Applications to COVID-19 Situational Awareness

TL;DR

This paper presents a robust live anomaly detection system for high-dimensional mobility data, aiding COVID-19 situational awareness by identifying abrupt mobility changes and assessing policy impacts.

Contribution

The work introduces a simple yet robust anomaly detection system tailored for diverse, high-frequency mobility data to support COVID-19 response efforts.

Findings

Effective detection of mobility anomalies related to COVID-19 measures

Visualization of anomalies and impact estimation of containment policies

Identification of potential outbreak signals from mobility patterns

Abstract

This work introduces a live anomaly detection system for high frequency and high-dimensional data collected at regional scale such as Origin Destination Matrices of mobile positioning data. To take into account different granularity in time and space of the data coming from different sources, the system is designed to be simple, yet robust to the data diversity, with the aim of detecting abrupt increase of mobility towards specific regions as well as sudden drops of movements. The methodology is designed to help policymakers or practitioners, and makes it possible to visualise anomalies as well as estimate the effect of COVID-19 related containment or lifting measures in terms of their impact on human mobility as well as spot potential new outbreaks related to large gatherings.