Segmentations with Explanations for Outage Analysis

Recent hurricane events have caused unprecedented amounts of damage and severely threatened our public safety and economy. The most observable (and severe) impact of these hurricanes is the loss of electric power in many regions, which causes the breakdown of many public services. Understanding the power outages and how they evolve during a hurricane provide insights on how to reduce outages in the future, and how to improve the robustness of the underlying critical infrastructure systems. In this paper, we propose a novel segmentation with explanations framework to help experts understand such datasets. Our method, CUT-n-REVEAL, first finds a segmentation of the outage sequences to capture pattern changes in the sequences. We then propose a novel explanation optimization problem to find an intuitive explanation of the segmentation, that highlights the culprit of the change. Via extensive experiments, we show that our method performs consistently in multiple datasets with ground truth. We further study real county-level power outage data from several recent hurricanes (Matthew, Harvey, Irma) and show that CUT-n-REVEAL recovers important, nontrivial and actionable patterns for domain experts.