# Short-term prediction of Electricity Outages Caused by Convective Storms

## TL;DR

This paper introduces a machine learning framework for predicting power outages caused by convective storms by tracking storm cells using radar images and classifying their damage potential, addressing data imbalance issues.

## Contribution

A novel approach combining radar image analysis and machine learning to predict storm-induced outages, with a focus on storm cell tracking and damage classification.

## Key findings

- Random forest and deep neural networks evaluated for classification.
- Storm cell tracking improves outage prediction accuracy.
- Handling imbalanced data remains a key challenge.

## Abstract

Prediction of power outages caused by convective storms which are highly localised in space and time is of crucial importance to power grid operators. We propose a new machine learning approach to predict the damage caused by storms. This approach hinges identifying and tracking of storm cells using weather radar images on the application of machine learning techniques. Overall prediction process consists of identifying storm cells from CAPPI weather radar images by contouring them with a solid 35 dBZ threshold, predicting a track of storm cells and classifying them based on their damage potential to power grid operators. Tracked storm cells are then classified by combining data obtained from weather radar, ground weather observations and lightning detectors. We compare random forest classifiers and deep neural networks as alternative methods to classify storm cells. The main challenge is that the training data are heavily imbalanced as extreme weather events are rare.