Make Thunderbolts Less Frightening -- Predicting Extreme Weather Using Deep Learning
This work addresses the challenge of extreme weather forecasting for meteorologists and public safety, but it is incremental as it applies existing deep learning architectures to a specific sub-problem.
The paper tackles the problem of predicting thunderstorms and lightning using a deep learning approach, achieving a probability of detection of over 94% for lightning within the next 15 minutes while reducing false alarms compared to prior methods.
Forecasting severe weather conditions is still a very challenging and computationally expensive task due to the enormous amount of data and the complexity of the underlying physics. Machine learning approaches and especially deep learning have however shown huge improvements in many research areas dealing with large datasets in recent years. In this work, we tackle one specific sub-problem of weather forecasting, namely the prediction of thunderstorms and lightning. We propose the use of a convolutional neural network architecture inspired by UNet++ and ResNet to predict thunderstorms as a binary classification problem based on satellite images and lightnings recorded in the past. We achieve a probability of detection of more than 94% for lightnings within the next 15 minutes while at the same time minimizing the false alarm ratio compared to previous approaches.