CNN-based architectures can be used to increase the prediction lead time of thunderstorms

Our latest research shows that Convolutional Neural Networks (CNN)-based architectures can be used to increase the prediction lead time of thunderstorms in the aviation field. These results are published in the journal paper titled “Thunderstorm prediction during pre-tactical air-traffic-flow management using convolutional neural networks”. A study written by Aniel Jardines^a, Hamidreza Eivazi^b, Elias Zea^b, Javier García-Heras^a, Juan Simarro^c, Evelyn Otero^b, Manuel Soler^a, Ricardo Vinuesa^b.

• ^a Department of Bioengineering and Aerospace Engineering, Universidad Carlos III de Madrid, Avda. Universidad 30, 28911 Leganés, Spain
• ^b Department of Engineering Mechanics, KTH Royal Institute of Technology, SE-1044, Stockholm, Sweden
• ^c Agencia Estatal de Meteorología (AEMET), Valencia, Spain

Abstract

Thunderstorms can be a large source of disruption for European air-traffic management causing a chaotic state of operation within the airspace system. In current practice, air-traffic managers are provided with imprecise forecasts which limit their ability to plan strategically. As a result, weather mitigation is performed using tactical measures with a time horizon of three hours. Increasing the lead time of thunderstorm predictions to the day before operations could help air-traffic managers plan around weather and improve the efficiency of air-traffic-management operations. Emerging techniques based on machine learning have provided promising results, partly attributed to reduced human bias and improved capacity in predicting thunderstorms purely from numerical weather prediction data. In this paper, we expand on our previous work on thunderstorm forecasting, by applying convolutional neural networks (CNNs) to exploit the spatial characteristics embedded in the weather data. The learning task of predicting convection is formulated as a binary-classification problem based on satellite data. The performance of multiple CNN-based architectures, including a fully-convolutional neural network (FCN), a CNN-based encoder–decoder, a U-Net, and a pyramid-scene parsing network (PSPNet) are compared against a multi-layer-perceptron (MLP) network. Our work indicates that CNN-based architectures improve the performance of point-prediction models, with a fully-convolutional neural-network architecture having the best performance. Results show that CNN-based architectures can be used to increase the prediction lead time of thunderstorms. Lastly, a case study illustrating the applications of convection-prediction models in an air-traffic-management setting is presented.

Elsevier offers 50-day open access to the full paper here.