EGU21-7516
https://doi.org/10.5194/egusphere-egu21-7516
EGU General Assembly 2021
© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.

Predicting Convective Storm Characteristics using Machine Learning from Hi-Resolution NWP Forecasts

Aniel Jardines1, Manuel Soler1, Javier García-Heras1, Matteo Ponzano2, Laure Raynaud2, Lucie Rottner2, Juan Simarro3, and Florenci Rey4
Aniel Jardines et al.
  • 1Universidad Carlos III Madrid, Aerospace, Spain (ajardine@ing.uc3m.es)
  • 2MeteoFrance
  • 3AEMET
  • 4EarthNetworks

Convective weather represents a significant disruption to air traffic flow management (ATFM) operations. Thunderstorms are the cause for a substantial amount of delay in both the en-route and airport environment. Before the day of operations, poor prediction capability of convective weather prohibits traffic managers from considering weather mitigation strategies during the pre-tactical phase of ATFM planning. As a result, convective weather is mitigated tactically, possibly leading to excessive delays.  

The skill of weather forecasting has greatly improved in recent years. Hi-resolution weather models can predict the future state of the atmosphere for some weather parameters. However, incorporating the output from these sophisticated weather products into an ATFM solution that provides easily interpreted information by the air traffic managers remains a challenge. 

This paper combines data from high-resolution numerical weather predictions with actual storm observations from lightning detecting and satellite images. It applies supervised machine learning techniques such as binary classification, multiclass classification, and regression to train neural networks to predict the occurrence, severity, and altitude of thunderstorms. The model predictions are given up to 36hr in advance, within timeframes necessary for pre-tactical planning of ATFM, providing traffic managers with valuable information for developing weather mitigation plans. 

How to cite: Jardines, A., Soler, M., García-Heras, J., Ponzano, M., Raynaud, L., Rottner, L., Simarro, J., and Rey, F.: Predicting Convective Storm Characteristics using Machine Learning from Hi-Resolution NWP Forecasts, EGU General Assembly 2021, online, 19–30 Apr 2021, EGU21-7516, https://doi.org/10.5194/egusphere-egu21-7516, 2021.

Display materials

Display link Display file

vOSPP judging on display materials

This contribution takes part in the vOSPP contest. Please log in to see the relevant judging section.

Comments on the display material

to access the discussion