Multivariate Multi-Step Convection Nowcasting with Deep Neural Networks: The Novara Case Study

Biondi, Riccardo; Chkeir, Sandy; Anesiadou, Aikaterini; Mascitelli, Alessandra; Realini, Eugenio; Nisi, Luca und Cimarelli, Corrado (2022): Multivariate Multi-Step Convection Nowcasting with Deep Neural Networks: The Novara Case Study. IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium, Kuala Lumpur, Malaysia, 17-22 July 2022. In: IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium, pp. 6598-6601

Abstract

Severe weather events are constantly increasing over northern Italy impacting the air traffic of one of the major airports of Europe: Milano Malpensa. Monitoring and predicting extreme convection is very challenging especially when it develops locally in a short time range. This work is performed within two projects funded by the H2020 SESAR Programme, with the objective of nowcasting with high accuracy the strong weather events affecting the airport. We collected different types of data from 10 locations around the airport and developed an end-to-end nowcasting deep neural networks based model for each of these stations. We show in this paper the results that we obtained for Novara, the only station for which we have available weather stations, radar, GNSS and lightning.

• Item Type: Conference or Workshop Item (Paper)
• Faculties: Geosciences > Department of Earth and Environmental Sciences > Mineralogy, Petrology and Geochemistry
• Subjects: 500 Science > 550 Earth sciences and geology
• Language: English