EO-ALERT: Machine Learning-Based On-Board Satellite Processing for Very-Low Latency Convective Storm Nowcasting

Hinz(1), J. I. Bravo(1), M. Kerr(1), C. Marcos (2), A. Latorre(1), F. Membibre(1)

(1)DEIMOS Space S.L.U., Tres Cantos, Madrid, 28760 Spain, Email: {robert.hinz, juan-ignacio.bravo, murray.kerr}@deimos-space.com

(2)Agencia Estatal de Meteorología, Spain, Email: cmarcosm@aemet.es


Recent years have seen a sharp growth in Satellite Earth Observation (EO) product applications, such as environment and resource monitoring, emergency management and civilian security, leading to an increase in demands on amount, type and quality of remote-sensing satellite data and efficient methods for data analysis. While modern Machine Learning (ML) and Artificial Intelligence (AI) algorithms are revolutionizing automatization, speed and quality of data analysis, the use of satellite EO-based image products for rapid meteorological and civil security applications is still limited by the bottleneck created by the classical EO data chain, which involves the acquisition, compression, and storage of sensor data on-board the satellite, and its transfer to ground for further processing. This introduces long latencies until product delivery to the end user.

The H2020 EU project EO-ALERT (http://eo-alert-h2020.eu) led by DEIMOS, addresses this problem through the development of a next-generation EO data processing chain that moves optimised key elements from the ground segment to on-board the satellite. Applying optimized ML methods, EO products are generated directly on-board the spacecraft.

The capabilities of the EO-ALERT product and its remote sensing data processing chain are demonstrated in an application scenario for meteorological nowcasting and very short-range forecasting for early warnings of convective storms. Its 3-step-approach consists of: Candidate convective cell extraction from satellite imagery, tracking of cell positions and features extracted from infrared channels over time, and the discrimination of convective cells in their different stages of evolution using machine learning classifiers (Gradient Boosting). Training and validation are performed using a specifically created dataset of MSG-SEVIRI images and OPERA weather-radar network composites corresponding to 205 days between 2016 and 2018 exhibiting extreme convective weather events. The performance is further compared against NWCSAF’s Rapid Developing Thunderstorms (RDT-CW) product. Through on-board implementation, the system is able to detect convective storm cells and predict their future trajectories, and to send the processed information to ground, within 5 minutes of the observation.

© 2020 EO-ALERT All Rights Reserved