Skip to main content

EO4NOWCAST: Near Real-Time Soil Moisture Assessment and Pluvial Flood Nowcasting services for the Genoa (Italy) territory

EO4NOWCAST is a containerized application that comprises: - a machine learning pipeline for the hourly prediction of the soild moisture based on the NDMI maps from Copernicus S2 and ground based precipitation; - a machine learning pipeline for the 5-min prediction of the flood risk; - a backend API application for accessing the pipeline products - frontend web application for navigating the EO4NOWCAST functionalities


Business Category
Earth Observation

What is the challenge that is being addressed?

The challenge is to provide a generally available tool to assess the risk of pluvial floods caused by intense and severe precipitation events based on novel technologies such as satellite EO products, AI model and meteorological monitoring and prediction services commonly available in any country.

What is the AI solution the project has implemented?

The solution is a generalized Decision Support System DSS platform that processes short term pluvial flood prediction in small and medium sized river basins, applicable in any context based on the use of satellite EO products and available meteorological monitoring systems thanks to machine learning methods. As a secondary result, the project has implemented a method to estimate near real-time soil moisture maps from the last available Copernicus Sentinel-2 tile.

Who helped implement the AI solution?

This solution is implemented in the context of EO4NOWCAST, a winning project from the AI4Copernicus 3rd Open Call, by the Artys company. The results of the project are available here