- Points of Contact:
- Franck Ranera (Serco Project Manager)
- Gilles Lavaux (Serco Work Package leader)
The H2020 RapidAI4EO project aims to establish the foundations for the next generation of continuous land monitoring applications. The project’s ambition is to enable new and better ways of measuring and understanding the human footprint on our planet, which is a key challenge of the UN Sustainable Development Goals.
As part of the project, a Graphical User Interface (GUI) demo has been developed by partner Serco on the ONDA cloud platform with the goal to provide a public demonstration of land change detection and mapping results.
The RapidAI4EO Training dataset is based on the fusion of Copernicus Sentinel-2 and Planet High Resolution imagery over 500,000 patch locations in Europe. The project consortium has then developed improved AI processes, through the use of Deep learning algorithms, to produce Land Use Land Cover (LULC) maps and change detection heatmaps, therefore providing intensified monitoring at a much higher level of detail and temporal cadence than it is possible today.
Using these input products, the GUI provides a GIS web-based interface for visualising imagery, heatmaps and LULC maps updates over three demonstration areas: the result panel conveniently displays previous and current imagery on which changes are found.
The demo is a useful tool to understand the value added of these LULC products, and, although originally designed for the change detection use case, it is based on open standard allowing the quick ingestion of other datasets, enlarging the relevancy to other thematic areas.
