ODFuse4Ship – Ocean Data Fusion for Ship Routing
Winning project from the 3rd Open Call funded by the AI4Copernicus Project
Country: France | Domain: Maritime
An interview with the winners – Alexandre Stegner, representing the ODFuse4Ship project
Q: What was your motivation for creating this proposal?
A: Our motivation is to develop and improve our technology that fuses different satellite data, thanks to advanced AI computer vision, in order to produce reliable and high resolution surface currents.
Q: Which is the most critical impact (societal or other) that your project could make (if you could name one) ?
A: Our goal is to provide oceanic data and innovative solutions to support the decarbonisation of maritime transport. Our short term optimal routing solution could reduce CO2 emissions by several hundred thousand tons per year. The optimisation of maritime transport is developing at high speed because it can be effective from now on without modifying the ships.
Q: Considering the recent funding received through the AI4Copernicus Open Calls, do you have any plans for further development of your idea?
A: The funding received through the AI4Copernicus Open Calls will amplify our technological development on data fusion. Further development will be to implement and test a short-term forecast model for surface oceanic currents using deep learning LSTM.
A few words about the project: An ocean of Earth Observation data is available today through the Copernicus programme. Each one of the individual observation data or numerical model outputs has their own disadvantages, offering limited reliability for operational use. The fusion of satellite observations of the ocean from different sensors (infrared, visible, altimetry, radar) through advanced AI-Computer Vision methods can provide end-users with real-time, highly-reliable and high-resolution surface currents.