Kick off AI4FOOD! A data-fusion and time series framework as a service
A service to characterize land surface properties, monitor trends and detect changes
We are proud to announce the kick off of AI4FOOD, a brand new ESA project initiated to detect and predict (near-term) change in different components of the land environment, with a special emphasis on agriculture and food systems. Within AI4FOOD we will set up an open source, modular, extensible, and reusable data-fusion and time series framework as a service. We will mainly focus on Sentinel-1 SAR and Sentinel-2 multispectral data fusion.
We will use new advanced Artificial Intelligence (AI) / Machine Learning (ML) techniques to evaluate and develop various algorithms for creation of fused continuous data streams. These algorithms will allow modelling of various land surface dynamics that can be used to characterize land surface properties, monitor trends and detect changes. We will use OpenEO API for the implementation and eventually offer these algorithms as separate services to the end users.
The AI4FOOD framework will be tested on three real life use cases, each associated with a stakeholder:
- Land Cover Change Monitoring (FAO)
- Cropland Phenology Indicators (ITACyL)
- Agriculture and Land Management Activities Identification (Agency for Agricultural Markets and Rural Development, Slovenia)
For this project, VITO has partnered with University of Valencia and Sinergise as top European experts on data fusion, time series techniques, open-source implementation, and operational service provision to users. Within VITO Remote Sensing, we will take the lead on project management, algorithm implementation and operational service deployment.
The AI4FOOD project will run until mid-2023. The development and progress will be visible to public through GitHub.