FertiRec – Postcode based fertiliser rate recommendation system
Winning project from the 3rd Open Call funded by the AI4Copernicus Project
Country: Germany | Domain: Agriculture
An interview with the winners – Riazuddin Kawsar, representing the FertiRec project
Q: What was your motivation for creating this proposal?
A: More and more fertiliser regulations are trying to minimize the environmental damage caused by over fertilisation. This is a decade old problem, which yet to be solved in an efficient way. The existing solutions are either too expensive or time consuming. The goal of this project was to introduce innovation that can provide accurate fertiliser rate recommendations using only satellite imagery in a simple and affordable manner.
Q: Which is the most critical impact (societal or other) that your project could make (if you could name one)?
A: Using satellite imagery, we developed models that can estimate crop-specific total nitrogen uptake in kg/ha units. Using historical satellite imagery, we can estimate total nitrogen uptake for previous years and and by utilising those observations we can provide a reasonable recommendation for nitrogen fertilisation ahead of the season. This helps farmers. Such information can also assist input manufacturers and retailers in estimating location-based demand, as well as assisting their customers with input purchase decisions and ultimately enable digital sales. Furthermore, as financial institutes are moving towards sustainable financing, they require a consistent matrices to assess the sustainability of their farmer clients’, farm operations. we can detect over and under fertilised areas and can be used as a reliable matrices for measuring environmental sustainability.
Q: Considering the recent funding received through the AI4Copernicus Open Calls, do you have any plans for further development of your idea?
A: The project will allow demonstrating the effectiveness of the approach in Germany for four important crops (Wheat, barley, Oilseed rape and Corn). In the end, we aim to generalise our models so they may be used around the globe and for a larger variety of crops.
A few words about the project: The Nitrogen (N) fertilisation rate recommendation is a decade old problem that yet to be solved in an efficient way. Existing technologies are either too expensive or time consuming. As a result, farmers make fertiliser rate decisions based on their experience, which is not data-driven and includes guesswork. The proposed project intends to provide a solution to the current service gaps. With the solution, a user can get a fertiliser rate recommendation, ahead of the season, by providing field boundary and crop type. This not only helps the farmer in fertilisation efforts, but also assists them in fertiliser purchasing decisions. We intend to make the service available for key crops in western European countries.