The ‘Toward precision agriculture 2.0’ research programme has included a group of potato farmers carrying out test runs with sensor observations by drones. The drone images show exactly where they should apply more or less nitrogen on their fields, allowing farmers to use the product more efficiently.
Frits van Evert, expert in precision agriculture at Wageningen University & Research said, “Dutch potato farmers apply an average of some 250 kilograms of nitrogen per hectare per year.It is applied in one session, just before or just after planting. Because weather conditions in the Netherlands vary significantly, more nitrogen may be lost in one year compared to another.”
Colour differences show nitrogen demand
According to Van Evert it is better to apply two thirds of the recommended amount of nitrogen at the start of cultivation. Advanced sensor observations provide the solution: “The level at which a plant reflects infrared, red and green light depends on the amount of nitrogen it contains. A plant with too little nitrogen has minor colour variations compared to a plant with sufficient nitrogen and modern sensors can measure those differences.”
These measurements can roughly be performed in three ways.
1. With a satellite: a low-cost solution, but unusable when cloudy.
2. With a sensor manually operated in the field or installed on a tractor: a reliable but costly method that hasn’t been widely accepted in practice.
3. With multispectral cameras and sensors in drones: this relatively new method is expected to make significant progress in the coming years.
How Application on Akkerweb works:
The images captured by the drone of the potato field are converted into a map. The farmer is sent this map by e-mail and can upload it via an app on Akkerweb which we developed with Agrifirm. This software then rolls out advice for farmers as to where they should use more or less nitrogen, and which areas don’t need extra application. While we have optimised the method for the use of the eBee-drone, developers of other drone types can make their sensor systems suitable too.
Source : https://www.wur.nl/