In Russia they are creating an agricultural system “friend or foe”

MOSCOW, November 9– . Scientists at Samara University created a unique system consisting of a hyperspectrometer and a special neural network for plant recognition, capable of identifying weeds. According to experts, the development will make it possible to create a sensor that, in tandem with a sprayer and a nozzle control system, will allow not only to find, but also to immediately destroy weeds, separating them from “useful” plants. The research results are published in the IOP Conference Series: Earth and Environmental Science.
As university scientists note, weeds develop very quickly, significantly outpacing the development of cultivated plants. They take away light, water, and nutrients, creating unfavorable conditions for the development of other crops. Also, young weeds can be intermediaries in the spread of diseases, while climbing weeds can complicate harvesting, which leads to large crop losses.

Researchers from the Samara National Research University named after academician S.P. Korolev (Samara University) have proposed a new way to combat weeds. They developed a system consisting of a hyperspectrometer and a special neural network for recognizing plants of different species, which is capable of both separating weeds from cultivated plants and separating different types of cultivated plants.
“

“We have received a system that will be able to solve a number of applied problems, primarily within the framework of precision agriculture. The hyperspectral camera developed at our university generates 150 spectral channels. It is not always possible to analyze this array of information using simple methods, so the key result of the work was the creation of a neural network that can recognize three types of plants. In the future, with the development of technology, the list of recognized crops will expand,” said Roman Skidanov, professor of the Department of Technical Cybernetics at Samara University.

He noted that the developed system will make it possible to create a weed sensor with which you can destroy them in a targeted manner without affecting cultivated plants. To do this, the device must be used together with an automatic sprayer, integrating it into the nozzle control system.
< /span>
In addition, according to scientists, the neural network together with a hyperspectrometer can be used as the basis of technical vision systems for unmanned agricultural machines. It can also be used on UAVs as a system for diagnosing plant health and general monitoring or control of crops.

As Skidanov noted, the development will help save and reduce the cost of some processes in agriculture.
«The economic effect can reach several hundred rubles for each cultivated hectare. It consists of saving expensive chemicals during targeted treatment of plants and increasing productivity,» he emphasized.
Samara University is a participant in the Russian state university support program «Priority-2030» «national project «Science and Universities».