VALENCIA, 27 Feb. (EUROPA PRESS) –
A team from the GTI-IA research group of the Valencian University Institute for Research in Artificial Intelligence (Vrain) of the Universitat Politècnica de València (UPV) has registered a device that, through the use of artificial intelligence (AI), detects up to a total of 27 crop diseases early to facilitate their early treatment and stop their spread.
‘Plantillo’ integrates artificial vision, data processing and deep learning tools, within a low-power device, as reported by the academic institution in a statement. In addition, it is an economical, upgradeable and portable device that is easy to attach to drones, machinery or autonomous agricultural robots that makes it easier for field professionals to detect and classify a total of 27 diseases of crops such as apple, blueberry, cherry, corn. , grape, orange, peach, pepper, potato, raspberry, soy, pumpkin, strawberry and tomato.
This software uses an innovative artificial intelligence model that runs directly on the device and is known as Edge AI. The device has a sophisticated neural network model specialized in image classification that not only has the ability to capture them, but is also capable of processing them “quickly and efficiently.” In this way, it analyzes the images to determine the presence of diseases and identify the specific type of disease that is present in the image.
Thus, “greater efficiency and speed are achieved in data analysis since it is not necessary to depend on external network connections or remote servers. This is especially beneficial in environments such as crop areas with limited or critical bandwidth.” , explained the main researcher of this VRAIN project from the UPV, Cédric Marco Detchart, as spokesperson for the team formed by the researchers who also developed it Jaime Andrés Rincón, Carlos Carrascosa and Vicente Javier Julián.
In addition, its ability to identify the disease early, as well as the areas where it has begun to manifest itself, “is essential to locate the affected points and take preventive measures with precision. By detecting diseased areas at an early stage, the device allows intervention “fast and precise”, which facilitates the “specific” treatment of the affected areas, implies cost savings by avoiding the unnecessary application of fungicides, pesticides and herbicides, and the progression to other parts of the field”, underlined Cédric Marco Detchart.