Scientists from the Iowa State University, United States of America, are working towards a future in which farmers may use unmanned aerial vehicles to detect and even foresee diseases and stress in their crops. Their vision is based on machine learning, an automated process in which technology can help farmers respond to plant stress more efficiently.
Arti Singh, an Adjunct Professor of Agronomy, leads a multidisciplinary research team that recently received a three-year grant of USD 499,845 from the National Institute of Food and Agriculture (USDA) to develop machine learning technology, which could automate farmers’ ability to diagnose a range of major stresses on soy crops. The technology which is under development would use cameras coupled with unmanned aerial vehicles, or UAVs, to collect panoramic images of soy fields. A computer application would automatically analyze the images and would alert the farmer about the matters with problems.
“Basically, machine learning is to simply train a machine to do something that we do”, said Singh. “When you want to teach a child what a car is, you show them cars. And that is what we are doing to train computer algorithms, showing them a large number of images of various soy stresses to identify, classify, quantify and foresee stress in the field.”, he finishes.
The research team gathered an enormous group of soy image data, some of them healthy and some of them with diseases and stress, which they have labeled. A computer program scans labeled images and assembles algorithms that can recognize stress in new images.
Source: https://www.agrolink.com.br/noticias/computadores-podem-identificar-estresse-da-soja_424328.html
