Agricultural fields are checked by MRI


Big data, machine learning, artificial intelligence. Over the past decade, these have become one of the biggest buzzwords in the tech industry. They affect our daily lives – think voice and facial recognition on smartphones. These same technologies are making greater strides in the agricultural industry.

Just a year ago, Jennifer Hobbs climbed a silo. Beside her was a farmer. The two were looking at the field. “This is how he spotted his field and optimized his management decisions,” the director of machine learning at Intelinair told the group of women gathered for the Women in Agribusiness Summit. “That was before he passed AgMRI.”

Data gathering

She explained that humans are limited to the visual spectrum. “And through decades of research, agronomy and crop science, we know that important information also lives in the infrared spectrum,” said Hobbs.

Hobbs and his team are using high-resolution aerial imagery, machine learning and computer vision to detect patterns of interest in fields and send alerts to farmers, so they can see problems before they go. do not become. The system is known as the AgMRI Agricultural Intelligence Platform.

Farmers can see the condition of the fields at a glance and then identify fields that have weed, water, climate fertility and many other issues. Intelinair collects data from satellite planes and drones several times during the season.

Courtesy of Mindy Ward

LAYERED APPEARANCE: A layered approach to data allows Intelinair to predict problem areas before they become a problem in agricultural fields.

This information from imagery is combined with other data sources, such as equipment data, weather, soil type, typography, etc. to form the basis of a virtual model of the field that captures all of the important characteristics and properties of the field.

Then they use machine learning, deep learning from computer vision, to extract patterns of interest around information such as crop type, nutrient deficiency, growth stage, and patterns. equipment.

“All of this information can be pulled automatically and used to provide information to the farmer,” Hobbs said. “These models are integrated into our learning engine, which can then be used through our digital platform. In 2021 alone, Intelinair collected more than 500 terabytes of images. Images on 100,000 fields. Over 5 million acres traveled 13 times during the season. From this, we were able to generate over 900,000 alerts that were sent to users. “

Why is this important? More data increases learning. Learning improves algorithms, and algorithms help farmers.

Data-driven solutions

For example, during the growing season, areas of the field can be identified for incomplete emergence, and these areas are used to generate a prescription map for targeted replantings.

“We can detect different weed densities and feed that information back to your equipment for pesticides for the herbicide treatment,” Hobbs added. “And at the end of the season, we identify the variable drying zones so that you can perfectly time your harvest. “

Back to the farmer who used to spot his field from the top of a silo. From the ground up, he knows his field incredibly well. He has decades, if not generations, of knowledge on this farm, Hobbs pointed out.

“He affectionately named it the moonfield, because of this silly appearance he takes on is the result of permanent water problems,” she said. “With machine learning, we are able to detect and quantify problematic wetlands in the field and send those alerts directly to a smartphone. “

In 2020, AgMRI detected areas of low emergence that could be targeted for replanting. Just half an inch of rain led to the replanting of nearly 83 acres of his 149-acre field. So, during the off-season, the farmer decided to make a major investment decision and install ditches on his field.

“He used information from our imagery, typography, and other layers from our digital twin to identify exactly what needed to be done. This same field in 2021 had zero acres of replanting and yield estimates 20-30% higher than before, ”Hobbs added. “Now with AgMRI he is able to justify that initial investment he made and quantify his return on investment. “

Big data, machine learning, artificial intelligence, these aren’t just buzzwords for Intelinair, Hobbs said. “We use these technologies to provide information and intelligence to the farming community to improve efficiency and maximize your management decisions. “


Previous With E-office, ERP files go electronic | Chandigarh News
Next AMD Data Center Sales Cross $ 1 Billion in Q3

No Comment

Leave a reply

Your email address will not be published.