A high-performance computing project at Mississippi State University aims to improve proper agriculture and benefit farmers. The researchers hope to use the data obtained by the drones to help farmers improve production by helping them quickly solve problems such as plant diseases, pests and water stress.
Advancing Agricultural Research through the High-Performance Computing project is a collaborative agreement between Mississippi State University and the USDA-Agriculture Research Service. Robert Moorhead, MSU professor and director of its Geosystems Research Institute was the lead investigator on the three -year project. The partnership is powered by “Atlas,” a high-powered system installed by MSU’s High Performance Computing Collaboratory in 2020.
Robert Moorhead, MSU professor and director of its Geosystems Research Institute at Mississippi State Universty (left) and Alessandro Matese, a visiting scholar from Italy conduct research on how farmers use data collected by drones to improve crops. (Sean Meachum, MSU)
The data collected by the drones has already helped farmers. Drones may offer a vision that has never been used and the MSU project seeks to rapidly analyze the data.
“A lot of producers use drones to go out and look at their plants,” Moorhead explains. “Now, researchers are starting to use it and trying to understand how a plant thrives, such as if more fertilizer helps and if it produces more fruit.”
Drones provide images that can be processed into a large image that offers something similar to satellite imagery, according to Moorhead. Comparisons can be made weekly. GRI’s work includes training on how to use images, and removing images that are skewed or have a cloud cover.
Moorhead said researchers are trying to determine the ultimate benefits for farmers. Computers have evolved to the point that soon farmers, or consultants, will be able to take images, send them to the cloud, and receive answers to issues including pest outbreaks, problems. in water or chemical problems.
“In that area, hopefully, we’ll develop some algorithms and methods that now take up a little bit of computer power,” Moorhead said. “If you consider the fact that the technology that sent the first space shuttle was in handheld computers about 10 years ago, you can see the potential power. It will eventually be local. It won’t require a large computer center. a place to get this information. It can be used anywhere. ”
Moorhead said farmers find that just by getting a cheap drone flying over their fields, they can see pigs in the middle that they don’t know are there, they can see deer browsing and grazing without them knowing they were there. Especially with corn, which grows over your head, they can see things they didn’t know before. ”
The partnership is powered by “Atlas,” a high-powered system installed by MSU’s High Performance Computing Collaboratory in 2020. (Mississippi State University)
If pests are the main concern, drones can fly low to get enough resolution to see them up close. They will be found immediately, Moorhead said, allowing farmers to deploy a timely application of the pesticide. “You don’t wait for the satellite image. You don’t wait for someone to walk into the field. You get an overall look at the field. ”
Another potential benefit, Moorhead said, is to study different winter ground cover to determine whether to use radishes, clover, peas or not. Farm trials by farmers are ongoing. Researchers are also looking at how to improve conservation practices, such as reducing runoff.
Farmers are increasingly adopting drone technology, but Moorhead said an issue now is who owns the data.
“Farmers want to collect data and develop data products, but often they are not confident that their data is protected. They want to know more about working with big vendors. to get data, but they doubt their data is being used by someone else.If I think I got a good deal of land I was renting, I don’t want others to know that.
Time is a big part of research. Moorhead said they determined that in Mississippi, only 10% of the growing season are cloudless days. That changes things in terms of predicting how much the plants change each week. Also, drones cannot fly in bad weather. All drones have a problem when there is more than a quarter of an inch of rain in an hour.
Assisting with the research this year was Alessandro Matese, a visiting scholar from Italy. Matese, a renowned researcher at the Institute of BioEconomy of the National Research Council of Italy, participated in a one-year partnership through MSU’s partnership with USDA. Matese is a promoter of the application of computer science aspects to agriculture.
“I see a great opportunity for collaboration here, and the opportunity to improve my knowledge of computer science in relation to agricultural purposes,” he said.
Matese hopes to meet with farmers in the area in the coming months. Such experience would expand his overall knowledge base, he said. Matese is based in the wine region of Tuscany and much of his experience is related to grape cultivation.
“Here, there are different types of plants that I am very interested in,” he said. “For example, cotton is a crop we have never seen in Italy. I would like to meet some farmers to increase my knowledge of the crops.”
“At this point, the farmer has to come out with a drone, or a consultant will come out, and they have to send the data somewhere to be processed,” Moorhead said. “It takes time. I see the process in the future becoming more real-time. You can get rid of pests more easily before they can destroy a plant. You can react immediately. ”
Moorhead envisions a future where farmers will eventually be able to program drones from their home, guiding them where they are going. The drones automatically return to a recharging station. The data will be downloaded automatically to let the farmer know if there is an issue.
“You can save money by knowing exactly what your fertilizer needs are,” Moorhead says. “It will be able to predict yields earlier, which will affect the price of commodities more reliably.”
One of Matese’s observations to date is that the Mississippi State program offers a method of processing data that is different than his experience in Italy.
“There is a huge amount of knowledge available in computer science,” he said. “It opens up a new vision, shows me new tools, new ways to engage with agricultural computers. It’s a very good organization in terms of collaboration. Everyone “people have a specific task, and it’s amazing for me to see how things work together. It’s a new reality.”
Matese said he gained essential knowledge to be brought back to Italy.
“I have colleagues here who have a high level of expertise,” he said. “It’s not very common to find people with an interest in computer science and agriculture. The other thing I would bring back is the way the team is structured here in the U.S. It’s very effective. Everyone knows that well at their tasks, and if there is a problem, everyone can ask others for help and support.