On the farm, FHB severity readings from various fields could be used by grain farmers to do things like differential harvesting, where they keep more-diseased grain separate from cleaner grain. “You can also get a sense of the areas that are most affected over time, and apply less nitrogen to those areas to decrease in-crop humidity, or spray more in those areas,” says McConachie. “For researchers, having this in an app means that FHB estimation will be much faster and more accurate. This task has always been carried out manually by students. And for breeders, a faster and more accurate way to measure FHB severity will also be more efficient in breeding programs, as it will yield estimation in time.” ONTARIO GRAIN FARMER COVER STORY 8 continued from page 7 THE POTENTIAL OF AI McConachie sees AI as an extremely useful tool, but also notes its limitations. That is, the YOLO AI serves as the basis for the app, but McConachie is also using other AI platforms to perform related tasks in his research workflow—albeit only for certain tasks. “There’s part of my thesis, for example, where AI could be used, but it would take a long time to do things that way,” he notes. “You’d have to do a lot of work to ensure the result would be reliable. So it’s not always the best approach, and with that part of my research, I’m doing something simpler that I’m pretty sure will work well.” When asked about AI in farming, McConachie believes it will be increasingly useful. For example, the existing platforms for variable automated spraying of crop protection products (based on sensors that detect weed concentrations or disease severity) will get much better. At the same time, McConachie observes that these systems need to be more rugged and that they are currently very expensive and can be quite slow to fix sensors that have stopped working. Regarding his own AI work, he’s very excited that it’s transferable to other crops and diseases, but this won’t come quickly. “It will take a number of years before we have systems to detect all diseases in all crops,” McConachie says. “It’s very difficult to detect and distinguish leaf diseases, and root diseases are a whole other area. And with estimating the yield impact of disease, the severity and incidence for some pathogens correlates well but others don’t. There are other factors in play, such as when the disease took hold, upcoming weather and so on.” But for now, McConachie is very excited that WheatScanR will help a lot of growers in 2026 and beyond. “I really hope a lot of people use it next year,” he says. “Word is spreading. I can’t wait to update it, but it’s pretty good as is.” Riley McConachie was a 2024 recipient of the Grain Farmers of Ontario Legacy Scholarship.•
RkJQdWJsaXNoZXIy MTQzODE4