AI Pesticide Research Part 1


AI Pesticide Research Part 1

From the Ag Information Network, I’m Bob Larson with today’s Fruit Grower report. Researchers at Oregon State University’s College of Engineering are putting the power of artificial intelligence to good use to help protect bees from pesticides.

Assistant Professor Cory Simon admits that pesticides are really beneficial for increasing crop yield and quality and ensuring food safety…

SIMON… “But they can also inadvertently harm non-target species like bees, wild bees and honey bees. These are really important for pollination as we know. And the other factor is that pests eventually develop resistance to pesticides, so new pesticides will continually be developed. And we need to predict whether newly proposed pesticides will be toxic to bees.

So, Simon says that made them think…

SIMON … “And so we’ve built a computer model that basically looks at a pesticide molecule, a new pesticide, and it predicts whether or not it’s going to be toxic to bees.”

Which, according to Simon, begs the question…

SIMON… “So how do we get there? We use machine learning, also known as artificial intelligence. And we relied on a dataset of over 350 examples of pesticide molecules. They were actually exposed to honey bees in honey bee toxicity experiments.

Which gives the machine learning enough information to associate patterns with toxicity.

Tune in tomorrow to learn more about this OSU study on bee protection.


Comments are closed.