KANSAS (KSNT) – Google is sharing a K-State entomologist’s work using artificial intelligence (AI) to identify, track and help conserve the world’s bees.
K-State Entomologist Brian Spiesman has developed a bee-tracking app, BeeMachine, using Google’s TensorFlow AI models to recognize hard-to-categorize bees. The app uses photos to provide a top three predictions for the bee species. The app lets users share bee sightings through a community feature.
“I realized AI might be the answer,” Spiesman said. “I started gathering data sets and adapting pre-trained models within Google’s TensorFlow so they would start to recognize hard-to-categorize bees, and it just grew from there. That’s how the BeeMachine, an AI-powered app and website for identifying bee species, was born.”
Topeka prepares for ‘No Kings’ protest on Saturday
Since launching the app, more than 6,200 users have submitted more than 20,000 sightings, according to the Google article on Spiesman.
Spiesman said the goal is to get people excited about bees. He said there’s been a similar effort to collect data on birds that’s been invaluable to research and conservation. He hopes that his app project will do the same for bees.
“I think we’re at a spot where we’re not limited by what the AI models are able to do,” Spiesman said. “We’re more limited by the inputs we have available to train them, so that’s really what we’re working on right now.”
Topeka Stealth joining Midwest baseball league in 2026
The app was funded by the National Institute of Food and Agriculture, the National Science Foundation, and Kansas State University, according to BeeMachine’s website. You can learn more about BeeMachine by clicking here.
For more local news, click here. Keep up with the latest breaking news in northeast Kansas by downloading our mobile app and by signing up for our news email alerts. Sign up for our Storm Track Weather app by clicking here.
