Honeybees are crucial in pollinating over 80 crops and contribute about $29 billion annually to U.S. agriculture. However, bee populations are declining rapidly due to habitat loss, pesticides, parasites, and climate change. In the past year, the U.S. lost over 55% of its honeybee colonies, which is concerning as one-third of our food relies on bees.
Traditionally, beekeepers rely on manual checks and their judgment to find problems, leading to delays. A team from UC Riverside has developed a new technology that could help save bee colonies.
They created the Electronic Bee-Veterinarian (EBV), a sensor-based system that uses low-cost heat sensors and forecasting models to predict dangerous hive temperatures.
This system provides early warnings to remote beekeepers, allowing them to take action before their colonies collapse due to extreme weather, disease, pesticides, food shortages, or other stressors.
Shamima Hossain, a Ph.D. student in computer science at UCR and lead author of the study, explained that the EBV converts temperature data into a “health factor,” giving an estimate of bee strength on a scale from zero to one. This simplified metric allows beekeepers to assess hive health quickly.
Honeybees maintain a hive temperature between 33 and 36 degrees Celsius (91.4–96.8°F) for proper brood development and colony survival.
The EBV method uses thermal diffusion equations and control theory, making its predictions understandable for scientists and beekeepers.
The model collects temperature data from low-cost sensors inside the hive and uses an algorithm to predict hive conditions several days in advance.
In tests at UCR’s apiary, the EBV method initially analyzed data from 10 hives and later expanded to 25 hives. The technology has proven effective in detecting conditions that require beekeeper intervention.
Hossain recalled, “When I looked at the dashboard and saw the health factor dropped below an empirical threshold, I contacted our apiary manager. When we checked the hive, we found something wrong, and they could take action to manage the situation.”
Hyosung Kim, an associate professor of electrical and computer engineering at UCR, emphasized the importance of keeping costs under $50 per hive. “There are commercial sensors available, but they are too expensive,” Kim said. “We decided to create a very cheap device using off-the-shelf components so beekeepers can afford it.”
Bees can tell time by temperature
The research team is working on the next phase, which involves developing automated hive climate controls that can respond to EBV’s predictions by automatically adjusting hive temperatures.
“Right now, we can only issue warnings,” Hossain said. “But in the next phase, we are designing a system that can automatically heat or cool the hive when needed.”
This new technology offers hope for saving honeybee colonies and ensuring the future of pollination and agriculture.
Journal Reference
- Mst. Shamima Hossain, Christos Faloutsos, Boris Baer, Hyoseung Kim, Vassilis J. Tsotras. Principled Mining, Forecasting, and Monitoring of Honeybee Time Series with EBV+. ACM Transactions on Knowledge Discovery from Data. DOI: 10.1145/3719014
