New Low-Cost Beehive Sensors Could Help Save Honeybee Colonies

Increased pesticide use, habitat loss and climate change have been contributing to a decades-long decline in global honeybee numbers.

Now, a computer science team from University of California, Riverside (UCR), has come up with an innovative way to help. They developed a sensor-based technology with the potential to revolutionize commercial beekeeping, reduce colony losses and cut labor costs.

“Honeybees, as natural crop pollinators, play a significant role in biodiversity and food production for human civilization. Bees actively regulate hive temperature (homeostasis) to maintain a colony’s proper functionality. Deviations from usual thermoregulation behavior due to external stressors (e.g., extreme environmental temperature, parasites, pesticide exposure, etc.) indicate an impending colony collapse,” the authors of the paper wrote. “Anticipating such threats by forecasting hive temperature and finding changes in temperature patterns would allow beekeepers to take early preventive measures and avoid critical issues.”

The Electronic Bee-Veterinarian (EBV) uses forecasting models and inexpensive heat sensors to predict when temperatures in a hive could reach dangerous levels, a press release from UCR said.

The system gives beekeepers remote early warnings so that they can take preventive action before colonies collapse during extreme cold or hot weather, or when bees aren’t able to regulate the temperature of their hives due to pesticide exposure, food shortages, disease or other stressors.

“We convert the temperature to a factor that we are calling the health factor, which gives an estimate of how strong the bees are on a scale from zero to one,” said lead author of the paper Shamima Hossain, a computer science Ph.D. student at UCR, in the press release.

The technology uses a simple metric, with “one” indicating that the bees are at their strongest, allowing beekeepers to quickly assess hive health.

UCR entomology professor Boris Baer thinks EBV could revolutionize beekeeping — an essential practice to large sectors of agriculture throughout the world.

More than 80 crops are pollinated by honeybees, and the essential pollinators contribute approximately $29 billion each year to agriculture in the United States. But factors like pesticide exposure, parasites, habitat loss and climate change have contributed to the decline of bee populations.

“Over the last year, the U.S. lost over 55% of its honeybee colonies,” said Baer, citing data collected by Project Apis m., which monitors U.S. beehive losses. “We are experiencing a major collapse of bee populations, and that is extremely worrying because about one-third of what we eat depends on bees.”

Right now beekeepers use manual inspections and their own judgment to detect issues, which often leads to delayed interventions. Baer said EBV could predict conditions days ahead of time, providing them with real-time insights and significantly reducing labor costs.

“People have dreamed of these sensors for a very long time,” Baer emphasized. “What I like here is that this system is fully integrated into the hive setup that beekeepers already use.”

Baer explained that honeybees maintain an internal hive temperature of between 91.4 and 96.8 degrees Fahrenheit to assure colony survival and proper brood development. Among the first indicators of a threat to hive health are fluctuations in temperature.

The EBV model feeds temperature data collected from sensors inside the hive into an algorithm that can then predict hive conditions several days ahead of time.

EBV was used to analyze data from up to 25 hives at the UCR apiary. It proved its effectiveness by detecting conditions requiring beekeeper intervention.

“When I looked at the dashboard and saw the health factor dropped below an empirical threshold, I contacted our apiary manager,” Hossain said. “When we went to check the hive, we found that there was actually something wrong, and they were able to take action to manage the situation.”

UCR electrical and computer engineering associate professor Hyoseung Kim explained that keeping costs at less than $50 per hive was a big priority.

“There are commercial sensors available, but they are too expensive,” Kim explained. “We decided to create a very cheap device using off-the-shelf components so that beekeepers can afford it.”

The researchers have begun the next phase of developing automated climate controls that beekeepers can install in hives to respond to EBV’s predictions by automatically adjusting hive temperature.

“Right now, we can only issue warnings,” Hossain said. “But in the next phase, we are working on designing a system that can automatically heat or cool the hive when needed.”

The paper, “Principled Mining, Forecasting and Monitoring of Honeybee Time Series with EBV+,” was published in the journal ACM Transactions on Knowledge Discovery from Data.