According to Greenpeace USA, honeybees pollinate 70 out of the top 100 human food crops worldwide. To put that in perspective, those 70 crops provide 90 percent of the world’s nutrition and a minimum of one out of every three bites of food. Unfortunately, the global honeybee population is in danger. While many causes are to blame for the diminishing number of bees that pollinate the world’s plants, humans are to blame for the two largest factors: habitat loss and pesticides.
As a beekeeper and computer scientist, Professor Vladimir Kulyukin both worries about the well-being of the honeybees and aims to use his knowledge to improve their plight. In 2017, he launched stage one of his BeePi project, a multisensor electronic beehive monitor that uses data from video, audio and temperature sources to estimate the state of a bee colony.
“There is an emerging consensus that electronic beehive monitoring is the way to go, so it can help extract critical data from the hive without disturbing the hive,” he told The Seattle Times in October 2017. “If you can think about the beehive as an intelligent, immobile robot, essentially monitoring the bee colony inside and letting all interested parties know of deviations from the norm, then it’ll cut down on hive inspections and transportation costs immensely.”
After successfully funding the electronic bee colony monitor project, BeePi is back for stage two—“Honeybees meet AI.” The long-term goal of this stage is to create a series of open source software and hardware tools for researchers, practitioners, enthusiasts and citizen scientists to monitor bee hives—either their own or someone else’s.
“Our vision is that in the future significant practical and scientific benefits will come from transforming our beehives into immobile robots that use AI to monitor the health of their bee colonies with multiple sensors, analyze the data, and alert beekeepers of any deviations from the norm,” the Kickstarter page explained.
In this next stage, BeePi plans to construct five more electronic bee monitors and distribute them to local beekeepers to collect data. The second objective, called “directional bee traffic estimation,” will measure the number of bees in the colony and where they are going (i.e. to the beehive, away from the beehive or sideways). The third goal of “sensor fusion” uses AI to integrate and analyse different types of sensory data, just like a human beekeeper would (e.g. images, video, audio). The ultimate goal is to curate and share terabytes of data for the good of the beekeeping community.
“My goal is to empower citizen scientists and beekeepers to essentially assemble their own monitors and share the data to build a national and possibly international infrastructure of information,” he told The Seattle Times in October 2017. “We are all in this together.”
The Kickstarter has 28 more days to reach its “all or none” goal of €4,453.