Let’s save the bees with machine learning

Machine learning and all its related forms of “AI” are being used to work on just about every problem under the sun, but even so, stemming the alarming decline of the bee population still seems out of left field. In fact it’s a great application for the technology and may help both bees and beekeepers keep hives healthy.

Machine learning and all its related forms of “AI” are being used to work on just about every problem under the sun, but even so, stemming the alarming decline of the bee population still seems out of left field. In fact it’s a great application for the technology and may help both bees and beekeepers keep hives healthy.

The latest threat to our precious honeybees is the varroa mite, a parasite that infests hives and sucks the blood from both bees and their young. While it rarely kills a bee outright, it can weaken it and cause young to be born similarly weak or deformed. Over time this can lead to colony collapse.

The worst part is that unless you’re looking closely, you might not even see the mites — being mites, they’re tiny: a millimeter or so across. So infestations often go on for some time without being discovered.

Beekeepers, caring folk at heart obviously, want to avoid this. But the solution has been to put a flat surface beneath a hive and pull it out every few days, inspecting all the waste, dirt, and other hive junk for the tiny bodies of the mites. It’s painstaking and time-consuming work, and of course if you miss a few, you might think the infestation is getting better instead of worse.

Machine learning to the rescue!

As I’ve had occasion to mention about a billion times before this, one of the things machine learning models are really good at is sorting through noisy data, like a surface covered in random tiny shapes, and finding targets, like the shape of a dead varroa mite.

Students at the École Polytechnique Fédérale de Lausanne in Switzerland created an image recognition agent called ApiZoom trained on images of mites that can sort through a photo and identify any visible mite bodies in seconds. All the beekeeper needs to do is take a regular smartphone photo and upload it to the EPFL system.

The project started back in 2017, and since then the model has been trained with tens of thousands of images and achieved a success rate of detection of about 90 percent, which the project’s Alain Bugnon told me is about at parity with humans. The plan now is to distribute the app as widely as possible.

“We envisage two phases: a web solution, then a smartphone solution. These two solutions allow to estimate the rate of infestation of a hive, but if the application is used on a large scale, of a region,” Bugnon said. “By collecting automatic and comprehensive data, it is not impossible to make new findings about a region or atypical practices of a beekeeper, and also possible mutations of the Varroa mites.”

That kind of systematic data collection would be a major help for coordinating infestation response at a national level. ApiZoom is being spun out as a separate company by Bugnon; hopefully this will help get the software to beekeepers as soon as possible. The bees will thank them later.

Let’s save the bees with machine learning

Machine learning and all its related forms of “AI” are being used to work on just about every problem under the sun, but even so, stemming the alarming decline of the bee population still seems out of left field. In fact it’s a great application for the technology and may help both bees and beekeepers keep hives healthy.

Machine learning and all its related forms of “AI” are being used to work on just about every problem under the sun, but even so, stemming the alarming decline of the bee population still seems out of left field. In fact it’s a great application for the technology and may help both bees and beekeepers keep hives healthy.

The latest threat to our precious honeybees is the varroa mite, a parasite that infests hives and sucks the blood from both bees and their young. While it rarely kills a bee outright, it can weaken it and cause young to be born similarly weak or deformed. Over time this can lead to colony collapse.

The worst part is that unless you’re looking closely, you might not even see the mites — being mites, they’re tiny: a millimeter or so across. So infestations often go on for some time without being discovered.

Beekeepers, caring folk at heart obviously, want to avoid this. But the solution has been to put a flat surface beneath a hive and pull it out every few days, inspecting all the waste, dirt, and other hive junk for the tiny bodies of the mites. It’s painstaking and time-consuming work, and of course if you miss a few, you might think the infestation is getting better instead of worse.

Machine learning to the rescue!

As I’ve had occasion to mention about a billion times before this, one of the things machine learning models are really good at is sorting through noisy data, like a surface covered in random tiny shapes, and finding targets, like the shape of a dead varroa mite.

Students at the École Polytechnique Fédérale de Lausanne in Switzerland created an image recognition agent called ApiZoom trained on images of mites that can sort through a photo and identify any visible mite bodies in seconds. All the beekeeper needs to do is take a regular smartphone photo and upload it to the EPFL system.

The project started back in 2017, and since then the model has been trained with tens of thousands of images and achieved a success rate of detection of about 90 percent, which the project’s Alain Bugnon told me is about at parity with humans. The plan now is to distribute the app as widely as possible.

“We envisage two phases: a web solution, then a smartphone solution. These two solutions allow to estimate the rate of infestation of a hive, but if the application is used on a large scale, of a region,” Bugnon said. “By collecting automatic and comprehensive data, it is not impossible to make new findings about a region or atypical practices of a beekeeper, and also possible mutations of the Varroa mites.”

That kind of systematic data collection would be a major help for coordinating infestation response at a national level. ApiZoom is being spun out as a separate company by Bugnon; hopefully this will help get the software to beekeepers as soon as possible. The bees will thank them later.

Bumble bees bearing high-tech backpacks act as a living data collection platform

There’s lots of research going into tiny drones, but one of the many hard parts is keeping them in the air for any real amount of time. Why not hitch a ride on something that already flies all day? That’s the idea behind this project that equips bumble bees with sensor-filled backpacks that charge wirelessly and collect data on the fields they visit.

There’s lots of research going into tiny drones, but one of the many hard parts is keeping them in the air for any real amount of time. Why not hitch a ride on something that already flies all day? That’s the idea behind this project that equips bumble bees with sensor-filled backpacks that charge wirelessly and collect data on the fields they visit.

A hive full of these cyber-bees could help monitor the health of a field by checking temperature and humidity, as well as watching for signs of rot or distress in the crops. A lot of this is done manually now, and of course drones are being set to work doing it, but if the bees are already there, why not get them to help out?

The “Living IoT” backpack, a tiny wafer loaded with electronics and a small battery, was designed by University of Washington engineers led by Shyam Gollakotta. He’s quick to note that although the research does to a certain extent take advantage of these clumsy, fuzzy creatures, they were careful to “follow best methods for care and handling.”

Part of that is minimizing the mass of the pack; other experiments have put RFID antennas and such on the backs of bees and other insects, but this is much more sophisticated.

[gallery ids="1757459,1757477,1757479,1757480,1757481,1757482"]

The chip has sensors and an integrated battery that lets it run for seven hours straight, yet weighs just 102 milligrams. A full-grown bumblebee, for comparison, could weigh anywhere from two to five times that.

They’re strong fliers, if not exact ones, and can carry three quarters of their body weight in pollen and nectar when returning to the hive. So the backpack, while far from unnoticeable, is still well within their capabilities.

“We showed for the first time that it’s possible to actually do all this computation and sensing using insects in lieu of drones,” explained Gollakotta in a UW news release. “We decided to use bumblebees because they’re large enough to carry a tiny battery that can power our system, and they return to a hive every night where we could wirelessly recharge the batteries.”

The backpacks can track location passively by monitoring the varying strengths of signals from nearby antennas, up to a range of about 80 meters. The data they collect is transferred while they’re in the hive via an energy-efficient backscatter method that Gollakotta has used in other projects.

The applications are many and various, though obviously limited to what can be observed while the bees go about their normal business. It could even help keep the bees themselves healthy.

“It would be interesting to see if the bees prefer one region of the farm and visit other areas less often,” said co-author Sawyer Fuller. “Alternatively, if you want to know what’s happening in a particular area, you could also program the backpack to say: ‘Hey bees, if you visit this location, take a temperature reading.’ ”

It is of course just in prototype form right now, but one can easily imagine the tech being deployed by farmers in the near future, or perhaps in a more sinister way by three-letter agencies wanting to put a bee on the wall near important conversations. The team plans to present their work (PDF) at the ACM MobiCom conference next year.