YOU might expect to hear an angry buzzing when honeybees have been disturbed. But some apiarists reckon they can also deduce the condition of their bees from the sounds they make. A steady hum could be the sign of a contented hive; a change in tone might indicate that the bees are about to swarm. That intuition is about to be put to the test. Soon, beekeepers will be able to try to find out what is troubling a colony by listening to the buzz using a smartphone app.

The app, which is in the final stages of testing, has been developed by Jerry Bromenshenk and a group of fellow bee experts at the University of Montana. It uses a form of artificial intelligence to analyse the sound that bees are making in order to deduce whether they are suffering from a number of maladies.

Those afflictions might provide an indication of an impending Colony Collapse Disorder (CCD), a mysterious syndrome that has plagued beekeepers in North America and Europe. Unlike a natural swarm, in which a large group of worker bees leave with their queen to form a new colony, CCD involves bees suddenly disappearing for no obvious reason, leaving their queen behind. Although recent reports suggest there has been a reduction in bee die-offs, according to some estimates 10m hives in America alone were wiped out by CCD from 2006 to 2013. Besides hitting honey production, this can also hinder the pollination of certain crops.

The development of the app has an unusual back story. The idea came from one of the many bee projects which Dr Bromenshenk and his colleagues are involved in. This work involves training bees to hunt for landmines. Landmines leak traces of explosive chemicals into the ground and the air. These tiny emissions can be detected by well-trained sniffer dogs. Since dogs can be heavy enough to detonate mines, some instead use rats that have been trained to do the same thing.

Explosive reaction

Training dogs and rats to find mines is slow and expensive. However, the Montana researchers reckon they can train bees to find mines in only a few hours. They do this by spiking a syrup feed with a small sample of explosive chemicals. The bees then associate the scent of the chemicals with food. This influences them to fly towards and around any source of the chemicals when foraging for nectar. As there could be some 20,000 bees flying, some means of tracking them is required. To do that, the researchers use lidar, a form of radar, which they tune to the frequency of the bees’ wing beats. This way an electronic map can be built up showing where the bees fly to, and thus where any landmines might be. In tests with the American army, the researchers found bees were more than 97% accurate in locating landmines.

This work is ongoing, but it has also led to other research. The academics came to realise that if minehunting bees are to be deployed successfully by soldiers or civilian contractors, then the operators would need to have good beekeeping skills. Such skills, of course, can be taught but it would take a long time for novices to acquire the knowledge of an experienced beekeeper, let alone be in tune with the many ailments that bees are susceptible to. This led in turn to the idea of developing a machine that could, like a seasoned beekeeper, listen to the buzz of bees to help determine their health.

For such an idea to work, it is necessary to attribute specific bee ailments to particular sounds. To do that, the university tapped into its worldwide network of beekeepers to find colonies that were known to suffer from only one problem, and to obtain sound recordings of bees in those colonies. The sounds that bees make come from their beating wings (although movements by other parts of their bodies may also be involved). Having built up a database of sounds, an artificial neural network, a form of machine learning used for pattern recognition, was employed to help build algorithms that can match bee sounds to those associated with certain hive problems.

Rather than produce a stand-alone device, the group developed a system which could be used on a smartphone. The resulting app, which is called Bee Health Guru, is being produced by Bee Alert Technology, a company spun out from the university.

To check on the health of a colony of bees it is usually necessary to open the hive, a procedure which involves using smoke to pacify the bees. That is a time-consuming process for commercial beekeeping operations, some of which may have several thousand colonies to take care of. With the app, all a beekeeper need do is to hold their smartphone near to the hive’s entrance for 30 seconds while it analyses the sound of the bees. The app then lists any health problems which it detects.

Seven different disorders will at first be checked, says David Firth, a team member who is helping to bring the app to market. These include the presence of hive beetle, a serious honeybee pest, parasitic mites and “foulbrood”, a bacterial infection which can destroy bee colonies.

The results might also point to early signs of CCD, which is now regarded as being caused by a combination of problems rather than one particular disease. In a 2010 paper in PLoS One, Dr Bromenshenk and his colleagues found that a bee virus and a fungus from a species known as Nosema were often prevalent in collapsed honeybee colonies, and that it was likely the two working together were more lethal to bees than either pathogen alone.

With the permission of users, data from the app can be shared with the researchers, who plan thereby to update the software to detect other diseases and problems, says Dr Firth. This could include exposure to pesticides, in particular a group called neonicotinoids which are suspected of harming honeybees (pesticide producers reject such claims). Finally, if all works to plan, bees will get to have their say about the things that cause them harm.