SAS Boosts Healthy Bee Populations Through Advanced Analytics and Machine Learning


In honor of World Bee Day, SAS highlights three separate projects where technology monitors, tracks and improves pollinator populations around the world. First, SAS researchers developed a non-invasive way to monitor real-time conditions in hives using auditory data and machine learning algorithms. SAS also works with Appalachian State University on the World Bee Count to visualize data on the world’s bee population and understand the best ways to save it. Finally, the recent SAS® Viya® The hackathon winners decoded bees’ communication through machine learning to maximize their access to food and increase the human food supply.

“SAS has always looked for ways to use technology for a better world,” said Oliver Schabenberger, COO and CTO of SAS. “By applying advanced analytics and artificial intelligence to beehive health, we have a better chance as a society of securing this extremely important part of our ecosystem and, ultimately, our food supply.”

Non-invasive hive health monitoring
Researchers from the SAS IoT division are developing a bioacoustic monitoring system to non-invasively monitor real-time hive conditions using digital signal processing tools and machine learning algorithms available in SAS Processing event streams and SAS Viya software. This system helps beekeepers better understand and predict hive problems that could lead to colony failure, including the emergence of new queens – something they wouldn’t normally be able to detect.

The annual loss rates of American hives exceed 40%, and between 25% and 40% of these losses are due to queen failure. Acoustic analysis can immediately alert beekeepers to missing queens, which is vitally important to dramatically reduce colony loss rates. With this system, beekeepers will have a better understanding of their hives without having to perform tedious and disruptive manual inspections.

“As a beekeeper myself, I know the magnitude of the impact bees have on our ecosystem, and I am inspired to find innovative ways to raise healthier bees for the benefit of all,” said Anya McGuirk, Distinguished Research Statistician Developer in the IoT division of SAS. “And as a SAS employee, I am proud to have conducted this experiment with SAS software in our own campus hives, demonstrating both the power of our analytical capabilities and our commitment to innovation and sustainability. “

By connecting sensors to SAS’s four Bee Downtown hives at its headquarters in Cary, North Carolina, the team started beehive data dissemination directly to the cloud to continuously measure data points in and around the hive, including weight, temperature, humidity, flight activity and acoustics. Flow machine learning models have been used to ‘listen’ to the sounds of the beehive, which can indicate the health, stress levels, swarming activities and condition of the queen bee. To ensure that only the hum of the hive was used to determine the health and happiness of the bees, the researchers used robust principal component analysis (RPCA), a machine learning technique, to separate out extraneous noises or irrelevant to the inventory of sounds collected by the beehive microphones.

The researchers found that with the capabilities of RPCA, they could detect worker bees “stinging” at the same frequency range at which a virgin queen stings after a swarm, likely to assess whether a queen was present. The researchers then designed an automated pipeline to detect either the queen piping following a swarm or the worker piping that occurs when the colony is queenless. This is of great benefit to beekeepers, warning them that a new queen might emerge and giving them the opportunity to intervene before a significant loss occurs.

Researchers plan to implement the acoustic diffusion system very soon and continue to look for ways to expand the use of the technology to help honey bees – and, ultimately, humanity.

Visualize global pollinator populations
Today, on World Bee Day, SAS is launching a data visualization that maps “counted” bees around the world for the World Bee Count, an initiative co-founded by the Analytical Research and Education Center (CARE) at Appalachian State University. The goal of a global bee count is to inspire citizens around the world to take pictures of bees as a first step in understanding the reasons for their alarming decline.

“The Global Bee Count allows us to collect bee data both to visualize our planet’s bee population and to create one of the largest and most informative bee data sets at this time. day ”, said Joseph Cazier, professor and executive director at Appalachian State University CARE. “The visualization of SAS data will show the location of bees and other pollinators in common. In a later phase of the project, researchers can overlay key data points such as crop yield, rainfall and other factors contributing to bee health, garnering a more complete understanding of our world pollinators. ”Bayer has agreed to help sponsor CARE to enable its students and faculty to research data from the Global Bee Count and other digital pollinator data sources.

In early May, the World Bee Count app was launched for users – both beekeepers and the general public, aka “citizen data scientists” – to add data points to the global pollinator map. In the app, beekeepers can enter the number of beehives they have available and any user can submit pollinator photos from their camera roll or through the in-app camera. Thanks to SAS Visual Analytics, SAS has created a visualization card to view images that users submit through the app. In addition to showing project results, the visualizations can potentially provide insight into the conditions that lead to the healthiest bee populations.

In future stages of this project, the robust dataset created from the app could help groups like universities and research institutes better strategize to save these vital creatures.

Using machine learning to maximize bees’ access to food
Representing the Nordic region, a team from Amesto NextBridge won the SAS EMEA Hackathon 2020, which challenged participants to improve sustainability using SAS Viya. Their winning project used machine learning to maximize bees’ access to food, which in turn would benefit humanity’s food supply. In partnership with To come up, the team successfully achieved this by developing a system capable of automatically detecting, decoding and mapping the “stirred” dances of bees using the observation hives of Beefutures and SAS Viya.

Bees are responsible for the pollination of nearly 75% of all plant species directly used for human food, but the number of bee colonies is declining, resulting in devastating loss to the human food supply. One of the main reasons for the decline of bee populations is the lack of access to food due to the increase in monoculture. When the bees find a good source of food, they return to the hive to communicate its exact location through a “waggle dance”. By observing these dances, beekeepers can better understand where their bees feed, and then consider establishing new hives in those locations to help maintain strong colonies.

“Watching all of these dances manually is next to impossible, but by using video footage from inside beehives and training machine learning algorithms to decode the dance, we will be able to better understand where bees find food,” he said. said Kjetil Kalager, Amesto NextBridge and Beefutures Team Leader. “We implemented this information, along with the coordinates of the hives, the angle of the sun, the time of day, and the farming around the hives into an interactive map in SAS Viya, then beekeepers can easily decode these. information about beehives and move to better-suited environments if necessary. “

This systematic real-time monitoring of wriggling dances allows bees to act as sensors for their ecosystems. Further research using this technology could uncover other information that bees communicate through dance that could help us save and protect their people, which ultimately benefits us all.

Check it out waggle dance project in action and find out how SAS is committed to corporate social responsibility.

About SAS
SAS is the leader in analytics. Through innovative software and services, SAS empowers and inspires customers around the world to turn data into intelligence. SAS gives you THE POWER TO KNOW®.

SAS and all other SAS Institute Inc. product or service names are registered trademarks or trademarks of SAS Institute Inc. in the United States and other countries. ® indicates United States registration. Other brand and product names are trademarks of their respective companies. Copyright © 2020 SAS Institute Inc. All rights reserved.

Editorial contact:
Kara roberts
[email protected]


Related links


Comments are closed.