By Malika Nisal Ratnayake and Alan Dorin et.al
Artificial intelligence (AI) offers a new way to track the insect pollinators essential to farming.
In a new study, we installed miniature digital cameras and computers inside a greenhouse at a strawberry farm in Victoria, Australia, to track bees and other insects as they flew from plant to plant pollinating flowers.
Using custom AI software, we analyzed several days' video footage from our system to build a picture of pollination behavior over a wide area.
In the same way that monitoring roads can help traffic run smoothly, our system promises to make pollination more efficient. This will enable better use of resources and increased food production.
A fresh set of eyes
With a growing human population and limited natural resources, food production needs to become more efficient and sustainable. Precision agriculture powered by new technologies, like AI, can help secure future food production.
Efficient pollination is crucial to produce healthy fruits, vegetables, legumes and nuts.
Optimal pollination requires just the right number of insect pollinator visits to flowers. Too few or too many visits, or visits by ineffective insect pollinators, can diminish the quality of food a flowering plant produces.
Typical techniques for monitoring insect pollination use direct visual observation or pan trapping, which are labor-intensive and take many days.
Additionally, without a very large number of trained observers it is impossible to collect simultaneous data across large farms. Yet such data are needed to provide time-critical evidence of the extent of crop pollination, before a season's pollination window is closed.
With our digital system, however, a farm manager could obtain same-day data on crop pollination levels.
Our pollination monitoring system was set up at Sunny Ridge farm in a strawberry greenhouse open to insects. The array of cameras monitored insect activity among the strawberries, recording honeybees, hover flies, moths, butterflies and some wasps.
Managing big (insect) data with advanced software
The volume of data our system collects requires custom software to reliably track individual insects flying among complex foliage.
A key issue our software overcomes is identifying insect movements within a video sequence, so an individual insect on a single path isn't accidentally counted multiple times. This enables accurate assessment of the number of insects in a region during a day, an analysis of their type (e.g. species), and monitoring of their flower visits.
Click here to see more...