An AI tool that is able to provide valuable data on grape crops has been designed.

This is a development conjured from a partnership between Lance Cadle-Davidson and Yu Jiang, a biologist and an assistant research professor at Cornell University respectively. To prevent his team from manually inspecting a vast number of grape leaves for infection, Cadle-Davidson and his collegues designed imaging robots, before Jiang introduced AI to obtain information from the images that were taken. Eventually, the BlackBird robotic camera was born.

The BlackBird robotic camera is a device that can identify biological traits of infection in grape leaves as a result of powdery mildew being present. According to an article on The Engineer, it can obtain data at a resolution of 1.2 micrometers per pixel, whilst also being able to provide 8,000 by 5,000 pixels of information for every 1cm sample of leaf.

In a job that would usually take around six months in a lab, the BlackBird robots can perform this analysis in just 24 hours.

“It has revolutionised our science, and we’re finding that Yu’s AI tools actually do a better job of explaining the genetics of these grapes than we can do sitting at a microscope for months at a time doing backbreaking work,” said Cadle-Davidson in a statement.

The team were awarded a $150,000 grant from Cornell to initiate future upgrades for the robot.

“We hope to find collaborative labs who can join us in taking advantage of this tool,” said Yu Jiang. 

“We see potential applications for this research in plant studies, animal fields or medical purposes.”