Ai facial recognition technology is being used to save multibillion-dollar grape crops. It is a combined effort between a biologist and an engineer, the technology uses robotics and AI to identify grape plants infected by fungus. Researchers across the nation will be able to work on a wide array of plant and animal research.
Lance Cadle-Davidson , a biologist, an adjunct professor in the School of Integrative Plant Science (SIPS) is developing grape varieties that are more resistant to powdery mildew. One of the major hurdles in this process was to collect manual samples from thousands of grape leaves for evidence of infection.
Annually millions of dollars are lost by grape growers on lost fruit and fungicide costs in order to tackle the fungus that attacks the wine and table grapes leaving sick white spores across leaves and fruits.
Earlier Cadle-Davidson and his team developed prototypes of imaging robots while working at the Grape Genetics Research Unit in Geneva, New York. This was achieved through a process called high-throughput phenotyping – through the USDA-ARS funded VitisGen2 grape breeding project and in partnership with the Light and Health Research Center. The collaboration managed to develop a robotic camera dubbed “BlackBird.”
This was not enough as it was crucial to extract relevant biological information from these images. This is where Yu Jiang, an assistant research professor in SIPS Horticulture Section at Cornell AgriTech comes in. With his expertise in systems engineering, data analytics, and artificial intelligence, he and his team use AI to solve the challenges.
The Black Bird was able to gather information at a scale of 1.2 micrometers per pixel – equivalent to a regular optical microscope. The robot was able to provide 8000 by 5000 pixels of information for each 1-centimeter leaf sample examined.
Yu Jian and his team used deep neural networks developed for computer vision tasks like face recognition and applied them to analyze the microscopic images of grape leaves.
He and his team also implemented the visualization of the network inferential processes. Ai facial recognition technology will help biologists better understand the analysis process and build confidence with AI models.
Cadle-Davidson said, “It has revolutionized 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.”
Jiang said, “We hope to find collaborative labs who can join us in taking advantage of this tool. We see potential applications for this research in plant studies, animal fields, or medical purposes.”
Their collaboration has already won an award and two new grants in the month of July. This includes the $100,000 grant from the USDA-ARS to disseminate BlackBird to ARS field offices working on other crops that do the same kind of high-throughput phenotyping work.
Donnell Brown, president of National Grape Research Alliance said, “This work is greatly accelerating the pace of breeding and genetics work in grapes. Normally, when we in the industry invest in research, we do it knowing that we may never see the outcome of our investments in our lifetimes – it’s really a faith-based investment in future generations of growers. But now, this technology is really shortening that timeline, for the benefit of growers and consumers.”