Next spring, a small army of PhytoPatholoBots (PPB) developed by Cornell will be deployed to four grape-breeding programs across the United States on a mission to guide the global grape and wine industry into the 21st century.
These autonomous robots will roll through the vineyards, using computer vision to collect data on the physiological condition of each vine. By combining this data with a decade of breakthroughs in grape breeding, Cornell researchers are improving PPB to allow breeders and growers to evaluate their vineyards—leaf by leaf, in real time, down to the chemical level.
PPB is launching in the first year of a new four-year project at Cornell funded by a $10 million nationwide grant from the National Institute of Food and Agriculture, Specialized Crops Research Initiative (NIFA-SCRI), led by the University of Minnesota. The scholarship extends to NIFA-SCRI’s She previously funded the VitisGen1 and 2 projects, a decade-long collaboration whose national team of scientists led by Cornell discovered several genes that control important traits in grapevines, such as disease resistance, insect resistance, and fruit and wine quality. Armed with these valuable new genetic resources, grape breeders across the country have been able to stock their pipelines in record time with new varieties that combine superior quality with higher disease resistance.
Cornell’s new project focuses on bringing VitisGen’s genetic and technological innovations into vineyards by combining plant pathology, computer vision, artificial intelligence, and robotics. This work is necessary to encourage growers to embark on large-scale cultivation of the new disease-resistant grape varieties made available by VitisGen. Nearly all grape varieties grown today are highly susceptible to powdery mildew and downy mildew—which growers around the world have, over the past 140 years, managed with multiple applications of chemical fungicides.
“Adoption of these new varieties alone has the potential to reduce pesticide use by 90%,” said Lance Cadel-Davidson, associate director and plant pathologist in the USDA-ARS Grape Genetics Research Unit at Cornell AgriTech. “Now that breeders have introduced natural disease resistance in soon-to-be-commercialized varieties, growers need updated guidance.”
To comprehensively develop this guidance, Cadle-Davidson enlisted Katie Gold, co-principal investigator and assistant professor of grape pathology at Cornell AgriTech, and applied roboticist Yu Jiang, assistant professor, Department of Horticulture in the College of Integrative Plant Sciences. The team also includes longtime VitisGen leader Bruce Reich, Professor of Plant Breeding and Genetics in the College of Integrative Plant Sciences, Department of Horticulture, and collaborator Kee Sun, co-director of the Cornell Bioinformatics Facility in Ithaca.
Gold, who specializes in the use of imaging spectroscopy for disease detection, will conduct field trials to design low-input disease management programs for new cultivars in the VitisGen pipeline. Spectroscopy measures how matter interacts with light and other electromagnetic radiation, with different types of matter producing different spectral signatures. Conventional cameras measure spectral signatures within the visible light (RGB) spectrum. But imaging spectroscopy — originally devised by NASA to study the solar system — produces data covering a range of electromagnetic radiation seven times greater than what the human eye can see.
PPB was formed during VitisGen2, after Jiang Cadle-Davidson helped speed up the process of evaluating thousands of seedlings in the lab by developing AI-based models to detect and quantify powdery and downy mildew on grapes using digital imaging. Jiang used those models to drive a microscopic RGB Cadell-Davidson robot, called BlackBird. With BlackBird, the Cadle-Davidson lab saw a 60-fold increase in the number of seedlings they could rate, and they found that the AI also identified disease more accurately than humans.
For this project, Jiang is working on expanding PPB imaging spectrometers (also known as hyperspectral sensors) to extend laboratory VitisGen probes to vineyards and enable breeders to phenotype grapevines in their natural environment. Gold will also use its newly equipped hyperspectral PPB, or HyperPPB, to “see” plants on a chemical level. It will apply this data in the field to detect disease before visible symptoms appear, and in the laboratory to begin to characterize the mechanisms underlying disease resistance—which is ultimately determined by the complex interaction between a plant’s genetic makeup and its environment.
“A lot of the real variability in foliage is captured at wavelengths that we can’t see and that basically corresponds to chemistry and physiology,” Gould said. “Hyperspectral has really demonstrated its ability in detecting and characterizing the multifaceted and less draining aspects of disease resistance and infection dynamics.”
Jiang hopes to commercialize the PPB robot family so farmers can monitor diseases as well as many other aspects of vine development in their vineyards on an ever larger scale. He said the collaboration is a prime example of how interdisciplinary research can accelerate the design process for the next generation of agri-food systems.
“We help educators target essential improvements while enabling them to respond more quickly to changes, whether they are anticipated or not,” Jiang said.
Many of these unexpected changes will be attributed to climate change, which Gould said will only increase disease and pest pressure in New York State, where it is already higher than in other major grape-growing regions in the United States. For the state’s $15 billion industry to continue to thrive, farmers will have to adopt new disease-resistant varieties and careful management methods.
“Over the course of VitisGen, more than 65 co-researchers have worked together with the latest technology,” Cadle-Davidson said. “But what I once thought was cutting edge can’t be compared to what Katie and Yu are bringing to the table. What we can achieve now is going to be very exciting, powerful and potentially revolutionary.”
Sarah Thompson is a writer at Cornell AgriTech.
#Autonomous #robots #modernize #grape #wine #industry #Cornell #Chronicle