Telescopes, radars and many other equipment installed in recent years on scientific Earth observation satellites and aircraft are helping to improve the environment in general and agricultural management in particular. In one of the most advanced practical applications in this field known, NASA experts have demonstrated the ability of aerial equipment and computer applications to detect infections in vineyards before these diseases are observable from the ground.
One of the first specific cases has been carried out in Cabernet Sauvingnon crops in California, with an initial observation campaign in 2020, and the results of which have been recently published in two simultaneous articles in the specialized journals Phytophatology (April 2023) and the Journal of Geophysical Research: Biogeosciences. (May 2023).
Experts estimate that root-rotting diseases, viruses and other plant pathogens destroy between 15% and 30% of the world's crops each year. Early detection can make the difference between a failed harvest and one that can be treated, indicate the authors of these two new studies to introduce the importance of work like theirs.
Using an airborne science instrument developed at NASA's Jet Propulsion Laboratory (JPL) in Southern California, researchers have found they can accurately detect early, low-intensity signs of disease of the grape that causes serious losses in the crops.
In the two published articles, researchers from JPL and Cornell University present technical data and practical experience from their work against a viral disease called GLRaV-3 (abbreviation for vine leaf curl-associated virus complex 3). ).
Transmitted primarily by insects, GLRaV-3 reduces yields and sours developing fruit, costing the U.S. wine and grape industry an estimated $3 billion in damages and losses annually. It is usually detected through laborious strain-by-strain screening and expensive molecular testing.
The research team wanted to see if they could help growers identify GLRaV-3 infections early and from the air by using machine learning and NASA's next-generation airborne visible/infrared imaging spectrometer (AVIRIS). -NG). The instrument's optical sensor, which records the interaction of sunlight with chemical bonds, has been used to measure and monitor hazards such as wildfires, oil spills, greenhouse gases and air pollution associated with volcanic eruptions.
It was during a 2020 campaign to map methane leaks in California that plant pathologist Dr. Katie Gold and her team took the opportunity to pose a different question: Could AVIRIS-NG uncover a covert infection of crops in one of the growing regions of the most important grapes in the state?
"Like humans, diseased plants may not show external symptoms right away, making early detection the biggest challenge growers face," said Gold, an assistant professor at Cornell University and lead author of the new studies. In the case of vine leaf curl virus, it can take up to a year before a vine shows telltale signs of infection, such as discolored foliage and stunted fruit. However, at the cellular level, stress is already underway before that, changing the way sunlight interacts with plant tissue.
Mounted in the belly of a research aircraft, AVIRIS-NG observed approximately 11,000 acres of vineyards in Lodi, California. The region, located in the heart of California's Central Valley, is a major producer of the state's premium wine grapes.
The team fed the observations into computer models they developed and trained to distinguish the infection. To help verify the results, industry collaborators scanned more than 300 acres of vineyards from the ground for visible viral symptoms while collecting vine samples for molecular testing.
Gold noted that it was a labor-intensive process that took place during a heat wave in California. "Without the hard work of producers, industry collaborators and exploration teams, none of what we accomplished would have been possible," he said. Similar efforts will continue under NASA's Acres Consortium, of which Gold is a principal scientist.
The researchers found that they could differentiate infected and uninfected vines before and after they became symptomatic, with the best-performing models achieving 87% accuracy. Successful early detection of GLRaV-3 could help provide grape growers with up to a year's notice to intervene.
In a companion paper published in the Journal of Geophysical Research: Biogeosciences, the researchers said their case study shows how emerging capabilities in air and space can support ground-based pathogen surveillance efforts. These capabilities include future missions such as NASA's Surface Biology and Geology (SBG), part of the fleet of missions that will make up the agency's Earth System Observatory. They said SBG will provide data that could be used in combination with machine learning for agricultural decision-making on a global scale.
Fernando Romero Galván, doctoral student and co-author of both studies, noted that sustainable agricultural practices are more important than ever in the face of climate change. "I think these are exciting times for remote sensing and plant disease detection," he said. "Scalable solutions can help producers make data-driven, sustainable crop management decisions."
