Fernando Romero Galvan is a first-year Ph.D. student working in the lab of Katie Gold, assistant professor of plant pathology and plant-microbe biology. The first student in the School of Integrative Plant Science to receive NASA’s FINESST (Future Investigators in NASA Earth and Space Science and Technology) award, Fernando is working to find solutions to major diseases impacting the New York grape industry through cutting-edge research that integrates digital agriculture technologies.
What do you love most about being a grad student in Katie Gold’s lab?
What I love most is the lab culture and the way Katie is working on improving the graduate student experience. One way she does this is by placing emphasis on mental health and work-life balance. Good science happens when scientists are happy and are able to express themselves, and a warm and inviting lab culture is needed for that to happen. It’s inspiring and someday, should I start a lab of my own, I’d like to continue that culture. Oh, and we also we get to play with robots.
What attracted you to Cornell AgriTech to do your studies?
Cornell AgriTech is a leader in digital agriculture. Labs such as Katie’s are developing innovative disease detection tools that are noninvasive. These can reduce the use of fungicides and advance us toward a more food secure world. I wanted to be a part of it!
What will the NASA award you’ve received allow you to do in your research?
My NASA FINESST award allows me to continue developing scalable disease detection in grapevines. The money directly supports my stipend, my research, tools and data collection, and the recognition offers a platform to showcase my work at a conference at Washington, D.C., which will allow me to make connections with other scientists in the NASA earth science community.
What is the focus of your research and what industry problem are you exploring?
The goal of my research is to develop both a specific application and general framework for scalable disease detection with imaging spectroscopy. For this work, I use grapevine leafroll virus (GLrV) and Vitis vinifera as a model system. Understanding how disease detection scales from the ground to airborne to spaceborne scale is an essential first step toward building global disease surveillance systems with forthcoming imaging spectroscopy satellite missions.
What technologies and innovations will enable you to make discoveries?
I work with hyperspectral imagery from NASA’s Airborne Visible/Infrared Imaging Spectrometer Next Generation, the Cadillac of imaging spectrometers. Although airborne instruments cannot cover the globe, new spaceborne imaging spectrometers will remove that limitation. I strategically transform my data to mimic data that we might get from these systems one day, which allows me to test how our knowledge, models and methods can be used to build a global disease modeling framework. Additionally, I use machine and deep learning methods to analyze my data, and will be using the PhytoPatholoBot, a fully autonomous vineyard sensing robot developed by Yu Jiang and Leo Liu, to collect validation data in one of our collaborating vineyards this summer.
How will your research benefit grape growers/the grape industry?
Detecting GLrV with spectroscopic imagery would improve how grape growers manage this pernicious disease and reduce the cost of management through more strategically deployed scouting teams and molecular testing. GLrV undergoes a yearlong latent phase in which it is infectious but the vine does not yet show symptoms. We are aiming to build a platform that will enable growers to more strategically and reliably identify vineyard sections to deploy highly accurate but expensive ground detection methods.
What’s the most interesting thing you’ve discovered in your research so far?
It’s motivating to see how well our models can differentiate between uninfected and GlrV infected vines. In the previous questions I have described the impact of this tech, and to see progress to make that vision real is fascinating and exciting.
Romero Galvan's research is supported by NASA’s FINESST award #80NSSC21K1605.
