URBANA, Ill., Aug. 10, 2018 — What if we could predict, in real-time, crop productivity and water use for the entire United States corn belt? Using the help of the National Center for Supercomputing Applications (NCSA)’s Blue Waters supercomputer, Blue Waters Professor Kaiyu Guan has found a way to simulate and project crop growth and water use to help ensure food security and environmental sustainability, while also optimizing farm efficiency for the entire American corn belt.
This groundbreaking research will have broad applications, from a food consumer to an independent farmer, to government decision makers. Due to the wide-breadth and innovative nature of Guan’s work, he was recently awarded with the 2018 Global Environmental Change Early Career award from the American Geophysical Union (AGU), which seeks to award outstanding interdisciplinary contributions in research, education, or society in the area of global environmental change.
Guan, the sole NCSA Blue Waters Professor from the College of ACES (Agricultural, Consumer and Environmental Sciences), was honored by the AGU for combining computer science with agriculture and environmental sustainability, using the power of NCSA’s Blue Waters supercomputer to simulate crop growth, predict crop yields, and assess environmental sustainability.
“NCSA generously gave me the Blue Waters Professorship, which has allowed me to fully leverage the supercomputer resources on campus,” said Guan. “There are three ways we use Blue Waters extensively. First of all, we use Blue Waters to develop models to simulate crop growth in the entire US corn belt, either in the current climate or in future climates. The second thing we are doing is using Blue Waters to process hundreds of terabytes of satellite data to have the capacity to real-time monitor every crop field in the US corn belt. We have also used the GPUs in Blue Waters to build various machine learning algorithms to integrate domain knowledge and satellite data to predict real-time crop yields, crop water needs, and soil nitrogen conditions.”
With these interdisciplinary tools to model, monitor and predict agricultural ecosystems, the research of Guan and his team is advancing in relevance. As the climate continues to change, and human demands for food and energy continues to mount, real-time monitoring and adaptation assessments for agricultural systems are becoming urgently needed for both the government and individual farmers.
“We want to build the tools, by leveraging our domain knowledge, satellites, machine learning and supercomputing, for both farmers and for the government,” Guan said. “What I really hope to see is that we can help farmers understand their field’s condition by reporting real-time monitoring information that we generated. This way, farmers will know their expected yield production, understand how much water and nitrogen is in their soil, and how much irrigation and fertilizer they may need.”
With the help of NCSA’s Blue Waters supercomputer, Guan isn’t limited to modeling small parcels of land. Instead, researchers can simulate growth at a country-wide scale, even in areas that require external irrigation or variable climates.
“I hope to let farmers have all of this information to help them to optimize their practices and increase the economic prospects from their land, while at the same time keeping their land sustainable so it can be worked for multiple generations without worrying about the degradation of the land.”
About NCSA
The National Center for Supercomputing Applications (NCSA) at the University of Illinois at Urbana-Champaign provides supercomputing and advanced digital resources for the nation’s science enterprise. At NCSA, University of Illinois faculty, staff, students, and collaborators from around the globe use advanced digital resources to address research grand challenges for the benefit of science and society. NCSA has been advancing one third of the Fortune 50 for more than 30 years by bringing industry, researchers, and students together to solve grand challenges at rapid speed and scale.
Source: NCSA