Kaiyu Guan

Dr. Kaiyu Guan is a Blue Waters Professor in ecohydrology and remote sensing in the Department of Natural Resources and Environmental Sciences (NRES), College of Agricultural, Consumer and Environmental Sciences (ACES) at the University of Illinois at Urbana-Champaign, and at the National Center for Supercomputing Applications (NCSA). He uses satellite data, computational models, field work, and machine learning approaches to address how climate and human practices affect crop productivity, water resource availability, and ecosystem functioning. He is interested in applying his knowledge and skills in solving real-life problems, such as large-scale crop monitoring and forecasting, water management and sustainability, and global food security. His lab closely works with scientists in computer science (deep learning, high performance computing), plant physiologists, agronomists, and economists in addressing the above real-life challenges. 

Before he joined UIUC, Kaiyu was a post-doctoral scholar working with NASA Harvest partner Prof. David Lobell in the Center on Food Security and the Environment and Department of Environmental Earth System Science, Stanford University. His postdoc research examined the impacts of climate change as well as adaptive actions on crop production and food security in West Africa and the United States. He used empirical and process-based approaches to model drought and heat stress effects on staple crop production and assess possible adaptation pathways. He also worked with Dr. Joe Berry on using satellite-based photosynthesis measurements (sun-induced chlorophyll fluorescence) to quantify crop productivity. Dr. Guan briefly worked for the Climate Corporation to help their nitrogen modeling development between his time with Stanford and UIUC.

Kaiyu received his PhD from Princeton University in 2013, and worked in the Land Surface Hydrology Research Group. His PhD research focused on understanding how hydrological variability impacts vegetation dynamics (vegetation phenology, ecosystem productivity, and biome distributions) at the continent scale of tropics using multiple remote sensing datasets and ecosystem/land surface models (e.g. SEIB and VIC).