About

Kaiyu Guan is a Levenick Endowed Professor in agroecosystem sensing and modeling at the University of Illinois Urbana-Champaign (UIUC). He is also a Blue-Waters Professor in Supercomputing at UIUC-NCSA, a University Scholar of the UIUC System, the Founding Director of the Agroecosystem Sustainability Center (ASC) at UIUC, and the Chief Scientist of the NASA Acres Consortium, representing NASA's flagship program in advancing US agriculture research. His major affiliations at UIUC include the Department of Natural Resources and Environmental Sciences (NRES), the Siebel School of Computing and Data Sciences (CS), the College of Agricultural, Consumer and Environmental Sciences (ACES), the Institute for Sustainability, Energy, and Environment (iSEE), and the National Center for Supercomputing Applications (NCSA). His research group employs advanced process models, satellite sensing technology, fieldwork, and artificial intelligence to investigate how climate and human practices influence crop productivity, water resources, ecosystem functioning, and environmental sustainability. His work focuses on applying these insights to real-world problems such as large-scale crop monitoring and forecasting, quantification of environmental impacts of farming and grazing, agricultural policy design, water management, sustainability, and global food security. Guan has held positions including full professor at UIUC since 2024, associate professor from 2021 to 2024, and assistant professor from 2016 to 2021. He is also the founding director of the Agroecosystem Sustainability Center since 2021 and the Blue Waters Professor in Supercomputing since 2016. His professional interests encompass agroecosystem modeling, cross-scale remote sensing, model-data fusion, terrestrial carbon cycle, biogeochemistry, climate change mitigation and adaptation, agroecosystem forecasting, artificial intelligence, and science-to-policy translation. Guan has received numerous honors, including the national agInnovation Research Award of Excellence (2025), being a finalist for the Blavatnik National Awards for Young Scientists (2024, 2025), the Levenick Endowed Professorship (2025), and recognition as a Clarivate Analytics Highly Cited Researcher (2024). He is actively involved in professional societies such as the American Geophysical Union, American Meteorological Society, Ecological Society of America, and European Geophysical Union.

Research topics

• Environmental science
• Ecology
• Agronomy
• Geography
• Computer Science
• Agroforestry
• Biology
• Environmental resource management
• Soil science
• Economics
• Physics
• Remote sensing
• Machine Learning
• Business
• Mathematics
• Natural resource economics
• Atmospheric sciences
• Materials science
• Chemistry
• Engineering
• Geology
• Meteorology
• Microeconomics
• Agricultural engineering

Selected publications

• Data for Clumping Index Estimation With 30°-tilted Cameras in Row Crops: Evaluation of Methods and Segment Size Effects

  Illinois Data Bank · 2026-01-01

  datasetOpen accessSenior author

  The clumping index (CI) quantifies the spatial distribution of foliage elements and is essential for accurately estimating the plant area index (PAI), canopy radiative transfer, and photosynthesis. Traditionally, the finite-length averaging method (LX), the gap size distribution method (CC), and a combined approach of CC and LX (CLX) have been applied to instruments like TRAC and digital hemispherical photography to estimate CI. However, a comprehensive evaluation of these methods in row crops remains limited, especially regarding the influence of segment size on CI. Meanwhile, digital cameras offer a cost-effective and user-friendly solution for canopy measurements in row crops, yet their application in this context remains underexplored. In this study, we employed a new approach using a 30°-tilted digital camera to estimate CI in corn and soybean fields, applying the LX, CC, and CLX methods. We systematically assessed the performance of these three methods by combining field measurements in real-world fields with simulations using the LESS 3D radiative transfer model. Our results showed that CLX applied to the whole image and 45° segment offered accurate estimation of CI (bias within ±0.1, RMSE < 0.2) and PAI (bias within ±0.4, RMSE < 1) in real-world fields and LESS simulations. The accuracy of the LX method was highly sensitive to segment size, with the best performance observed at the 15° segment (PAI bias within ±0.4). In contrast, the CC method remained stable across different segment sizes, and its performance was generally comparable to that of LX, except at the 15° segment. Across view zenith angles, CI derived from CC generally showed a continuous increase, while those from LX and CLX followed a rising trend at small zenith angles but began to decline at 68°, likely due to an increasing proportion of no-gap segments. Seasonally, LX tended to show decreasing CI during early growth stages but increased as the canopy matured, whereas CC and CLX showed gradually increasing CI before plateauing at peak PAI. The 30°-tilted camera effectively captured CI variations across different angles and growth stages, making it a practical and robust instrument for row crop canopy structure analysis. Applying these CI methods to digital cameras offers a low-cost and accessible CI estimation alternative, improving canopy structure monitoring accuracy in row crops.

  PublisherDOI

• How do Hydrological Variability and Human Activities Control the Spatiotemporal Changes of Riverine Nitrogen Export in the Upper Mississippi River Basin?

  Environmental Science & Technology · 2025-12-20 · 4 citations

  articleSenior authorCorresponding

  Excessive nitrogen export from agricultural watersheds remains a critical water quality challenge, with the Upper Mississippi River Basin (UMRB) significantly contributing to downstream eutrophication and hypoxia in the Gulf. This study investigates the spatiotemporal dynamics of riverine nitrate plus nitrite (NO3– + NO2–-N) export across the UMRB at high spatial resolution (12-digit Hydrologic Unit Codes or HUC12 subwatershed scale) during 2001–2020 and quantifies the effects of anthropogenic activities and hydrological variability on riverine NO3– + NO2–-N export changes in the region between 2001–2005 and 2016–2020. Our results revealed hotspots of substantial increases in NO3– + NO2–-N yields across the UMRB, with distinct regional patterns in driving factors. Over the entire UMRB, NO3– + NO2–-N yields increased by 9.7 kg/ha/yr on average from 2001–2005 to 2016–2020, with anthropogenic activities contributing 4.8 kg/ha/yr and hydrological variability contributing 4.9 kg/ha/yr. The northern and western UMRB had combined influences from both anthropogenic activities and hydrological variability, while the east-central regions had predominantly hydrologically driven changes. Agricultural sources, including fertilizer, manure, and biological nitrogen fixation, collectively contributed over 80% of NO3– + NO2–-N loading throughout the basin. This framework for disentangling human and hydrological impacts provides critical insights for developing effective and targeted watershed management strategies to reduce nutrient losses and improve water quality.

  PublisherDOI

• Multi-sensor assessment of phenology-based field-level cover cropping detection using satellite vegetation time series from Harmonized Landsat-8 and Sentinel-2, MODIS, and PlanetScope

  International Journal of Applied Earth Observation and Geoinformation · 2025-12-03 · 1 citations

  articleOpen accessCorresponding

  • Multi-sensor assessment of phenology-based field-level cover cropping detection. • HLS surpasses MODIS and MODIS-calibrated PlanetScope with an accuracy of 76%. • MODIS-based radiometric calibration decreases PlanetScope’s performance. • Multi-scale cover cropping data are leveraged with quantified discrepancies. • Field size, regional adoption, and cover crop species impact detection accuracy. Remote sensing-detected phenological differences among cover crops, cash crops, and soil backgrounds are crucial for detecting cover cropping practices. However, variations in detection performance with satellite data of different spatial, temporal, and radiometric characteristics and the potential factors affecting the performance remain unclear. Building on the previously developed framework, we aimed to evaluate the performance of multiple satellite sensors, leverage multi-scale ground truth data, and identify potential factors for improving field-level cover cropping detection. Specifically, we (1) compared widely-used NDVI time series from Harmonized Landsat-8 and Sentinel-2 (HLS, ∼3-day and 30 m), MODIS (daily and 250 m), and PlanetScope (near-daily and 3 m, requiring radiometric calibration), (2) quantified discrepancies between county-level data from National Agricultural Statistics Service (NASS) and field-level data from Indiana State Department of Agriculture (ISDA), and (3) analyzed the impacts of cover cropping field sizes, regional adoption rates, and cover crop species on cover cropping detection. We found that (1) HLS outperformed MODIS and MODIS-calibrated PlanetScope (CPS) with an average accuracy of 76.2 % ± 3.0 % across Indiana in 2017. (2) Significant discrepancies between ISDA and NASS data were found in 9 % of counties and were negatively correlated with detection accuracies in counties where ISDA-reported adoption was substantially higher than that reported by NASS (r = -0.54, p < 0.005). (3) Detection accuracy was higher in larger cover cropping fields, positively correlated with regional adoption rates (r = 0.42 and p < 0.001), with the highest accuracy for wheat (88.95 %), followed by winter grains (77.73 %), ryegrass (75.52 %), barley (75.35 %), and cereal rye (68.59 %). Our study offers valuable insights into selecting satellite sensors, reconciling multi-scale ground truth data, and identifying potential factors for improving phenology-based field-level cover cropping detection.

  PublisherDOI

• Embracing large language model (LLM) technologies in hydrology research

  Environmental Research Water · 2025-05-27 · 3 citations

  articleOpen accessSenior authorCorresponding

  The growing complexity of hydrological systems necessitates innovative approaches to data management, knowledge management, and model development. Large language models (LLMs) have great potential to accelerate hydrological research by unifying and advancing these three critical aspects. In this perspective work, we review recent advances and applications of LLMs and exemplify using LLMs in hydrology studies. We demonstrate that LLMs can enhance data accessibility by efficiently extracting and organizing information from diverse sources and formats. LLMs also facilitate comprehensive knowledge management through knowledge retrieval and synthesis, enabling the integration of various datasets. Furthermore, LLMs, combined with modular development, Chain-of-Thought reasoning, and the intent-based network framework, hold immense promise for transforming physical model development and fostering model unification across scales. LLMs are powerful tools for integrating domain hydrological knowledge and advances in machine learning. Their potential in hydrological studies and the mitigation of their risks will require rigorous assessment, domain-specific regulations and guidelines, and significant contributions from hydrologists. We envision LLMs become indispensable resources for meeting the evolving demands of transdisciplinary hydrological research.

  PublisherDOI

• Industrial Design-Driven Exploration of the Impact Mechnism of Fire Evacuation Efficiency in High-Rise Buildings

  Sustainability · 2025-10-21

  articleOpen access1st author

  This study constructs a comprehensive analytical framework for fire evacuation efficiency in high-rise buildings based on risk management theory, environment–behavior relationship theory, and stress-cognition theory. Through a systematic literature review and three rounds of Delphi expert consultation, a measurement questionnaire for fire-escape behavior was developed, ultimately screening out 35 key measurement items. Data were collected from 248 residents of high-rise residential buildings in Beijing who had experienced fires. Exploratory factor analysis (EFA), confirmatory factor analysis (CFA), and structural equation modeling (SEM) were employed to validate the model. The results show that the fire emergency management system (FEMS) and building-safety performance planning (BSPP) have a significant positive impact on escape response behavior (ERB), while situational panic psychological perception (SPPP) has a negative impact. The study also finds that emergency-response training and diversified escape-route design are key driving factors, and cognitive bias significantly affects situational panic psychological perception. This research provides empirical support for fire-escape management in high-rise buildings and develops a reliable measurement tool.

  PublisherOA PDFDOI

• Damage identification method of reef limestone concrete structures based on wavelet packet energy variation rate

  Marine Georesources and Geotechnology · 2025-06-16 · 1 citations

  article
  PublisherDOI

• Comparing continuous-corn and soybean-corn rotation cropping systems in the U.S. central Midwest: Trade-offs among crop yield, nutrient losses, and change in soil organic carbon

  Agriculture Ecosystems & Environment · 2025-06-07 · 8 citations

  articleCorresponding
  PublisherDOI

• Corrigendum to “An upscaling approach for estimating field-level irrigation water use through the Budyko framework” [J. Hydrol. 661 (2025) 133785]

  Journal of Hydrology · 2025-09-26

  articleCorresponding
  PublisherDOI

• Transfer learning for improved crop yield predictions in a cross-scale pathway: a case study for Brazilian national soybean

  International Journal of Applied Earth Observation and Geoinformation · 2025-11-21

  articleOpen accessCorresponding

  • Cross-scale pathway suffers from model scalability and data scarcity. • Transfer learning improves cross-scale pathway by 15% explained variance. • Transfer learning slightly alleviates the impact of model scalability. • Transfer learning significantly alleviates the impact of data scarcity. Crop yield prediction at a fine spatial scale is crucial for improving agricultural management and resource allocations. Many countries and regions lack fine-scale yield data for fine-scale modeling and thus have to use a “cross-scale pathway”, where coarse-scale (e.g., state-level) data are used to train a model for fine-scale (e.g., county-level or field-level) yield predictions. However, the cross-scale pathway has limited effectiveness in predicting yield due to issues with data availability and model scalability. In this study, we quantify the benefits of transfer learning in the cross-scale pathway. We applied transfer learning by fine-tuning a previously trained and validated AI-based machine learning model, originally developed for field-level soybean yield predictions in the United States, using Brazilian state-level data to predict Brazilian municipal-level soybean yield. Despite differences in environmental conditions, crop phenology, and yield responses between the U.S. and Brazil, we show that transfer learning improves the municipal-level predictions from the cross-scale pathway by increasing the R 2 from 0.29 (without transfer learning) to 0.44. Notably, this is achieved without using any municipal-level data and relying only on scarce state-level observations. When the municipal-level data were used, the transfer learning achieved an R 2 of 0.57, the most stable high performance compared with previous studies. The effectiveness of the cross-scale pathway, thus, increases from 50% to 78% with transfer learning. These findings demonstrate the benefits of transfer learning in the cross-scale pathway under data-limited conditions, and underscore the potential for global crop yield predictions across scales.

  PublisherDOI

• Clumping index estimation with 30°-tilted cameras in row crops: Evaluation of methods and segment size effects

  Agricultural and Forest Meteorology · 2025-09-24

  articleCorresponding
  PublisherDOI

Recent grants

• CAREER: Ensuring Co-Sustainability of Food Production and Environmental Quality in the U.S. Midwest Agroecosystems

  NSF · $510k · 2019–2026

Frequent coauthors

• Bin Peng

  351 shared

• Carl J. Bernacchi

  University of Illinois Urbana-Champaign

  146 shared

• Chongya Jiang

  131 shared

• Wang Zhou

  Sun Yat-sen University

  108 shared

• Sheng Wang

  Northeastern University

  95 shared

• Elizabeth A. Ainsworth

  87 shared

• Hyungsuk Kimm

  Seoul National University

  76 shared

• Ming Pan

  73 shared

Labs

• Siebel School of Computing and Data SciencePI

Education

• Ph.D., Computer Science

  University of Illinois at Urbana-Champaign

  2007

• M.S., Computer Science

  University of Illinois at Urbana-Champaign

  2003

• B.S., Computer Science

  University of Science and Technology of China

  2001

Awards & honors

• National winner of the agInnovation Research Innovation Awar…
• Blavatnik National Awards for Young Scientist Finalist (2025…
• Levenick Endowed Professorship (2025)
• Clarivate Analytics Highly Cited Researchers list (2024)
• Blavatnik National Awards for Young Scientist Finalist (2024…