About

Jorge A. Guzman is associated with the Center for Digital Agriculture at the University of Illinois. The center focuses on advancing digital and smart agriculture through research, education, and industry collaboration. The center's initiatives include developing AI-driven tools such as CropWizard, a decision-support service powered by generative AI, and engaging in projects like AI AgriBench to build trust in AI agronomy through transparent benchmarking. The center also offers interdisciplinary educational programs, including a fully online Master’s Degree in Engineering with a concentration in Digital Agriculture, aimed at cultivating expertise in digital agriculture technologies. The center's research encompasses data collection, storage, transmission, and analysis, with a focus on optimizing precision agriculture, food manufacturing, water use, and other critical areas. It collaborates with international partners, such as National Taiwan University, to host global seminar series on digital and smart agriculture. The center actively involves students through programs like the CDA REU, providing opportunities to work on cutting-edge projects involving robotics, biotechnology, and animal science. Key contributions include developing accessible datasets like PigLife for computer vision training in livestock industries and exploring generative AI applications for agricultural decision-making, exemplified by CropWizard and CropGPT. The center's work aims to support researchers, educators, farmers, and industry stakeholders in keeping pace with technological transformations in agriculture.

Research topics

• Environmental science
• Water resource management
• Computer Science
• Geography
• Geology
• Ecology
• Soil science
• Environmental engineering
• Meteorology

Selected publications

• Desiccation cracks and their impacts on bare soil evaporation

  Soil and Tillage Research · 2026-04-13

  articleOpen accessSenior author
  PublisherDOI

• Evaluating Phosphorus Sorption and Desorption in Agricultural Wastewater Using Designer Biochar Pellets

  Water Environment Research · 2026-03-25

  articleOpen accessCorresponding

  ABSTRACT Tile drains enhance crop productivity but also increase phosphorus (P) runoff into nearby water bodies, contributing to harmful algal blooms. This study examines the effectiveness of designer biochar pellets (DBPs) in removing or releasing P from agricultural effluents, soils, or deionized water, respectively. The DBPs are composed of pine sawdust biomass and bentonite clay, pretreated with lime sludge prior to pyrolysis, and subsequently exposed to various wastewater effluents and field conditions. DBP treatment in P removal varied across effluent types, ranging from 18 to 155 mg kg −1 . In contrast, P desorption in deionized water ranged from 0.1 to 8.9 mg L −1 . DBP extracted from the field after the trial showed contrasting soil phosphorus extraction results, ranging from 0.45 to 0.6 mg L −1 for new and 0.3 to 1.2 mg L −1 for spent, respectively. Furthermore, P extracted from soil before planting (1 to 5 mg L −1 ), no lime sludge and DPB exposure to soil, after planting (3 to 15 mg L −1 ), after manure waste, lime sludge, and DBP exposure to soil, and after harvesting on plots treated as new , spent , and control was found to range from 10 to 55, 5 to 30, and 5 to 35 mg L −1 , respectively, indicating that DBPs may serve as a P‐removal agent and an amendment. Scanning electron microscopy (SEM) confirmed phosphorus sorption in the pellets, ranging from 0% to 0.2%, and ICP analyses identified other elements such as iron and silicon. The sorption and desorption experiment in this study is governed by four primary components: pH, salts (Ca, Mg, and K), P, and dissolved organic carbon (DOC) concentrations. Among these factors, pH plays a central role in regulating sorption behavior by influencing surface charge, ion speciation, and mineral reactivity. Additionally, lime sludge in DBPs enhances phosphorus removal by promoting P precipitation, further strengthening the system's sorption capacity. This underscores the importance of tailoring effluent treatment based on the specific characteristics of the source.

  PublisherDOI

• Tailings particle size distribution methodology: the good, the bad, and the ugly

  Paste/˜Pœaste · 2025-01-01

  articleOpen access

  The determination of particle size distribution (PSD) is a critical aspect in the characterisation of mine tailings, influencing engineering assessments, particularly in the areas of thickening, rheology, transport and deposition. This paper critically evaluates various methodologies used to determine the PSD of tailings, with a focus on fractions smaller than two millimetres. The study highlights the variations in methodologies, particularly emphasising the inadequacies of traditional techniques originally developed for weathered soils, which are often inappropriately applied to freshly ground rock tailings. Through a comprehensive comparison, the paper identifies the strengths and limitations of each method, exposing outdated practices that may lead to inaccurate PSD results. The discussion culminates in a recommendation for the most suitable methodology for tailings PSD determination, considering the unique properties of tailings material. The findings aim to guide consultants and site-based personnel in selecting the most reliable and accurate techniques for tailings PSD analysis.

  PublisherOA PDFDOI

• MSR42 Three Different Methods to Estimate a Rare Disease (RD) Prevalence in a Country with a Limited Dataset: Which One Fits?

  Value in Health · 2025-07-01

  article
  PublisherDOI

• Mitigating severe hydrological droughts in the Brazilian tropical high-land region: A novel land use strategy under climate change

  International Soil and Water Conservation Research · 2025-03-20 · 6 citations

  articleOpen access

  Severe droughts have significantly increased in frequency, magnitude, and intensity over the past decade, particularly impacting tropical and subtropical regions. Southeast Brazil exemplifies this trend, where severe hydrological droughts threaten the economy and society. We propose a novel approach to assess the impact of land use and climate change on severe hydrological droughts by integrating streamflow simulations with the Standard Hydrological Index (SHI), which is based on variations in water storage within the basin. To test our approach, the Lavras Simulation of Hydrology (LASH) model was applied to sixty-nine sub-basins in the upper Grande River basin, Southeast Brazil. We defined severe droughts as events where SHI ≤ −1.5, calculating threshold water storage (S threshold ) for the baseline period (1961–2005) to evaluate the impacts of land use and climate change scenarios. Land use scenarios were designed to maintain stable agricultural areas, while climate change scenarios (RCP4.5 and RCP8.5) were projected through 2060. The findings indicated that forest recovery significantly reduced severe hydrological drought frequency, whereas deforestation intensified it. Sub-basins altered by human activity showed more susceptibility to climate change. However, forested sub-basins were notably impacted by land use changes, mainly from pasture replacing Atlantic Forest. Highlighting deforestation as a critical driver for regional hydrological vulnerability, our method underscores the urgent need for effective land use management and conservation strategies of Atlantic Forest to mitigate the risk of severe droughts, regardless of the climate change pathways.

  PublisherDOI

• Prediction of gully erosion susceptibility through the lens of the SHapley Additive exPlanations (SHAP) method using a stacking ensemble model

  Journal of Environmental Management · 2025-04-25 · 11 citations

  articleOpen access

  This study develops a novel explainable stacking ensemble model that combines the stacked generalization ensemble method with SHapley Additive exPlanations (SHAP) to enhance the prediction and interpretation of gully erosion susceptibility. Applied to Jefferson County, Illinois, our approach leverages Random Forest (RF), Gradient Boosting Machine (GBM), Logistic Regression (LR), and Deep Neural Networks (DNN) as both base and meta-learners in various configurations, resulting in 44 distinct stacking models. The comparative analysis demonstrated the superior predictive performance of the stacked models when evaluated at 200 randomly gully sites selected points based on LiDAR difference observations; all but three exceeded the highest area under the curve (AUC) value of 0.86 achieved by the best-performing base model (GBM). The LR stacking model, combining RF and GBM as base models with LR as the meta-learner, emerged as the most effective, achieving an AUC of 0.916. The resulting gully erosion susceptibility map by the LR stacking model classified 33 % of the agricultural land (89,208 ha) as the "very high" class, compared to 27 %, 87 %, 27 %, and 55 % predicted by individual RF, LR, GBM, and DNN models, respectively. Crucially, SHAP analysis elucidated how changes in feature values influence model behavior, considering feature interactions within both the base models and the meta-learner. The SHAP identified the annual leaf area index (LAI) as the most influential feature in both RF and GBM base models. Additionally, it highlights the significance of the GBM model in comparison to the RF base model in the final decision-making process of the stacking model. By offering a transparent mechanism to evaluate how different features and models contribute to final decisions, this approach can be extended to broader environmental management and policy-making contexts, facilitating more informed and responsible resource allocation.

  PublisherDOI

• Comparative performance evaluation of Weir Minerals’ Cavex® CVX and Cavex® DE hydrocyclones for optimised sand generation in tailings dam construction

  Paste/˜Pœaste · 2025-01-01

  articleOpen access

  This study presents a comparative evaluation of the performance envelope of the Weir Minerals Cavex® CVX standard cyclone and the Weir Minerals Cavex® DE two-stage separation cyclone, focusing on their effectiveness in tailings classification for sand generation, a critical component in tailings dam construction. Full-scale cyclones were tested in a pilot plant under controlled conditions to assess the impact of key operational variables, including feed pressure and feed dilution, on the quality of the cyclone underflow. Particular attention was given to the fines content of the sand material produced as it directly influences the structural integrity of sand constructed tailings dams.

  PublisherOA PDFDOI

• Enhancing corn leaf fiber as phosphorus adsorbent material

  Water Environment Research · 2025-04-29 · 2 citations

  articleOpen access

  Abstract The contribution of dissolved phosphorus (P) from tile drain systems in agricultural lands is significant, leading to water impairment and promoting algae bloom development in water bodies. Hence, there is an urgent need for sustainable and efficient technology, such as absorbent material, that can effectively remove P at low concentrations in these systems. This study aimed to evaluate fiber extraction from corn leaves and its potential for reducing dissolved P. Corn fibers were extracted from corn leaves using alkali treatment by varying the concentration of sodium hydroxide (5–15%w/w), extraction temperature (85–95°C), and time (60‐120 min Results of the alkali extraction showed that the highest fiber recovery of 45.18 ± 0.39% g g −1 was achieved at 10% NaOH at 85°C for 60 min condition. To enhance the phosphorus adsorption capacity of the extracted corn fibers, kaolinite clay (0–30% w/w) and calcium carbonate (0–50% w/w) were incorporated into the leaf fiber. Adsorption tests revealed that corn leaf fiber alone reduced phosphate concentration by 8.75 ± 1.49% within 60 minutes. However, when enhanced with 30% w/w kaolinite clay and 35% w/w calcium carbonate, the phosphate concentration in the solution decreased by 79.40 ± 11.90%. Energy‐dispersive X‐ray fluorescence analysis confirmed the presence of phosphorus in the enhanced adsorbent material following treatment. This study demonstrates the potential of enhancing agricultural wastes like corn leaf fiber as a low‐cost alternative for phosphorus removal in agricultural tile drain systems that can later disposed of as fertilizer in a circular economy scheme. Practitioner Points Corn leaf fiber, extracted using alkali treatment, shows potential as a sustainable, low‐cost adsorbent material for phosphorus removal Enhancing corn leaf fiber with kaolinite clay and calcium carbonate significantly improves phosphate reduction Converting agricultural waste like corn leaf as adsorbent material can help manage phosphorus levels in agricultural tile drains

  PublisherOA PDFDOI

• Water Footprint (WFP) in Hydropower Plants Using Observed Meteorological Datasets: The Case of the Funil Hydropower Plant, Southeast Brazil

  Environmental footprints and eco-design of products and processes · 2024-01-01 · 1 citations

  book-chapter
  PublisherDOI

• Dynamic land cover evapotranspiration model algorithm: DyLEMa

  Computers and Electronics in Agriculture · 2024-03-27

  articleOpen accessCorresponding

  • Among decision tree-based MLs, RF Performance compared better than CART and XGB. • DyLEMa can reconstruct ET based on seasonal segregated atmospheric and land data. • DyLEMa ET PBIAS was reduced in temporal validation compared to the USGS ET data. • DyLEMa ET estimates are robust across various cloud contamination rates. • DyLEMa ET estimates are robust across Landsat sensor failure. This study presents the “Dynamic Land Cover Evapotranspiration Model Algorithm: DyLEMa” for continuous spatiotemporal evapotranspiration (ET) estimates across diverse land uses. DyLEMa employs a coupled Random Forest model with a novel dynamic recalibrating strategy to improve pre-optimized seasonal hyperparameters following satellite acquisition alongside land cover classes. An analysis of feature importance indicated the significant variability in ET processes across different land cover classes and seasons. Hence, DyLEMa was applied to 20 years of daily 30x30 m pixel resolution Landsat-derived ET data in Illinois to address spatial and temporal discontinuities due to cloud contamination and sensor failures. DyLEMa performance was evaluated on Eddy Covariance measurements to find out that DyLEMa predictions reduced the average PBIAS error from + 31 % to −7% compared to existing US Geological Survey ET products. Spatially, DyLEMa underscores the value of a land cover-aware approach in ET estimation under varied cloud cover rates and their ability to preserve landscape features. However, the performance of DyLEMa was affected by the quality of land cover classification, suggesting the need for a refined region-specific land cover classification. DyLEMa’s flexibility and performance suggest its applicability to other regions and satellite datasets, offering a promising reduction in uncertainty of ET estimates with impacts on environmental and water resources assessments on regional scales.

  PublisherDOI

Frequent coauthors

• Maria L. Chu

  39 shared

• Daniel N. Moriasi

  32 shared

• Patrick J. Starks

  22 shared

• Jean L. Steiner

  Kansas State University

  22 shared

• Ramón Piezzi

  17 shared

• Carlos Rogério de Mello

  Universidade Federal de Lavras

  15 shared

• Garey A. Fox

  North Carolina State University

  13 shared

• Dennis C. Flanagan

  National Soil Erosion Research Laboratory

  8 shared

Education

• Ph.D., Biosystems and Agricultural Engineering

  Oklahoma State University

  2010