About

Dr. Sami Khanal is an Associate Professor in the Department of Food, Agricultural and Biological Engineering at The Ohio State University. His research focuses on developing decision support systems to promote sustainable agricultural production practices, involving stakeholders such as farmers, environmentalists, and policymakers. He utilizes advanced technologies including GIS, global positioning systems, remote sensing (from drones, aircraft, satellites, and ground sensors), machine vision, image processing, machine learning, and ecosystem models to understand and quantify ecosystem services such as crop and soil health, biomass, water quality, and greenhouse gas emissions across various land management practices. Dr. Khanal's work aims to create agricultural landscapes where increased food and feedstock production coexists with environmental conservation and mitigation of environmental problems.

Research topics

• Computer Science
• Machine Learning
• Artificial Intelligence
• Engineering
• Geography
• Environmental science
• Agricultural engineering
• Aeronautics
• Mathematics
• Environmental resource management
• Simulation
• Business
• Telecommunications
• Agronomy

Selected publications

• Nutrient recovery from Co-Hydrothermal carbonization of animal manures: Synergistic effects on hydrochar properties and agronomic potential

  Waste Management · 2026-01-31 · 1 citations

  articleOpen access

  This study evaluates the effects of co-hydrothermal carbonization (Co-HTC) of poultry (PM), dairy (DM), and swine manure (SM) at 180, 220, and 260 °C on hydrochar yield, nutrient recovery, phytotoxicity, and heavy metal retention. Co-HTC of PM with DM (PMDM) and PM with SM (PMSM) were assessed for synergistic effects by comparing observed values to predicted additive outcomes based on individual HTC data. Hydrochar yield decreased with increasing temperature across all treatments; however, PMSM and PMDM exhibited synergistic enhancement in yield at 180 °C (synergistic coefficient: 1.13-1.23). Elemental analysis indicated that nitrogen retention was maximized in PMDM hydrochars (4.71 ± 0.61% N at 180 °C), while PMSM hydrochars exhibited superior retention of phosphorus, magnesium, and calcium. Most potassium leached into the co-HTC process liquid. Heavy metals (Zn, Cu, and Ni) were effectively immobilized, with Co-HTC resulting in lower concentrations of Mo, Pb, and Cr compared to individual HTC. Seed germination index (GI), used to assess phytotoxicity, revealed temperature- and feedstock dependent trends, with PMSM hydrochar produced at 180 °C achieving the highest GI (140.91 ± 7.05%), indicating synergistic reduction in phytotoxicity. These findings demonstrate that Co-HTC can optimize recovery of nutrients into hydrochar and enhance the agronomic and environmental quality of hydrochars through tailored feedstock interactions and process tuning.

  PublisherDOI

• AI-Driven Insights from Multimodal Data for Optimized Soybean Growth Monitoring 

  2026-03-14

  articleOpen accessSenior author

  Monitoring soybean growth provides critical insights for farmers, enabling them to closely track crop development and implement proactive management practices that ultimately enhance yields. Inefficient management and excessive chemical use not only reduce efficiency but also result in significant environmental consequences, including water contamination and increased greenhouse gas (GHG) emissions. These environmental impacts degrade soil health, disrupt weather patterns, and contribute to issues such as soil nutrient depletion and irregular precipitation, all of which have direct, adverse effects on agricultural productivity. Integrating various sensor data, such as satellite and small Unmanned Aerial System (sUAS) data, with machine learning (ML) offers a pathway to precise soybean growth monitoring. This pathway enables farmers to make data-driven decisions that reduce the need for field scouting while improving resource efficiency. Though recent studies have begun to explore field-level, precise growth monitoring using sUAS and satellite imagery, in-depth research on their integration strategies is necessary to develop practical, cost-effective methods for accurately estimating soybean phenological stages. In this study, a comprehensive analysis of soybean growth is conducted across early vegetative to reproductive stages using ML and multi-sensor methods. The selected soybean fields are located at three Ohio State Agricultural Research Stations, which are geographically dispersed across Ohio, USA. Using fixed-wing Wingtra sUAS, high-resolution optical images of soybean fields were collected from 2023 to 2025. To determine whether simple machine learning or complex deep learning methods perform better, multiple combinations of these models with sUAS and satellite are trained, and their performance is evaluated. Best model performance was observed with the Vision Transformer (ViT) model on sUAS images, which detected soybean growth stages with an average Root Mean Squared Error (RMSE) of 0.7. Poor performance was observed with the Random Forest model on open-source Sentinel-2 images, with an RMSE of 3.1. Upon closer investigation of good-performing and poor-performing growth stages through sUAS and satellite, it was observed that early growth stages performed really well only with sUAS data (RMSER2), satellite performed relatively well with RMSE

  PublisherDOI

• Leveraging machine learning and geospatial analysis to determine agronomic and economic optima for variable‐rate seeding in corn and soybean

  Agronomy Journal · 2026-03-01

  articleSenior author

  Abstract Integrating soil and topographic properties into variable‐rate seeding (VRS) provides essential information for decision‐making to enhance crop production and profitability. Only a few studies have explored geospatial and machine‐learning approaches to understand factors influencing crop yield and profitability in VRS. Therefore, field studies on corn ( Zea mays L.) and soybean [ Glycine max (L.) Merr.] production systems were conducted in Miami, OH, with five and four seed‐rate treatments, respectively, from 2017 to 2022. The objectives of this study were to explore the effectiveness of VRS, in combination with soil and topographic properties, in delineating the optimal agronomic and economic seeding rates for corn and soybeans. To achieve this goal, data on yield, soil properties, and topographic factors were collected. Spatial regression model and geospatial analyses were performed and compared with a random forest machine‐learning model to identify key variables that best explain yield. Results from spatial regression and the random forest model indicated that elevation, cation exchange capacity, slope, and soil organic matter were the key variables influencing corn and soybean yields, along with seeding rate. Hence, these field properties were used to delineate clusters. For corn, both agronomic and economic optimum seeding rates varied across clusters, indicating the importance of a cluster‐specific VRS strategy. In contrast, the agronomic and economic optimum seeding rates for soybean were insignificant across clusters. These findings underscore VRS's potential for corn in heterogeneous fields but highlight its limited applicability in soybeans. Future research should prioritize field‐specific VRS to validate cluster‐based recommendations and ensure scalability across diverse agricultural systems.

  PublisherDOI

• A multimodal machine learning framework for cereal rye biomass estimation across landscapes

  Remote Sensing Applications Society and Environment · 2026-04-01

  articleSenior authorCorresponding
  PublisherDOI

• Improving the Quality of LiDAR Point Cloud Data in Greenhouse Environments

  Agronomy · 2025-09-16

  articleOpen access

  Automated crop monitoring in controlled environments is imperative for enhancing crop productivity. The availability of small unmanned aerial systems (sUAS) and cost-effective LiDAR sensors present an opportunity to conveniently gather high-quality data for crop monitoring. The LiDAR-collected point cloud data, however, often encounter challenges such as occlusions and low point density that can be addressed by acquiring additional data from multiple flight paths. This study evaluated the performance of using an Iterative Closest Point (ICP)-based algorithm for registering sUAS-based LiDAR point clouds collected in the greenhouse environment. To address the issue of objects that may cause ICP or local feature-based registration to mismatch correspondences, this study developed a robust registration pipeline. First, the geometric centroid of the ground floor boundary was leveraged to improve the initial alignment, and then piecewise ICP was implemented to achieve fine registration. The evaluation of point cloud registration performance included visualization, root mean square error (RMSE), volume estimation of reference objects, and the distribution of point cloud density. The best RMSE dropped from 20.4 cm to 2.4 cm, and point cloud density improved after registration, and the volume-estimation error for reference objects dropped from 72% (single view) to 6% (post-registration). This study presents a promising approach to point cloud registration that outperforms conventional ICP in greenhouse layouts while eliminating the need for artificial reference objects.

  PublisherOA PDFDOI

• Beyond radiation use efficiency: A mechanistic biochemical photosynthesis model for crop growth simulation and agroecosystem modeling

  Computers and Electronics in Agriculture · 2025-03-05 · 2 citations

  article
  PublisherDOI

• Supplemental figures for "Development of a Subsurface Sensing Probe for Measurement of Nitrogen Oxide Gases"

  2025-06-11

  preprintOpen accessSenior author

  <p dir="ltr">This is the supplemental material document corresponding to the article entitled 'Development of a Subsurface Sensing Probe for Measurement of Nitrogen Oxide Gases'. The document primarily includes supplementary figures and plots that display gas concentration measurements for N2O and NO sensor devices during additional 14-day fertilizer trials. Also included are data plots regarding soil properties during all fertilizer trials.</p>

  PublisherDOI

• An Orchestration Engine for Scalable, On-Demand AI Phenotyping from UAS Imagery in Agriculture

  2025-11-03 · 1 citations

  articleOpen accessSenior author

  Farmers, worldwide, are increasingly leveraging data derived from Unmanned Aerial Systems (UAS) imagery to enhance decision-making. This trend reflects a significant rise in both academic and commercial sectors. Furthermore, advancements in UAS and battery technology now enable longer flights and greater coverage, while higher-resolution optical and multispectral cameras provide finer ground sampling distances (GSD). From a regulatory standpoint, the Federal Aviation Administration (FAA) is beginning to accommodate multi-drone operations and Beyond Visual Line of Sight (BVLOS) operations, which can ultimately reduce the cost to collect UAS imagery.

  PublisherOA PDFDOI

• Cyberinfrastructure for machine learning applications in agriculture: experiences, analysis, and vision

  Frontiers in Artificial Intelligence · 2025-01-23 · 5 citations

  articleOpen accessSenior author

  Introduction: Advancements in machine learning (ML) algorithms that make predictions from data without being explicitly programmed and the increased computational speeds of graphics processing units (GPUs) over the last decade have led to remarkable progress in the capabilities of ML. In many fields, including agriculture, this progress has outpaced the availability of sufficiently diverse and high-quality datasets, which now serve as a limiting factor. While many agricultural use cases appear feasible with current compute resources and ML algorithms, the lack of reusable hardware and software components, referred to as cyberinfrastructure (CI), for collecting, transmitting, cleaning, labeling, and training datasets is a major hindrance toward developing solutions to address agricultural use cases. This study focuses on addressing these challenges by exploring the collection, processing, and training of ML models using a multimodal dataset and providing a vision for agriculture-focused CI to accelerate innovation in the field. Methods: Data were collected during the 2023 growing season from three agricultural research locations across Ohio. The dataset includes 1 terabyte (TB) of multimodal data, comprising Unmanned Aerial System (UAS) imagery (RGB and multispectral), as well as soil and weather sensor data. The two primary crops studied were corn and soybean, which are the state's most widely cultivated crops. The data collected and processed from this study were used to train ML models to make predictions of crop growth stage, soil moisture, and final yield. Results: The exercise of processing this dataset resulted in four CI components that can be used to provide higher accuracy predictions in the agricultural domain. These components included (1) a UAS imagery pipeline that reduced processing time and improved image quality over standard methods, (2) a tabular data pipeline that aggregated data from multiple sources and temporal resolutions and aligned it with a common temporal resolution, (3) an approach to adapting the model architecture for a vision transformer (ViT) that incorporates agricultural domain expertise, and (4) a data visualization prototype that was used to identify outliers and improve trust in the data. Discussion: Further work will be aimed at maturing the CI components and implementing them on high performance computing (HPC). There are open questions as to how CI components like these can best be leveraged to serve the needs of the agricultural community to accelerate the development of ML applications in agriculture.

  PublisherOA PDFDOI

• Scaling Biomass Estimation by Expanding Ground Truth with UAS-Derived Training Data

  Remote Sensing · 2025-09-12 · 2 citations

  articleOpen accessSenior authorCorresponding

  Accurate estimation of winter cover crop biomass at a landscape scale is key to assessing benefits and promoting widespread adoption. Satellite imagery offers broad coverage but is limited by coarse resolution and spatial mismatch with field measurements. This study introduces a hybrid framework to improve satellite-based estimation of cereal rye cover crop biomass by integrating UAS-derived data. Extreme gradient boosting (XGBoost) and random forest (RF) machine learning models were trained across three scenarios: (1) UAS-based models, using field-measured biomass alongside UAS-derived vegetation indices (VIs) and crop height; (2) satellite-based models, using field-measured biomass and Sentinel-2 satellite-derived VIs and grey level co-occurrence texture measures; and (3) UAS–satellite synergistic models, where UAS-estimated biomass served as surrogate ground truth for calibrating satellite-derived VIs and texture features. Our results show that the error increased by up to 49% for XGBoost and 31% for RF when using field-measured cereal rye biomass at a 0.5 × 0.5 m2 to directly train satellite-derived features with 10 m resolution (RMSE = 83.09 g m−2 for XGBoost and 80.46 g m−2 for RF), compared to using UAS-derived features at 5 cm (RMSE = 55.78 g m−2 for XGBoost and 61.63 g m−2 for RF). Notably, the UAS–satellite synergistic model demonstrated improved alignment with RMSE of 59.79 g m−2 for XGBoost and 61.45 g m−2 for RF while potentially overcoming the limitations due to differences in the size of satellite pixels and field measurements. These findings underscore the potential of UAS-derived biomass estimates to improve the accuracy, scalability, and spatial fidelity of satellite-based cover crop biomass estimation.

  PublisherOA PDFDOI

Frequent coauthors

• Ajay Shah

  The Ohio State University

  7 shared

• Kushal KC

  The Ohio State University

  7 shared

• Robert P. Anex

  6 shared

• Kaiguang Zhao

  The Ohio State University

  5 shared

• S. A. Shearer

  The Ohio State University

  5 shared

• Christopher Stewart

  4 shared

• John P Fulton

  Brown University

  4 shared

• Daryl Herzmann

  Iowa State University

  3 shared

Education

• PhD, Environment and Resources

  University of Wisconsin-Madison

  2012

Awards & honors

• First Woman Member of ASAE, 1921