Save as PDF

Heesup Yun

Postdoctoral Researcher, University of California, Davis

hspyun@ucdavis.edu | heesup.github.io | Google Scholar

Research Interests

AI-enabled sensing and autonomy for agricultural systems, agricultural robotics and UAVs, edge AI, simulation-to-real transfer with synthetic data, thermal and multimodal sensing for crop water stress and phenotyping

Education

Ph.D., Biological Systems Engineering2026

Department of Biological and Agricultural Engineering, University of California, Davis, CA, USA

Dissertation: Generative Models for Image-Based Plant Analysis: Thermal Image Super-Resolution and Plant Architecture Generation

Advisor: J. Mason Earles

M.S., Biosystems Engineering2017

Seoul National University, Seoul, Korea

B.S., Biosystems Engineering / Mechanical and Aerospace Engineering2015

Seoul National University, Seoul, Korea

Research Experience

Postdoctoral Researcher, Plant AI and Biophysics Lab08/2026 – present

University of California, Davis

Graduate Research Assistant, Plant AI and Biophysics Lab09/2021 – 06/2026

University of California, Davis

G×E×M Innovation in Intelligence for Climate Adaptation (gemini.sf.ucdavis.edu/)

  • Four years of field data collection using drones and ground rovers
  • Thermal image super-resolution and RGB sensor fusion for low-cost thermal cameras
  • Synthetic training data from 3D plant simulation (Helios) for thermal and RGB models
  • Real-to-sim plant modeling: generating 3D plant simulation models from images with vision language models
  • Low-cost weather stations for plot-scale microclimate measurement
  • iOS app for low-cost image data collection; leaf angle measurement web app using a smartphone IMU
  • Web-based data processing and analysis software for breeding researchers

Graduate Student Researcher, Biosystems Control and Precision Agriculture Lab03/2015 – 02/2017

Seoul National University

UAV-based remote sensing for growth monitoring of major upland crops (iPET, 3 years)

  • Growth monitoring of white radish and Chinese cabbage with UAV imagery
  • Multi-temporal NDVI analysis for crop growth assessment
  • Plant volume and biomass estimation from 3D digital surface models

Undergraduate Researcher07/2012 – 02/2015

Seoul National University

Biosystems Control and Precision Agriculture Lab: UAV remote sensing for hairy vetch biomass estimation

  • Excess green (ExG) index monitoring from UAV RGB imagery
  • Cover crop volume and biomass estimation

Off-Road Equipment and Soil-Machine Systems Design Lab: load-sensitive engine throttle control for fuel efficiency

  • Tractor RPM filtering with a Kalman filter
  • MATLAB/Simulink model of tractor fuel consumption
  • ISO 11783 (ISOBUS) firmware in C on an ATmega microcontroller

Field Robotics and Sensing Systems

WeedTrackr: edge AI weed monitoring for orchards and vineyards2025

Raspberry Pi Zero with the Raspberry Pi AI Camera (Sony IMX500) and GPS, designed to mount on a mower or tractor. MobileNetV2 weed classifier quantized to INT8 for on-camera inference (75% smaller model), with geotagged weed maps for spray planning. 1st Place, AIFS × Sony AI AgTech Challenge.

Robo-ag: autonomous targeted spray robot2023

Targeted spray applicator on the farm-ng Amiga for vineyard rows. GPS path following, GeoJSON application maps, and solenoid nozzle control. Elegance in Design Prize, Farm Robotics Challenge.

Research UAV platforms2023 – 2024

Custom multirotors (DJI F550, Tarot 650 Sport) with Pixhawk/ArduPilot. Assembly, PID tuning, flight endurance testing, and LiDAR/GPS integration with EMI shielding for autonomous missions.

Weighing and data logging system for forest evapotranspiration

Load cell and Arduino-based system that continuously weighs and logs the forest floor to measure evapotranspiration (ET) in a research forest (J4). Applied to a forest fire prevention system (Korean Patent 10-1938973).

Industry Experience

Software Engineer, Division of AI Edge Solution02/2017 – 08/2021

A.I.MATICS Inc., Seoul, Korea (automotive AI and vehicle telematics)

Computer vision for driver monitoring and ADAS, from embedded deployment on in-vehicle devices to cloud processing on AWS

Driver action monitoring system for ADAS

  • Driver body keypoint detection (MobileNetV3 backbone, heatmap estimation), object detection on IR dashcam images, and RNN-based driver attention classification
  • Launched as a product in May 2020

Driver status monitoring system for ADAS

  • Facial keypoint detection, CNN-based eye status classification, and KLT face tracking on IR dashcam images
  • Shown at CES 2019 and the National Association of Fleet Administrators

Motorcyclist and vehicle detection for ADAS

  • Aggregate channel features and random forest, optimized for ARM NEON
  • HOG and SVM with a hardware-accelerated feature pipeline on a Blackfin DSP

Cloud processing of driver videos

  • Deep-learning driver recognition on dashcam videos (AVI) uploaded to AWS S3, with the models deployed on EC2
  • Queue-based automatic spawning and scaling of EC2 instances

Publications

Journal Articles

  1. J11.Uyehara, I. K., Yun, H., Rizzo, K. T., Ranario, E., & Earles, M. (2026). AgRowStitch: A Leaf-Scale Image Stitching Pipeline for Ground-Based Agricultural Images. Applied Engineering in Agriculture, 42(3), 307-317.
  2. J10.Yun, H., Uyehara, I. K., Droutsas, I., Ranario, E., Diepenbrock, C. H., Bailey, B. N., & Earles, J. M. (2026). A vision language model for generating XML-based organ-level plant architecture representations of cowpea from simulated images. Frontiers in Artificial Intelligence, 9, 1844338. doi:10.3389/frai.2026.1844338
  3. J9.Mayanja, I. K., Yun, H., & Bailey, B. N. (2026). Automated calibration of stomatal conductance models from thermal imagery by leveraging synthetic images generated from Helios 3D biophysical model simulations. Journal of Experimental Botany, 77(2), 312–329. doi:10.1093/jxb/eraf420
  4. J8.Ranario, E., Mayanja, I., Yun, H., Bailey, B. N., & Earles, J. M. (2026). Thermal Image Segmentation in Weedy Fields via Synthetic RGB-Trained Models and GAN-Based Cross-Modality Alignment. Plant Phenomics, 100214. doi:10.1016/j.plaphe.2026.100214
  5. J7.Jeon, Y.-J., Kim, H. S., Lee, T. S., Park, S. H., Yun, H., & Jung, D.-H. (2025). Multimodal Optical Biosensing and 3D-CNN Fusion for Phenotyping Physiological Responses of Basil Under Water Deficit Stress. Agronomy, 16(1), 55. doi:10.3390/agronomy16010055
  6. J6.Berlingeri, J., Fuentes, A., Ranario, E., Yun, H., Rim, E. Y., Garrett, O., Howard, A., et al. (2025). Integration of crop modeling and sensing into molecular breeding for nutritional quality and stress tolerance. Theoretical and Applied Genetics, 138(9), 205.
  7. J5.Kim, D.-W., Jeong, S. J., Lee, W. S., Yun, H., Chung, Y. S., Kwon, Y.-S., & Kim, H.-J. (2023). Growth monitoring of field-grown onion and garlic by CIE Lab* color space and region-based crop segmentation of UAV RGB images. Precision Agriculture, 24(5), 1982–2001.
  8. J4.Yun, H., Kim, H. J., Cho, W., Kim, H. S., & Lim, S. J. (2020). Development of an in situ Dead Leaf Weight Monitoring System. Precision Agriculture Science and Technology, 2(3), 181–188. (in Korean) doi:10.12972/pastj.20200022
  9. J3.Kim, D. W., Yun, H. S., Jeong, S. J., Kwon, Y. S., Kim, S. G., Lee, W. S., & Kim, H. J. (2018). Modeling and testing of growth status for Chinese cabbage and white radish with UAV-based RGB imagery. Remote Sensing, 10(4), 563. doi:10.3390/rs10040563
  10. J2.Yun, H. S., Park, S. H., Kim, H. J., Lee, W. S., Lee, K. D., Hong, S. Y., & Jung, G. H. (2016). Use of unmanned aerial vehicle for multi-temporal monitoring of soybean vegetation fraction. Journal of Biosystems Engineering, 41(2), 126–137. (Cover article)
  11. J1.Lee, K. D., Na, S. I., Baek, S. C., Park, K. D., Choi, J. S., Kim, S. J., Kim, H. J., Yun, H. S., & Hong, S. Y. (2015). Estimating the Amount of Nitrogen in Hairy Vetch on Paddy Fields using Unmanned Aerial Vehicle Imagery. Korean Journal of Soil Science and Fertilizer, 48(5), 384–390. (in Korean)

Conference Proceedings

  1. C4.Kamangir, H., Yun, H., & Earles, J. M. (2026). Time, Space, and Modality: Probing Earth Foundation Models for Intra-Field Crop Yield Forecasting. In 2nd Workshop on Representation Learning for Earth Observation (REO2), NeurIPS 2026.
  2. C3.Lundqvist, L., Ranario, E., Kamangir, H., Yun, H., Diepenbrock, C., Bailey, B. N., & Earles, J. M. (2026). Does Your VFM Speak Plant? The Botanical Grammar of Vision Foundation Models for Object Detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, Agriculture-Vision Workshop (pp. 9768–9776).
  3. C2.Ranario, E., Lundqvist, L., Yun, H., Bailey, B. N., & Earles, J. M. (2025). AGILE: A Diffusion-Based Attention-Guided Image and Label Translation for Efficient Cross-Domain Plant Trait Identification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, Agriculture-Vision Workshop (pp. 5392–5401).
  4. C1.Yun, H., Lo, S., Diepenbrock, C. H., Bailey, B. N., & Earles, J. M. (2024). VisTA-SR: Improving the Accuracy and Resolution of Low-Cost Thermal Imaging Cameras for Agriculture. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, Agriculture-Vision Workshop (pp. 5470–5479).

Preprints

  1. P1.Yun, H., Uyehara, I. K., Ranario, E., Lundqvist, L., Diepenbrock, C. H., Bailey, B. N., & Earles, J. M. (2026). Using Vision Language Foundation Models to Generate Plant Simulation Configurations via In-Context Learning. arXiv preprint arXiv:2603.08930.

Patents

  • Kim, H. J., Yun, H. S., Kim, H. S., Park, J. H., & Lim, S. J. Forest fire alarm system based on on-site measurement of fallen leaf water content. Korean Patent 10-1938973 (2019).

Software

Conference Presentations

  1. 10.Yun, H., Uyehara, I. K., Ranario, E., Lundqvist, L., Diepenbrock, C. H., Bailey, B. N., & Earles, J. M. (2026). Plant simulator meets vision language models: Generating plant simulation configurations via in-context learning. ASABE Annual International Meeting, Indianapolis, IN, Paper No. 2600400.
  2. 9.Yun, H., Droutsas, I., Bailey, B. N., Diepenbrock, C., & Earles, M. (2024). Closing the Real2Sim gap between real images and simulation models of cowpea. ASABE Annual International Meeting, Anaheim, CA.
  3. 8.Yun, H., & Earles, M. (2023). Improving low-cost thermal images for estimating traits of cowpea and common beans. ASABE Annual International Meeting, Omaha, NE.
  4. 7.Mayanja, I. K., Yun, H., Earles, M., & Bailey, B. N. (2023). Automated parameterization of stomatal conductance models from thermal imagery by leveraging synthetic images generated from Helios 3D biophysical model simulations. North American Plant Phenotyping Network, West Lafayette, IN.
  5. 6.Kim, D., Jeong, S. J., Yun, H., Kwon, Y. S., & Kim, H. J. (2017). Validation testing of UAV-based vegetable growth estimation models. ASABE Annual International Meeting. doi:10.13031/aim.201701302
  6. 5.Yun, H., Jung, S. J., & Kim, H. J. (2016). Radiometric calibration and vegetation index analysis of upland-crop UAV images. Proceedings of the Korean Society for Agricultural Machinery Conference, 21(1), 129-130.
  7. 4.Yun, H., Kim, H. J., Park, K., Lee, K., & Hong, S. (2015). Use of an UAV for biomass monitoring of hairy vetch. ASABE Annual International Meeting. doi:10.13031/aim.20152183775
  8. 3.Yun, H., Cho, W. J., Jiang, J. S., & Kim, H. J. (2015). Estimation of leaf area, plant height, and fresh weight of lettuce in a plant factory using structure from motion (SfM). Proceedings of the Korean Society for Agricultural Machinery Conference, 20(2), 171-172.
  9. 2.Yun, H. S., Kim, H. J., Lee, K. D., Hong, S. Y., & Park, K. D. (2015). Monitoring hairy vetch growth using UAV images. Proceedings of the Korean Society for Agricultural Machinery Conference, 20(1), 73-74.
  10. 1.Park, S. H., Yun, H. S., Kim, H. J., Lee, K. D., Hong, S. Y., & Jung, G. H. (2014). Multi-temporal visualizing of soybean crop canopy using images from an unmanned aerial vehicle (UAV). Proceedings of the Korean Society for Agricultural Machinery Conference, 19(2), 223.

Teaching

Teaching Assistant, EBS 165 Bioinstrumentation and ControlFall 2025

University of California, Davis

Guest Lecturer, PLS 154 Plant BreedingWinter 2025

University of California, Davis

AI-enabled tools in plant breeding: leaf temperature and angle measurement in a greenhouse (01/30/2025)

Teaching Assistant, 5261.222 DynamicsFall 2015

Seoul National University

Teaching Interests

Agricultural robotics and autonomy, sensors and instrumentation, control systems, machine learning and computer vision for agricultural systems, UAV remote sensing, embedded and edge AI

Mentoring

  • Graduate student advisor, UC Davis undergraduate team (4 students), ASABE Student Robotics Challenge, completed July 2026. The team built an autonomous line-following robot for corn stand counting and selective removal of unhealthy plants.2026

Honors and Awards

  • Teaching Assistant Excellence Award, UC Davis College of Engineering2026
  • 1st Place, AIFS × Sony AI AgTech Challenge2025
  • Research Spotlight Presentation Highlights ($300), 6th AKABFE2024
  • Elegance in Design Prize ($5,000), Farm Robotics Challenge2023
  • Travel Award, 11th SNU CALS Global Challenger2013

Last updated: October 2026