Agricultural and Life Sciences (IFAS)
Schumann Lab
Led by Arnold Schumann · Soil, Water, and Ecosystem Sciences
What we study
The Schumann Lab studies soil and water management in citrus groves, focusing on precision agriculture to improve nitrogen and water use efficiency. They use field experiments, sensors, and modeling to address yield variability and environmental protection.
What working here is like
- Computational
- Plants
- Coding helps
- Projects
- 3
- Papers
- 5
Current projects
Nitrogen Best Management Practice for citrus trees
Research on nitrogen use efficiency in citrus to improve yield and quality.
Variable rate granular fertilization of citrus groves
Testing fertilizer spreaders for single-tree prescription zones.
Show 1 more projectsShow fewer
Estimation of citrus fruit yield using ultrasonically-sensed tree size
Tests whether ultrasonic sensors that measure the size of citrus trees can be used to estimate how much fruit a tree will produce.
Summaries are written by AI in plain language from public symposium abstracts and may be imperfect.
Recent papers, explained
- Improving Watermelon Disease Classification with Stable Diffusion-Generated Images and EfficientNetV2-L-Based Architecture
2026 · AgriEngineering
Tests if AI-generated images can help classify watermelon diseases.
- Advancing site-specific disease and pest management in precision agriculture: From reasoning-driven foundation models to adaptive, feedback-based learning
2026 · Computers and Electronics in Agriculture
Explores how foundation models can improve crop disease detection.
Show 3 more papersShow fewer
- Zero-shot crop segmentation via 3D depth-aware vision pipeline using unsupervised clustering
2026 · Artificial Intelligence in Agriculture
Creates an AI tool to segment crops without needing labeled images.
- Proximal sensing pipeline for field-scale mapping of individual weeds using low-cost components and YOLO object detection
2026 · Smart Agricultural Technology
Develops a system to map weeds in fields using cameras and AI.
- Potato crop coefficient (Kc) prediction based on encoder-decoder graph learning model
2026 · Journal of Agriculture and Food Research
Uses a graph learning model to predict potato crop water use in Canada.
Plain-language summaries are AI-written and reviewed by us; check the paper for details.
How to reach out
Arnold Schumann hasn't set up this page yet. You can also look them up in the UF directory (search “Arnold Schumann”).