Recipient Organization
COLORADO STATE UNIVERSITY
(N/A)
FORT COLLINS,CO 80523
Performing Department
(N/A)
Non Technical Summary
(N/A)
Animal Health Component
20%
Research Effort Categories
Basic
80%
Applied
20%
Developmental
0%
Goals / Objectives
Breeding crops with improved abiotic stress tolerance, disease resistance, and yield is critical for the long term resilience of modern American agriculture. Unoccupied aerial vehicle (UAV) based hyperspectral remote sensing is a powerful tool for plant phenotyping, including for early detection of disease and crop resistance rating at fine spatial and temporal scales to improve breeding efforts. This approach is particularly effective for phenotyping below-ground diseases in root crops like Rhizoctonia Root and Crown Rot of sugar beet, as hyperspectral imaging can detect above-ground signatures of stress that are not visible with the human eye. The integration of UAVs and machine learning provides precise and real-time disease management, reducing diagnostic cost, and increasing throughput compared to laboratory methods. This project will evaluate the capability of UAV-based hyperspectral imaging and machine learning in detecting and characterizing Rhizoctonia infection in sugar beet, with the long term goal of developing a validated hyperspectral phenotyping pipeline to accelerate disease resistance trait discovery and breeding in sugar beet.
Project Methods
To develop a hyperspectral phenotyping pipeline for Rhizoctonia Root and Crown Rot in sugar beet, the cooperator will 1) Test and identify spectral indices derived from hyperspectral imaging to detect and rate Rhizoctonia disease response in sugar beet and beet wild relatives; 2) Develop analytic pipelines for high throughput hyperspectral imaging and rating of beets and wild beets in field conditions; 3) Identify and examine the variation in biophysical and biochemical functional traits that play the major role in sugar beet response to the diseases.