The CitrusGuard-CIN initiative establishes an AI-powered detection and response network designed to help citrus industry mitigate the persistent threat of Huanglongbing (HLB, or citrus greening) and other emerging plant health challenges. The project leverages state-of-the-art remote sensing, machine learning, and agronomic data science to enable earlier, data-driven detection of disease and stress in citrus groves. By integrating unmanned aerial vehicle (UAV) multispectral imagery, soil IoT sensor data, and advanced neural network models (CNN, LSTM), CitrusGuard-CIN will deliver a scalable decision-support system capable of identifying early stress indicators months before visual symptoms appear.

This 36-month effort (April 2026 – March 2029) brings together our team with the Florida Citrus Research and Development Foundation (FCRDF), USDA ARS Fort Pierce Laboratory, UF IFAS Extension, and the Florida Department of Agriculture and Consumer Services (FDACS). Together, these partners will build a comprehensive, FAIR-compliant data workflow for citrus health monitoring that integrates seamlessly with USDA Climate Hubs and the AI Institute for Agricultural Resilience (AIIRA).

The project’s specific objectives are to:

1. Develop an open, standardized dataset of UAV- and IoT-based citrus health indicators;

2. Create and validate AI models for early HLB stress detection and classification;

3. Demonstrate system performance across multiple Florida counties; and

4. Provide growers with accessible digital dashboards, training materials, and best-practice guides.

 

Expected outcomes include a public repository of disease detection datasets and AI models, improved situational awareness for growers and extension specialists, and stronger cross-agency coordination for citrus disease resilience. The long-term impact will be a replicable, data-driven infrastructure for precision agriculture, enhancing productivity, reducing economic losses, and supporting the sustainability specialty crops under increasing climatic stress.