Smart Sugarcane Health Monitoring Platform with Satellite Remote Sensing and Machine Learning

Sugar-AI is a JCU-led research and translation project developing an AI-enabled crop health monitoring tool for sugarcane. The project uses satellite imagery and machine learning to detect ratoon stunting disease (RSD), a high-impact disease that can spread without obvious visible symptoms and cause major yield losses. By combining multispectral satellite data with field and laboratory reference data, the team is building practical models that can identify disease risk across large farming areas more efficiently than traditional inspection alone.

The work has already shown strong promise in North Queensland, with initial development and validation undertaken in partnership with Herbert Cane Productivity Services and further engagement expanding into the Burdekin and Tully regions. The broader aim is to support earlier intervention, reduce unnecessary testing costs, improve productivity, and provide growers with scalable decision-support tools that fit real farming workflows.

Beyond RSD, Sugar-AI is creating a foundation for wider AI-based surveillance of crop health and biosecurity threats. The project reflects JCU’s strength in translating advanced AI into practical solutions for tropical agriculture, regional industries, and sustainable food production.

Project Team and Collaborators:
Professor Mostafa Rahimi Azghadi and JCU team
Herbert Cane Productivity Services Ltd; growers and collaborators in the Herbert, Burdekin and Tully regions; broader industry engagement with sugar sector partners.

Funding Sources to be Acknowledged:

Australia’s Economic Accelerator (AEA) Seed and Ignite Funding