How AI could help scientists track a pest threatening citrus trees
An entomologist used Microsoft’s Discovery app to adapt an AI-driven insect monitoring system to track the Asian citrus psyllid, a pest spreading a devastating citrus disease, compressing weeks of research into days.
The Microsoft Discovery app integrates literature, tools, and data across disciplines to accelerate scientific research, including entomology, neurophysiology, and engineering. An entomologist on the Microsoft Premonition team used the app to synthesize real-world sources and design field experiments aimed at monitoring crop pests, leveraging agentic AI to bridge gaps between disparate scientific domains.
Insects transmit diseases to humans, animals, and crops, with the World Health Organization estimating over 700,000 deaths annually from vector-borne illnesses. The Food and Agriculture Organization reports pests and plant diseases destroy up to 40% of global crop production each year, underscoring the need for rapid, scalable monitoring solutions to protect food security.
The Premonition Biological Weather Station (BWS) uses real-time sensing and edge AI to identify insect species by analyzing flight biomechanics and robotically collect samples to detect pathogens. Traditionally, adapting such systems to new pests required weeks of interdisciplinary collaboration, but the Discovery app compressed this process by automating literature reviews, experimental design, and permitting research.
The app enabled the entomologist to reprogram BWSs for the Asian citrus psyllid (ACP), a vector of Citrus Greening Disease, and design a replicated Latin square field study to test lure configurations. Agentic AI acted as a scientific collaborator, integrating insights from insect ecology, neurophysiology, and olfaction to refine experimental decisions while maintaining human oversight throughout the process.