Abstract: Mosquito control programs depend on accurate, timely field data, yet most districts continue to face fragmented systems and duplicated effort. Trap data, treatments, and technician observations often reside in separate silos, making it difficult to connect what is observed in the field with the actions that follow. Digital tools have replaced paper in many operations, but the deeper challenge remains: transforming field information into operational intelligence.
Nidus was developed to address this need. It is a field-first system that unifies notes, locations, and time into a living operational record of mosquito activity and control work. By embedding spatial and temporal context directly into every observation, Nidus helps technicians and managers identify patterns, trace outcomes, and focus attention where it matters most. The platform incorporates adaptive inference and lightweight artificial intelligence methods that learn from user input and environmental context, progressively improving its ability to suggest priorities and detect meaningful patterns in field data.
This presentation will introduce Nidus, highlight results from its deployment in daily operations at Delta Mosquito and Vector Control District, and discuss how early applications of AI can augment human expertise in vector control. The presentation will also outline opportunities for collaboration among agencies and researchers interested in building practical, transparent, and field-driven AI systems to support the next generation of mosquito control operations.
