AgriTrack framework for AI-based tracking of pest migration through farmers' helpline data

Area of Science:

• Agricultural Science
• Data Science
• Artificial Intelligence

Background:

• Large-scale pest and disease tracking is crucial for precision agriculture.
• Traditional manual methods are costly, time-consuming, and impractical for extensive studies.
• A scalable, data-driven solution is needed to overcome these limitations.

Purpose of the Study:

• Introduce AgriTrack, a framework for tracking pest/disease movement and predicting farmer information needs.
• Leverage extensive farmer query data for advanced spatio-temporal analysis.
• Provide actionable insights for agricultural stakeholders through a data-driven approach.

Main Methods:

• Utilized fourteen years of
• Kisan Call Centre
• data (over 36 million farmer queries).
• Implemented AI for intra-seasonal and inter-seasonal spatial movement tracking.
• Employed Deep Learning for forecasting farmer information demand.

Main Results:

• Demonstrated AI-based spatio-temporal tracking of pest movements.
• Successfully predicted shifts in critical dates and farmer information demand.
• Validated the framework's efficacy through a case study on Termite pests in Wheat crops.

Conclusions:

• AgriTrack provides a scalable, data-driven solution for pest and disease monitoring.
• The framework reduces the time and resources needed for manual monitoring.
• AgriTrack offers actionable insights for proactive agricultural management.