Collaborative Research: AI-ENGAGE: HARVEST: Holistic AI-powered Agricultural Response Validation and Early Prediction System across Territories

Missouri University Of Science And Technology, Rolla MO

Investigators

Abstract

This project investigates smart farming technologies that use artificial intelligence (AI) to help farmers protect crops, use resources more efficiently, and reduce reliance on chemicals. Typically, farmers lose 20–40% of their harvest each year to pests, diseases, and water or nutrient shortages. By providing early warnings and real-time advice, the HARVEST project enables farmers to respond to these threats and avoid significant losses. By combining sensors, drones, mobile robots, and user-friendly web portals, the proposed approach guides farmers on how to apply water, fertilizer, and pesticides more precisely, thus increasing yields and reducing waste. An international collaboration across the United States, India, Japan, and Australia ensures the developed tools are tested in diverse environments and adapted to support small and medium-scale farms. This project accelerates global food security and fosters workforce development through student training in interdisciplinary AI and digital agriculture. The HARVEST project aims to develop an AI-driven system that addresses important challenges in agricultural production (specifically corn and rice), such as pest outbreaks, crop diseases, nutrient deficiencies, and water stress through three core innovations. First, an early-warning module merges rapid disease tests with image-based analysis to detect pests at their onset. Second, a Digital Twin platform creates a virtual model of each farm, enabling farmers to simulate management strategies without risking real-world impacts on their fields. Third, a multimodal generative AI framework learns from data collected in one region and adapts insights for use in other regions while preserving data privacy of each farm. The HARVEST system collects data through in-field sensors, robotic vehicles, and drones; processes this information using advanced machine learning algorithms; and delivers actionable recommendations via mobile applications. By validating the developed solutions across four countries, the project develops practical tools to enhance crop yields, improve farmer incomes, and strengthen agricultural economic prosperity. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.