Cropler launched AI-based PlantPilot that provides hyperlocal field-specific crop recommendations

In an era where vast fields of wheat monitored by drones and weather stations are becoming the norm, a significant amount of environmental data and field images accumulate, often going underutilized. This can result in the underperformance of expensive monitoring equipment, with returns evaporating like morning dew. To address this, Cropler introduces PlantPilot, an AI assistant designed to transform raw data into actionable agronomic insights by providing field-specific recommendations.

PlantPilot differentiates itself from standard AI services by tailoring its advice to the unique characteristics of each field, including microclimate, soil composition, and growth patterns. This is not just another chatbot. PlantPilot’s advice ranges from selecting the next season’s crops to identifying diseases and recommending specific treatments like fungicides for crops such as blueberries.

The service’s capability extends beyond basic agronomic guidelines, incorporating real-time and historical data from specific locations and Cropler’s web platform. It monitors a range of factors:

• Current and regional weather patterns
• GPS location data to gauge regional specifics
• Phenological stages through agri-cameras
• Crop health status and NDVI imaging history
• Field scoring data, crop rotation, and key agricultural dates

This wealth of regional and personalized information eliminates the need for repetitive data entry, allowing farmers to inquire about their current concerns. PlantPilot is already knowledgeable of all necessary contexts.

Moreover, PlantPilot stands out by integrating local hardware and language models to provide context-aware recommendations. It combines the visual capabilities of drones with the analytical intelligence of AI to offer precise advice on field-specific conditions, such as recommending the proper fungicide for a specific wheat type in Poland based on real-time conditions and regional disease pressures.

PlantPilot’s approach is applicable to various crops and regions, from corn in Chile to strawberries in Ukraine. By integrating verified local information with specific data from each field, PlantPilot provides tailored advice that considers unique agricultural challenges and best practices.

Initial tests of PlantPilot indicate a 90% accuracy rate for region-specific recommendations. With ongoing advancements in AI and language models, its capabilities are expected to be further enhanced. A beta version will soon be available to Cropler subscribers, offering a valuable tool for farmers, agronomists, and agricultural researchers.