Developing and Evaluating High-Resolution Satellite Imagery and an AI-Driven Web-Based Decision Tool for Precision Agriculture and Environment Management
Faculty Mentor Information
Dr. Johnny Li, University of Idaho
Presentation Date
7-16-2026
Abstract
This project develops an AI-driven web-based decision support tool for precision agriculture by integrating satellite imagery, geospatial analysis, and environmental data to support field-level crop management. The system uses high-resolution PlanetScope SuperDove satellite imagery together with GeoJSON field boundaries to analyze agricultural fields and provide actionable insights. A web application has been developed using React for the frontend and Django REST Framework for the backend, allowing users to upload field boundaries, visualize fields on an interactive map, and store field information in a database. The system automatically calculates field geometry, retrieves real-time weather information through the Open-Meteo API, and processes PlanetScope imagery to compute vegetation indices such as the Normalized Difference Vegetation Index (NDVI) for assessing crop health. Current decision support features include basic irrigation recommendations, crop suggestions, and vegetation health assessment based on weather and satellite-derived information. Future work will expand the system by incorporating additional vegetation indices, soil datasets, and machine learning models to detect crop stress, improve agricultural recommendations, and support precision agriculture at the University of Idaho's Center for Agriculture, Food and Environment (CAFÉ) Research Farm.
Developing and Evaluating High-Resolution Satellite Imagery and an AI-Driven Web-Based Decision Tool for Precision Agriculture and Environment Management
This project develops an AI-driven web-based decision support tool for precision agriculture by integrating satellite imagery, geospatial analysis, and environmental data to support field-level crop management. The system uses high-resolution PlanetScope SuperDove satellite imagery together with GeoJSON field boundaries to analyze agricultural fields and provide actionable insights. A web application has been developed using React for the frontend and Django REST Framework for the backend, allowing users to upload field boundaries, visualize fields on an interactive map, and store field information in a database. The system automatically calculates field geometry, retrieves real-time weather information through the Open-Meteo API, and processes PlanetScope imagery to compute vegetation indices such as the Normalized Difference Vegetation Index (NDVI) for assessing crop health. Current decision support features include basic irrigation recommendations, crop suggestions, and vegetation health assessment based on weather and satellite-derived information. Future work will expand the system by incorporating additional vegetation indices, soil datasets, and machine learning models to detect crop stress, improve agricultural recommendations, and support precision agriculture at the University of Idaho's Center for Agriculture, Food and Environment (CAFÉ) Research Farm.