AGROBOOST: AN AUTONOMOUS AGRICULTURAL INTELLIGENCE SYSTEM INTEGRATING SATELLITE IMAGERY, UNMANNED AERIAL VEHICLES, AND MACHINE LEARNING FOR EARLY CROP STRESS DETECTION
Keywords:
precision agriculture; unmanned aerial vehicles; satellite remote sensing; computer vision; machine learning; crop stress detection; NDVI; smart farmingAbstract
Undetected crop stress remains one of the principal causes of preventable agricultural loss worldwide, with the Food and Agriculture Organization (FAO) estimating that up to twenty percent of global crop yield is lost to conditions — water stress, plant disease, pest infestation, and nutrient deficiency — that could have been mitigated through earlier intervention. Existing monitoring approaches rely either on satellite remote sensing, which offers wide-area coverage but suffers from low revisit frequency (three to five days) and coarse spatial resolution (ten to thirty meters), or on manual field inspection, which is accurate but slow, costly, and difficult to scale.
This paper presents AgroBoost, an autonomous agricultural intelligence system that fuses satellite imagery, autonomous drone-based aerial inspection, and machine-learning-driven computer vision into a single continuous monitoring pipeline. The system identifies candidate problem zones from large-scale satellite scans, dispatches an autonomous drone for high-resolution close-range imaging of flagged areas, applies a trained detection model to classify disease, pest, and water-stress signatures, and delivers localized, actionable recommendations to farmers through a real-time dashboard. We describe the system architecture, the hardware and software stack, and a working prototype, and we discuss the system's potential agronomic, economic, and environmental impact relative to existing single-source monitoring approaches.
References
1.Food and Agriculture Organization of the United Nations (FAO). The State of Food and Agriculture 2023. Rome: FAO, 2023.
2.Jocher, G., Chaurasia, A., Qiu, J. Ultralytics YOLOv8. Ultralytics, 2023.
3.Bradski, G. The OpenCV Library. Dr. Dobb's Journal of Software Tools, 2000.
4.European Space Agency (ESA). Sentinel-2 User Handbook. ESA Standard Document, 2015.
5.Meier, L., Honegger, D., Pollefeys, M. PX4: A Node-Based Multithreaded Open Source Robotics Framework for Deeply Embedded Platforms. IEEE International Conference on Robotics and Automation (ICRA), 2015.
6.Mulla, D. J. Twenty-Five Years of Remote Sensing in Precision Agriculture: Key Advances and Remaining Knowledge Gaps. Biosystems Engineering, 114(4), 358–371, 2013.