M.S. Level Student
Southern Illinois University Carbondale
Advised by Dr. Ruopu Li
Detection of Soybean SCN Infection Using Multi-Scale Remote Sensing
This study focuses on the early detection of Soybean Cyst Nematode (SCN) using multi-scale remote sensing techniques. Recognizing the significant impact of SCN on soybean yield and the limitations of traditional detection methods, this research aims to develop a more efficient, accurate, and real-time detection system. The study employs a blend of close-range (ground-based) hyperspectral, mid-range (UAV imaging), and far-range (satellite imaging) remote sensing methods to detect SCN infestations in soybean fields. Through the integration of various spectral bands, vegetation indices, and machine learning algorithms, the research seeks to identify early-stage SCN disturbances in soybean phenology. This comprehensive approach, which includes a detailed analysis of both spatial distribution and temporal evolution of SCN infestation, has the potential to significantly improve the early detection and management of SCN in soybeans, contributing to more sustainable and resilient soybean production. The study is a crucial step towards advancing agricultural remote sensing applications and offers promising insights into precision agriculture and pest management strategies.