Digital Phenotyping of Crop Health in Manajipet's Agricultural Fields: A Computer Vision and Material Science-Informed Approach for Early Pest/Disease Detection and Bio-Pesticide Recommendation

Bine Rithika (Lead Researcher): Timely detection of crop stress is vital for global food security. This study introduces an integrated Digital Phenotyping (DP) and Material Science framework to enhance early pest/disease detection and bio-pesticide efficacy in the Manajipet agricultural fields. We employed a Deep Learning model (YOLOv7) on multispectral imagery, achieving a high mean Average Precision (93.5%) for stress identification.