Abstract
Abstract With the rapid development of precision agriculture, the integration of drone imagery and yield sensor data has become a key technology for enhancing agricultural productivity. As an advanced deep learning model, the cross-modal Transformer demonstrates significant application potential in precision agriculture due to its powerful feature extraction and fusion capabilities. This study explores the application of cross-modal Transformer in integrating drone imagery and yield sensor data for precision agriculture. By constructing an efficient fusion model, this technology achieves deep integration and precise analysis of multi-source data, thereby providing scientific decision-making support for agricultural production.