Machine learning and remote sensing for precision agriculture: Progresses and challenges

Precision agriculture, as a critical approach to addressing global food security and sustainable resource utilization, necessitates precise monitoring and intelligent management throughout the entire agricultural lifecycle. The integration of remote sensing technology and machine learning serves as a cornerstone for advancing precision agriculture. This paper explores the prospects of applying machine learning and remote sensing technologies in precision agriculture, focusing on recent advancements in crop monitoring, soil health assessment, pest and disease detection, agricultural disaster prediction, and resource optimization management. Furthermore, the paper highlights existing challenges, including the complexity of data processing, the generalization capabilities of models, and the barriers to widespread acceptance of agricultural technology. Future research should emphasize enhancing model performance, automating data annotation, and facilitating the practical implementation of these technologies to foster sustainable agriculture. The advancement of precision agriculture will hinge on the deep integration of machine learning and remote sensing technologies, enabling agricultural production to progress toward greater intelligence, operational efficiency, and sustainability.