Field Crop 2025, Vol.8, No.4, 204-212 http://cropscipublisher.com/index.php/fc 209 different multispectral cameras of drones and found that indices such as NDVI and VARI could well track growth at different reproductive stages, and the method was economical and efficient (Dimyati et al., 2023). In Southeast Asia, RGB images are also used for early detection and yield estimation, helping farmers take management measures in a timely manner (Sari et al., 2021; Luu et al., 2023). 6.3 Deep learning-based monitoring of rice diseases and precision management practices The combination of deep learning and unmanned aerial vehicle (UAV) images has brought new methods to the monitoring and precise management of rice diseases. For instance, deep neural networks can extract features from images to identify nutritional deficiencies and guide fertilization. This method has high monitoring accuracy and can also help improve rice growth (Chen et al., 2025). Unmanned aerial vehicle (UAV) monitoring is often combined with multispectral imaging and spatial analysis to map the distribution of pests such as bacterial wilt and stem borer, facilitating zonal management and precise control (Kharim et al., 2022). In addition, deep convolutional neural networks have also been used to analyze drought responses and changes in disease symptoms, providing support for genetic research and the breeding of stress-resistant rice varieties (Jiang et al., 2021). 7 Conclusion and Prospect Unmanned aerial vehicle (UAV) remote sensing technology can quickly and non-destructively monitor the growth, nutrient status, water pressure and diseases of rice. It can provide high-resolution images at the centimeter level and also collect data flexibly and promptly. This makes up for the deficiencies of traditional investigations and satellite images. Traditional methods are often time-consuming, labor-intensive, sometimes destructive and easily affected by the weather. Monitoring with drones can better achieve precise fertilization and irrigation, detect pests and diseases early, and predict yields. This can not only enhance the efficiency of resource utilization and reduce input costs, but also make rice production more sustainable. If the data from drones is combined with ground sensors (such as Internet of Things weather stations) and satellite data, multi-scale and multi-source monitoring can be achieved. Drones have higher spatial and temporal accuracy in field management, while satellites can cover larger areas. Through data fusion (such as scale transformation or machine learning methods), leaf area index (LAI) and yield can be estimated more accurately, and field details can also be retained during large-scale monitoring. This approach is conducive to dynamic decision-making and better integrates plot management with regional agricultural policies. In the future, the development direction of rice agriculture will be to integrate unmanned aerial vehicle remote sensing, machine learning and digital agriculture platforms to establish an intelligent monitoring and decision-making system. With the development of artificial intelligence, big data and cloud computing, these systems will become increasingly easy to use. They can assess crop health in real time, monitor diseases and also manage crops in different zones. This not only enhances the level of precision agriculture, but also reduces labor and costs, and promotes intensive and sustainable production. The current focus of research is to extend the endurance of unmanned aerial vehicles, enhance the sensor carrying capacity and data processing efficiency. At the same time, more stable and scalable models should be developed to enable them to adapt to different environments. Acknowledgments We would like to express our gratitude to the reviewers for their valuable feedback, which helped improve the manuscript. Conflict of Interest Disclosure The authors affirm that this research was conducted without any commercial or financial relationships that could be construed as a potential conflict of interest. References Ban S., Liu W., Tian M., Wang Q., Yuan T., Chang Q., and Li L., 2022, Rice leaf chlorophyll content estimation using UAV-based spectral images in different regions, Agronomy, 12(11): 2832. https://doi.org/10.3390/agronomy12112832
RkJQdWJsaXNoZXIy MjQ4ODYzNA==