Real-Time Detection of Rice Bacterial Blight using Remote Sensing and Deep Learning

This research introduces an innovative method for the real-time identification of bacterial blight in rice crops via remote sensing and deep learning (DL) technologies. Bacterial blight represents a significant threat to rice production, requiring quick detection for efficient control. To address this challenge, remote sensing data from drones and satellites is analyzed to detect visual signs connected to the diseases. A convolutional neural network (CNN) model is used to classify and identify sick rice plants using high-resolution images. The results demonstrate that the model attained an accurate rate of 98.2%, significantly enhancing the speed and precision of illness identification relative to conventional approaches. The combination of advanced DL algorithms with remote sensing technologies enables quick responses and improves sustainable agriculture practices. It illustrates the capability of using technology for crop monitoring, enhancing food security, and optimizing resource management in agriculture.