Development of Spectral Features for Monitoring Rice Bacterial Leaf Blight Disease Using Broad-Band Remote Sensing Systems

As an important rice disease, rice bacterial leaf blight (RBLB, caused by the bacterium Xanthomonas oryzae pv. oryzae), has become widespread in east China in recent years. Significant losses in rice yield occurred as a result of the disease’s epidemic, making it imperative to monitor RBLB at a large scale. With the development of remote sensing technology, the broad-band sensors equipped with red-edge channels over multiple spatial resolutions offer numerous available data for large-scale monitoring of rice diseases. However, RBLB is characterized by rapid dispersal under suitable conditions, making it difficult to track the disease at a regional scale with a single sensor in practice. Therefore, it is necessary to identify or construct features that are effective across different sensors for monitoring RBLB. To achieve this goal, the spectral response of RBLB was first analyzed based on the canopy hyperspectral data. Using the relative spectral response (RSR) functions of four representative satellite or UAV sensors (i.e., Sentinel-2, GF-6, Planet, and Rededge-M) and the hyperspectral data, the corresponding broad-band spectral data was simulated. According to a thorough band combination and sensitivity analysis, two novel spectral indices for monitoring RBLB that can be effective across multiple sensors (i.e., RBBRI and RBBDI) were developed. An optimal feature set that includes the two novel indices and a classical vegetation index was formed. The capability of such a feature set in monitoring RBLB was assessed via FLDA and SVM algorithms. The result demonstrated that both constructed novel indices exhibited high sensitivity to the disease across multiple sensors. Meanwhile, the feature set yielded an overall accuracy above 90% for all sensors, which indicates its cross-sensor generality in monitoring RBLB. The outcome of this research permits disease monitoring with different remote sensing data over a large scale.