A deep convolutional neural network-based wavelength selection method for spectral characteristics of rice blast disease

Abstract

Characteristic wavelength selection is a research hotspot in hyperspectral data processing and a key to improving the accuracy of identifying the degree of rice blast infection. This study combines deep learning and visualization techniques to create a wavelength selection method for spectral features of rice blast. A deep convolutional neural (DCNN) structure was designed by combining the convolutional block attention module (CBAM) with residual network (ResNet) to learn different classes of disease features. And the guided grade-weighted heatmap (Guided-GradHM) of the last layer of convolution was obtained using the guided gradient-weighted class activation mapping (Guided-GradCAM) method. Then the spectral characteristic wavelengths were selected based on the average Guided-GradHM of different disease levels. Finally, statistical analysis (JM distance, within-class scatter) and comparative modeling analysis were used to verify the method's validity in this study. The results show that the characteristic wavelengths selected by the Guided-GradCAM method based on the ResNet-CBAM network structure have good inter-class separability and intra-class aggregation, with JM distance greater than 1.9 and within-class scatter less than 0.4. Meanwhile, the random forest (RF) and support vector machine (SVM) models constructed from the spectral characteristic wavelengths selected by the Guided-GradCAM method achieved the best disease level classification accuracy, with overall accuracy (OA) and Kappa of 97.21% and 96.55%, 96.51%, and 95.69%, respectively. Overall, this research method can more accurately select the spectral characteristic wavelengths of different disease levels of rice blast and can provide a more effective method for accurate identification and timely control of the disease.