Hyperspectral imaging coupled with Dual-channel convolutional neural network for early detection of apple valsa canker

Assessing the status of apple tree for orchard precision management is critical. However, apple valsa canker severely restricts apple production and quality in China, especially symptomless branches skin at the pathogen early infection stage increases the difficulty for rapid and high throughput disease detection in orchards. Hyperspectral imaging (HSI) is a promising sensing technique widely implemented for plant disease detection. While exploring efficient methods for HSI analysis remains challenging due to the high dimensionality, information redundancy, and noise interference. This study aims to establish a dual-channel convolutional neural network (DC-CNN) model (integration of 3D-CNN and 1D-CNN) based on spectral and spatial information for detecting apple branches infected by apple valsa canker at an early stage. DC-CNN models were established based on different spectral pre-processing algorithms. The gradient-weighted class activation mapping (Grad-CAM) algorithm with constructed saliency maps and gradient histograms were used to explain the classification mechanism of the models visually. The results demonstrated that the DC-CNN model based on the images and spectra after multiple scattering correction (MSC) pretreatment had the best performance, with an accuracy of 98% for early detection of apple valsa canker. This study confirmed the feasibility of HSI coupled with DC-CNN in the early detection of apple valsa canker. Furthermore, the visual explanation helped improve the DC-CNN model’s explanatory and availability.