In-field classification of the asymptomatic biotrophic phase of potato late blight based on deep learning and proximal hyperspectral imaging

• Published in: Computers and electronics in agriculture Vol. 205; p. 107585
• Main Authors: Qi, Chao, Sandroni, Murilo, Cairo Westergaard, Jesper, Høegh Riis Sundmark, Ea, Bagge, Merethe, Alexandersson, Erik, Gao, Junfeng
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.02.2023
• Subjects: Agricultural Science; Asymptomatic biotrophic phase; Attention networks; Convolutional neural networks; Jordbruksvetenskap; Plant phenotyping; Wavelength selection; Asymptomatic biotrophic phase; Attention networks; Plant phenotyping; Convolutional neural networks; Wavelength selection
• DOI: 10.1016/j.compag.2022.107585
• ISSN: 0168-1699; 1872-7107

•In-field classification of the asymptomatic biotrophic phase of potato late blight.•Proximal hyperspectral images collected in multiple days with 20 potato genotypes.•A new 3D convolutional deep learning architecture PLB-2D-3D-A is proposed.•Important wavelengths are determined for early PLB disease recognition in fields. Effective detection of potato late blight (PLB) is an essential aspect of potato cultivation. However, it is a challenge to detect late blight in asymptomatic biotrophic phase in fields with conventional imaging approaches because of the lack of visual symptoms in the canopy. Hyperspectral imaging can capture spectral signals from a wide range of wavelengths also outside the visual wavelengths. Here, we propose a deep learning classification architecture for hyperspectral images by combining 2D convolutional neural network (2D-CNN) and 3D-CNN with deep cooperative attention networks (PLB-2D-3D-A). First, 2D-CNN and 3D-CNN are used to extract rich spectral space features, and then the attention mechanism AttentionBlock and SE-ResNet are used to emphasize the salient features in the feature maps and increase the generalization ability of the model. The dataset is built with 15,360 images (64x64x204), cropped from 240 raw images captured in an experimental field with over 20 potato genotypes. The accuracy in the test dataset of 2000 images reached 0.739 in the full band and 0.790 in the specific bands (492 nm, 519 nm, 560 nm, 592 nm, 717 nm and 765 nm). This study shows an encouraging result for classification of the asymptomatic biotrophic phase of PLB disease with deep learning and proximal hyperspectral imaging.