TY - JOUR

T1 - In-field classification of the asymptomatic biotrophic phase of potato late blight based on deep learning and proximal hyperspectral imaging

AU - Qi, Chao

AU - Sandroni, Murilo

AU - Cairo Westergaard, Jesper

AU - Høegh Riis Sundmark, Ea

AU - Bagge, Merethe

AU - Alexandersson, Erik

AU - Gao, Junfeng

N1 - Publisher Copyright: © 2022 The Author(s)

PY - 2023

Y1 - 2023

N2 - 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.

AB - 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.

KW - Asymptomatic biotrophic phase

KW - Attention networks

KW - Convolutional neural networks

KW - Plant phenotyping

KW - Wavelength selection

U2 - 10.1016/j.compag.2022.107585

DO - 10.1016/j.compag.2022.107585

M3 - Journal article

AN - SCOPUS:85145259687

VL - 205

JO - Computers and Electronics in Agriculture

JF - Computers and Electronics in Agriculture

SN - 0168-1699

M1 - 107585

ER -