Plant disease identification using explainable 3D deep learning on hyperspectral images

Abstract

Background Hyperspectral imaging is emerging as a promising approach for plant disease identification. The large and possibly redundant information contained in hyperspectral data cubes makes deep learning based identification of plant diseases a natural fit. Here, we deploy a novel 3D deep convolutional neural network (DCNN) that directly assimilates the hyperspectral data. Furthermore, we interrogate the learnt model to produce physiologically meaningful explanations. We focus on an economically important disease, charcoal rot, which is a soil borne fungal disease that affects the yield of soybean crops worldwide. Results Based on hyperspectral imaging of inoculated and mock-inoculated stem images, our 3D DCNN has a classification accuracy of 95.73% and an infected class F1 score of 0.87. Using the concept of a saliency map, we visualize the most sensitive pixel locations, and show that the spatial regions with visible disease symptoms are overwhelmingly chosen by the model for classification. We also find that the most sensitive wavelengths used by the model for classification are in the near infrared region (NIR), which is also the commonly used spectral range for determining the vegetative health of a plant. Conclusion The use of an explainable deep learning model not only provides high accuracy, but also provides physiological insight into model predictions, thus generating confidence in model predictions. These explained predictions lend themselves for eventual use in precision agriculture and research application using automated phenotyping platforms.

From visual estimates to fully automated sensor-based measurements of plant disease severity: status and challenges for improving accuracy

“…As with RGB images, CNNs show great potential as a component of deep learning. Nagasubramanian et al (2017Nagasubramanian et al ( , 2019) applied a 3D CNN for detection of charcoal rot on soybean using closerange VIS-NIR hyperspectral images and achieved a detection accuracy of 97% and was able to predict lesion length on most stems. However, these technologies demand substantial training data.…”

Machine learning for high-throughput field phenotyping and image processing provides insight into the association of above and below-ground traits in cassava (Manihot esculenta Crantz)

“…For the pre-processing, data scaling between -1 and 1 and a Box Cox transformation were performed to achieve a normal distribution [46]. Principal component analysis (PCA) and principal component regression (PCR) [47] was applied to compare performance and reduce the model complexity providing a lower-dimensional representation of predictor variables and to avoid multi-collinearity between predictors [48][49][50]. To analyze the data at different growth stages, a multi-temporal VIs technique was applied [27]; this procedure increases the predictor variables from 77 to 693 per timing point accumulating the VIs value per phenological stage.…”

Plant Diseases Recognition from Digital Images using Multichannel Convolutional Neural Networks

“…In the case of soybeans, one of the main legumes of industrial interest, it was possible to identify only studies S7, S81, and S84. Highlighted is the approach proposed by [41] in study S7 that creates an architecture called 3D-CNN that can be used to extract features jointly across the spatial and spectral dimension for classification of a 3D hyperspectral data. The authors demonstrated that a 3D CNN model could be used effectively to learn from hyperspectral data to identify charcoal rot disease in soybean stems.…”