Generalized Linear Model with Elastic Net Regularization and Convolutional Neural Network for Evaluating Aphanomyces Root Rot Severity in Lentil

Abstract

Phenomics technologies allow quantitative assessment of phenotypes across a larger number of plant genotypes compared to traditional phenotyping approaches. The utilization of such technologies has enabled the generation of multidimensional plant traits creating big datasets. However, to harness the power of phenomics technologies, more sophisticated data analysis methods are required. In this study, Aphanomyces root rot (ARR) resistance in 547 lentil accessions and lines was evaluated using Red-Green-Blue (RGB) images of roots. We created a dataset of 6,460 root images that were annotated by a plant breeder based on the disease severity. Two approaches, generalized linear model with elastic net regularization (EN) and convolutional neural network (CNN), were developed to classify disease resistance categories into three classes: resistant, partially resistant, and susceptible. The results indicated that the selected image features using EN models were able to classify three disease categories with an accuracy of up to 0.91±0.004 (0.96±0.005 resistant, 0.82±0.009 partially resistant, and 0.92±0.007 susceptible) compared to CNN with an accuracy of about 0.84±0.009 (0.96±0.008 resistant, 0.68±0.026 partially resistant, and 0.83±0.015 susceptible). The resistant class was accurately detected using both classification methods. However, partially resistant class was challenging to detect as the features (data) of the partially resistant class often overlapped with those of resistant and susceptible classes. Collectively, the findings provided insights on the use of phenomics techniques and machine learning approaches to provide quantitative measures of ARR resistance in lentil.

Evaluation of Effective Class-Balancing Techniques for CNN-Based Assessment of Aphanomyces Root Rot Resistance in Pea (Pisum sativum L.)

“…Thus, it should be noted that the significance of selecting the effective class balancing technique would depend on the characteristics of the dataset, deep learning model, and the optimization techniques adopted. Previously, Marzougui et al [ 39 ] adopted a CNN-based model and machine learning algorithms of selected image features to evaluate the severity of ARR infection in lentils. The generalized linear regression model resulted in an accuracy of up to 91% for classification of three disease severity classes.…”

“…A digital camera with 16-MB (Canon ® PowerShot SX530 HS, Irving, TX, United States) was used to collect image data of 4608 × 3456 pixels at 50 cm above the samples. A fluorescent light source was used to illuminate the object of interest (400–700 nm), and the set-up was similar to those described in Marzougui et al [ 38 , 39 ]. The original data captured images of six plants together in a single shot with an image resolution of 0.17 mm/pixel.…”

Internet of Things‐based root disease classification in alfalfa plants using hybrid optimization‐enabled deep convolutional neural network

“…The performance improvement of proposed approach is analyzed with the existing techniques, like partition aware-RPL (PA-RPL) + deep learning, 9,31 Energy-efficient geographic (EEG) routing + CNN, 17,32 hybrid routing + Canny and Ostu based segmentation, 18,33 and priority-based and energy efficient routing (PriNergy) + ANN. 20,34…”

Analysis of RGB Plant Images to Identify Root Rot Disease in Korean Ginseng Plants Using Deep Learning

“…The root rot disease has been identified from the plant leaves using hyperspectral leaf images and machine learning techniques [25]. The root images are analyzed using feature extraction methods [29] and deep learning techniques [30] to find the root rot disease in Lentil. In order to obtain the root images, the plants are removed from the pots and the root images are captured.…”