Deep learning based assessment of disease severity for early blight in tomato crop

Smart breeding approaches in post-genomics era for developing climate-resilient food crops

“…Furthermore, ML based digital image have been successfully employed for assessment of diseases in crop plants. Such examples include the detection of bacterial blight disease incidence in rice (Lu et al, 2017), maize (Dechant et al, 2017), soybean (Ghosal et al, 2018), and tomato (Prabhakar et al, 2020). Similarly, digital imaging with python based ML programs was employed to assess the mosaic, spots, brown streak, mites, and nutrient deficiency in cassava (Ramcharan et al, 2019).…”

Evaluation of rice bacterial blight severity from lab to field with hyperspectral imaging technique

“…Establishing effective analytical models for data interpretation is a significant part of phenotyping based on hyperspectral imaging. Deep learning methods have been applied to the phenotypic analysis of crop diseases in lab and field environments with the advantages of powerful automatic learning and feature extraction (Zhang et al, 2018b;Too et al, 2019;Prabhakar et al, 2020). Duarte-Carvajalino et al (2018) found that convolutional neural network (CNN) network was better than multilayer perceptron and support vector machine (SVM) in predicting the severity of potato late blight.…”

Crop breeding for a changing climate: integrating phenomics and genomics with bioinformatics

“…Harnessing the rapidly accumulating repositories of genomic and phenomic data to effectively characterize biological traits and pathways remains a complex statistical challenge that is being addressed in part through the application of novel machine learning (ML) algorithms (Esposito et al 2019;Prabhakar et al 2020). Bioinformatics will need to continue to build and manage integrated databases alongside software to facilitate the analysis and visualization of multi 'omic data.…”