Machine Learning for High-Throughput Stress Phenotyping in Plants.

By Arti Singh, Baskar Ganapathysubramanian, Ashutosh Kumar Singh, Soumik Sarkar. Trends in Plant Science, 2016

928 citations recorded by the source corpus.

Advances in automated and high-throughput imaging technologies have resulted in a deluge of high-resolution images and sensor data of plants. However, extracting patterns and features from this large corpus of data requires the use of machine learning (ML) tools to enable data assimilation and feature identification for stress phenotyping. Four stages of the decision cycle in plant stress phenotyping and plant breeding activities where different ML approaches can be deployed are (i) identification, (ii) classification, (iii) quantification, and (iv) prediction (ICQP). We provide here a comprehensive overview and user-friendly taxonomy of ML tools to enable the plant community to correctly and easily apply the appropriate ML tools and best-practice guidelines for various biotic and abiotic stress traits.

Subfields: Analytical Chemistry, Plant Science

View Paper: https://www.semanticscholar.org/paper/a09a9f69ff145508a12e6dbb81ccd7f5be4bd2fc

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Analytical Chemistry

In Plant Science

Citations in the corpus

Hyperspectral image analysis techniques for the detection and classification of the early onset of plant disease and stress (2017, background): “[8] which examines machine learning for stress phenotyping, exploring literature on high throughput phenotyping for stress identification, classification, quantification and prediction using different sensors.”
Using Deep Learning for Image-Based Plant Disease Detection (2016, background): “A very recent review on the use of machine learning on plant phenotyping (Singh et al., 2015) extensively discusses the work in this domain.”
Quantitative and qualitative phenotyping of disease resistance of crops by hyperspectral sensors: seamless interlocking of phytopathology, sensors, and machine learning is needed! (2019, background): “Methods from the ﬁeld of artiﬁcial intelligence (e.g. data mining, machine learning, and pattern recognition) and computational sustainability already contribute to provide solutions for plant phenotyping, even in high-throughput setups [46 ,47,48].”
Deep machine learning provides state-of-the-art performance in image-based plant phenotyping (2016, neutral): “Whilst these techniques provide considerable success in many situations [4], their performance is saturating and often falls short of the high accuracy required for fully automated systems.”
Automated Identification of Northern Leaf Blight-Infected Maize Plants from Field Imagery Using Deep Learning. (2017, methodology): “Machine learning techniques have been used to detect, classify, and quantify a wide variety of diseases on many crops, as reviewed by Barbedo (2013) and Singh et al. (2016).”
Unmanned Aerial Vehicle Remote Sensing for Field-Based Crop Phenotyping: Current Status and Perspectives (2017, background): “…for crop phenotype analysis from remote sensing include direct monitoring, image classification, concurrent comparison, empirical statistics modeling, physical reversion modeling, machine learning, and time series analysis of remote sensing parameters (Singh et al., 2016; Virlet et al., 2017).”
Current and future applications of statistical machine learning algorithms for agricultural machine vision systems (2019, methodology): “The PCA was found to be very commonly used for selecting the specific wavelengths (features) from high dimensional hyperspectral imaging for plant phenotypic applications (Singh et al., 2016; Pandey et al., 2017; Liang et al., 2017).”
Crop Yield Prediction Using Deep Reinforcement Learning Model for Sustainable Agrarian Applications (2020, background): “Crop yield mainly depends upon climatic conditions, soil quality, landscapes, pest infestations, water quality and availability, genotype, planning of harvest activity and so on [3]–[5].”
Deep Plant Phenomics: A Deep Learning Platform for Complex Plant Phenotyping Tasks (2017, background): “Plant disease detection and diagnosis is an example of a complex phenotyping task where machine learning techniques, such as support vector machines, clustering algorithms, and neural networks, have demonstrated success (Singh et al., 2016).”
High-Throughput Field-Phenotyping Tools for Plant Breeding and Precision Agriculture (2019, methodology): “Sev ral machine learning algo ithms h ve be n tested for HTPP data and were summarized earlier [66].”
Using UAV Borne, Multi-Spectral Imaging for the Field Phenotyping of Shoot Biomass, Leaf Area Index and Height of West African Sorghum Varieties under Two Contrasted Water Conditions (2021, background): “Thus, the rapid development of GPU and machine learning technologies in recent years could improve the model capabilities [63].”
Translating High-Throughput Phenotyping into Genetic Gain (2018, background): “Despite recent advances in data acquisition and processing, these large data sets have created new bottlenecks in data management [73], and advanced supervised algorithms require manual labeling of very large data sets for implementation [55], although they are potentially amenable to crowd sourcing”