Challenges and Opportunities in Machine-Augmented Plant Stress Phenotyping

Abstract

Plant stress phenotyping is essential to select stress-resistant varieties and develop better stress-management strategies. Standardization of visual assessments and deployment of imaging techniques have improved the accuracy and reliability of stress assessment in comparison with unaided visual measurement. The growing capabilities of machine learning (ML) methods in conjunction with image-based phenotyping can extract new insights from curated, annotated, and high-dimensional datasets across varied crops and stresses. We propose an overarching strategy for utilizing ML techniques that methodically enables the application of plant stress phenotyping at multiple scales across different types of stresses, program goals, and environments. Understanding Plant Stress Is Crucial for Yield ProtectionPlant stress is a state of plant growth under non-ideal environmental conditions caused by various biotic (pathogen, insect, pest, and weed) and abiotic (temperature stress, nutrient deficiency, toxicity, herbicide) factors. Significant crop yield loss due to various plant stresses has the potential to threaten global food security [1]. Plant disease epidemics are a constant threat and continue to emerge owing to complex host-pathogen-environment dynamics [2,3]. Global climate change can exacerbate this situation because of the predicted increases in insect and pathogen pressure for major grains including rice (Oryza sativa), maize (Zea mays L.), and wheat (Triticum aestivum) [4]. Moreover, weather-related challenges such as drought, flooding, hail, and windstorms adversely affect crop production. Yield preservation and protection is a dynamic challenge for pathologists, entomologists, plant breeders, and crop producers globally. Understanding plant stress is crucial for improving yield protection to meet with the growing demand for food production [5]. In the past decade, significant advances in image processing and machine learning (ML; see Glossary) algorithms have been made to handle image-based stress datasets for automated data analysis and application of trained models [6][7][8]. We review the development and application of ML algorithms for image-based plant stress phenotyping at multiple scales ranging from leaf and canopy (plot) to field (production) scale. We discuss some of the major challenges in the practical application of ML algorithms, and list future efforts that will be necessary to make ML a more mainstream tool in plant stress phenotyping applications and usage. HighlightsPlant stress phenotyping is challenging to implement at multiple organizational scales (leaf, canopy, field).There is a need to improve the speed, accuracy, reliability, and scalability of stress phenotyping while allowing flexibility for highly variable program goals.

UAS-Based Plant Phenotyping for Research and Breeding Applications

“…Also, coupling of ground robotic systems [ 212 ] with UAS may be desirable to phenotype traits obscured from the UAS Automated Plot Segmentation and Labeling : another active area of research is plot segmentation with minimal previous work on automatic microplot segmentation using UAS data. Generally, a polygon of each plot is drawn manually or semiautomatically using GIS-based software such as QGIS or ArcGIS [ 30 , 174 , 210 ]; therefore, a fully automated solution is desirable especially in a breeding program that involves thousands to hundreds of thousands plots [ 14 ] ML and DL problem : ML and DL methods for plant phenotyping are an active area of research, and we suggest readers who are interested in this analysis refer to [ 162 , 164 , 206 ] as a starting point. While ML and DL are useful tools for UAS phenotyping, care needs to be taken to ensure that the data and problems trying to be solved are compatible with these methods (this includes large data size and variability).…”

“…ML and DL problem : ML and DL methods for plant phenotyping are an active area of research, and we suggest readers who are interested in this analysis refer to [ 162 , 164 , 206 ] as a starting point. While ML and DL are useful tools for UAS phenotyping, care needs to be taken to ensure that the data and problems trying to be solved are compatible with these methods (this includes large data size and variability).…”

Multiscale Parallel Algorithm for Early Detection of Tomato Gray Mold in a Complex Natural Environment

“…While ensuring real-time availability of the system, about 86% mAP was achieved with 50% IoU. Singh et al (2020) concluded that although plant disease detection technology has developed rapidly, the methods can be only effectively used for a restricted number of plants.…”

Biotechnological Approaches for Genetic Improvement of Lemon (Citrus limon (L.) Burm. f.) against Mal Secco Disease

“…Large-scale genetic and breeding experiments take advantage of computer-image analysis integrated with biological data [ 80 ] such as different image techniques (visible light, fluorescence, near-infrared, hyperspectral, 3D, laser, magnetic resonance, positron emission detectors for short-lived isotopes (PET), X-ray computed tomography and X-ray digital radiography) [ 81 , 82 ]. Much interest is also shown toward machine learning approaches to detect patterns and hidden correlation from large amounts of data [ 83 ].…”