Challenges and Opportunities in Machine-Augmented Plant Stress Phenotyping

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.

Automated summary

Plant stress phenotyping is crucial for selecting stress-resistant varieties and improving stress-management strategies. Standardization of visual assessments and deployment of imaging techniques have enhanced accuracy and reliability of stress assessment, while machine learning methods are increasingly utilized to extract insights from high-dimensional datasets. A comprehensive strategy is proposed for utilizing machine learning techniques in applying plant stress phenotyping across various crops, stresses, and environments.