Technological advances in imaging and modelling of leaf structural traits: a review of heat stress in wheat

Abstract

Abiotic stresses such as heat waves significantly reduce wheat productivity by altering leaf anatomy and physiology, leading to reduced photosynthetic carbon assimilation and crop yield. Despite the advancement in various imaging technologies at the field, canopy, plant, tissue, cellular, and subcellular levels, phenotyping of imaging-based leaf structural traits (e.g. vein density, stomatal density, and stomatal aperture) for abiotic stresses is still time-consuming and expensive without the aid of artificial intelligence (AI) and machine learning (ML). This review consolidates current knowledge of wheat leaf structural and functional adaptations to heat stress and highlights key advancements in imaging technologies for studying these important phenotypic traits. Recent high-resolution, non-destructive imaging technologies, including confocal laser scanning microscopy, X-ray computed tomography, and optical coherence tomography, have enabled in vivo visualization of plants. Integrating these imaging techniques with AI/ML facilitates high-throughput phenotyping and the modelling of stress responses. We emphasize the potential for future research to leverage these technological advancements in imaging and AI, combining imaging data with physiological and multi-omics studies to deepen the understanding of plant heat tolerance mechanisms. Such multidisciplinary integration in leaf structure phenotyping will accelerate the development of resilient wheat varieties, offering critical insights for crop improvement in the face of climate change.

Plant phenotyping relevance

植物の葉構造・機能形質を対象とする画像計測技術とAI/MLによる表現型解析を中心に整理したレビューであり、植物フェノタイピング手法レビューに該当する。

Code and data availability

This is a review article on imaging and modelling of wheat leaf structural traits under heat stress. The supplied blocks contain no public phenotype datasets, author image/sensor data, analysis code, or trained models specific to this paper; all cited studies are prior work, and the only URL present is the Creative CC-

No evidence-backed public reproduction asset is currently recorded.