PubMed · 2026-07-10
Crops struggle when light is scarce, whether from dense canopies, cloudy skies, or intercropping. This review maps how plants cope through shade avoidance or shade tolerance, identifies why current scientific tools are too fragmented to guide breeders or farmers, and proposes an AI-driven framework combining mass phenotyping and digital field models to predict and breed for shade-efficient crops.
Two dominant adaptive strategies govern crop responses to low light: shade avoidance (elongating to escape competition) and shade tolerance (adjusting metabolism to function under reduced light), and most crops lean on one or the other.
C3 crops (like wheat and rice) and C4 crops (like maize and sorghum) respond to light limitation through fundamentally different biological logic driven by differences in leaf anatomy, energy pathways, and regulatory control.
Current research lacks a unified indicator framework, leaving prediction models poorly coupled across scales; the paper proposes AI-assisted multiscale digital twins to close this gap and generate actionable breeding targets.