Summary
This study leveraged high-throughput hyperspectral phenotyping and explainable AI to classify dynamic waterlogging responses in 230 barley accessions across three temporal phases, achieving 86% classification accuracy. Longitudinal GWAS identified 236 significant loci and implicated MYB transcription factors and genes involved in oxidative stress regulation as central to waterlogging tolerance. The authors developed 3D-QTLVis, an interactive tool for visualising temporal dynamics in genomic associations, to enable clearer interpretation of stress-response loci.
Regional applicability
The findings are directly relevant to United Kingdom barley breeding and cultivation, as waterlogging is a significant agronomic constraint in UK cereal production, particularly in high-rainfall regions and heavy clay soils. The identified genomic markers and spectral indices could inform UK breeding programmes aimed at developing more waterlogging-tolerant barley varieties suited to wetter growing conditions.
Key measures
Hyperspectral reflectance indices (WATER1, SIPI), chlorophyll fluorescence, visible imaging over 14 days waterlogging + 7 days recovery; AI classification accuracy (86%); number and location of significant GWAS loci; candidate gene identification
Outcomes reported
The study identified 236 significant genomic loci associated with barley waterlogging stress responses across three temporal phases (early stress, late stress, recovery) using explainable AI-assisted hyperspectral phenotyping and longitudinal GWAS. Key spectral indices (WATER1 and SIPI) and candidate genes involved in oxidative stress regulation, transcriptional control, and auxin transport were characterised.
Topic tags
Dig deeper with Pulse AI.
Pulse AI has read the whole catalogue. Ask about this record, its theme, or how the findings apply to UK farming and policy — every answer cites the underlying studies.