| Popis: |
Background and aims Root distribution over the soil profile is important for crop resource uptake. Using machine learning (ML), this study investigated whether measured planar root length density (pRLD) at different soil depths were related to uptake of isotope tracer (15N) and drought stress indicator (13C) in wheat, to reveal root function. Methods In the RadiMax semi-field root-screening facility 95/120 different winter wheat genotypes were phenotyped for root growth in 2018/2019, respectively. Using the minirhizotron technique, root images were acquired across a depth range from 80 to 250 cm in May, June, and July and pRLD was extracted using a convolutional neural network. We developed ML models to explore whether the pRLD estimates at different soil depths were predictive of the uptake of deep soil nitrogen - using deep placement of 15N tracer as well as drought resilience potential using natural abundance of 13C isotope. We analyzed the correlations to tracer levels to both an analytical root depth estimation and an ML approach. We further analyzed the genotypic effects on root function using mediation analysis. Results Both analytical and ML models demonstrated clear correlations between pRLD distribution and resource uptake. Further, both models demonstrated that deep roots at approx. 150 to 170 cm depth were most important for explaining the plant content of 15N and 13C isotopes. The correlations were higher in 2018 than in 2019. Conclusions The results demonstrated that in the semi-field non-invasive root phenotyping setup, analytical and ML-based analysis provided complementary insight into the importance of deep rooting for water and nitrogen uptake. |
