Designed nutrient-gradient phenotyping enables predictive ionomics of tropical leafy greens
- 1The Robert H Smith Faculty of Agriculture, Food and Environment, Hebrew University of Jerusalem, Israel
Abstract
Accurate prediction of edible-leaf mineral composition is challenging because tissue ionomes integrate nutrient supply, plant identity, growth dilution, water-balance regulation and cumulative environmental exposure. We combined a designed nutrient-gradient experimental framework with machine learning to predict leaf ionome using 1,163 Chinese spinach (Amaranthus dubius) and Chinese broccoli (Brassica oleracea Alboglabra Group) plants grown across 16 designed nutrient-gradient experiments in a semi-controlled tropical greenhouse. Targeted perturbations of N, P, K, Ca, Mg, Fe and Mo were combined with cumulative transpiration, integrated microclimate, shoot dry weight and laboratory quantification of 12 harvested-leaf mineral targets. The resulting ionome was broad, non-Gaussian and species dependent, with coordinated off-target shifts also evident for minerals whose supplied concentrations were held constant. We benchmarked AutoGluon and TabPFN using five-fold leakage-free, distribution-balanced grouped cross-validation, in which all biological replicates from each dosing condition were withheld together. Across previously unseen nutrient conditions, pooled out-of-fold R2 ranged from 0.72 to 0.92, with broadly comparable performance between architectures. Learning curves showed rapid early gains for several targets but persistent condition-level generalization gaps for total reduced nitrogen, K, Mn and Zn. Model-agnostic Shapley additive explanations identified target-specific combinations of nutrient inputs, plant type, substrate, cumulative environment and physiological traits, while cross-model attribution agreement varied among minerals. Finally, reduced-feature models were tested on an independent grower-operated cohort of 99 plants. Calibration was closest for NO3, Mg and B, whereas Mn and Na showed substantial external bias. These results establish leakage-aware predictive ionomics as a robust framework for post-harvest lab-free crop mineral estimation while defining the calibration and sensing requirements for commercial deployment.
Related
- Construction of a Daphnia -sustaining microcosm using purely inorganic medium: a system designed to investigate endogenous nutrient biosynthesis
- Comparative analysis of gradient boosting and random forest regressors for nutrient prediction in smart agriculture
- Phenotyping replication strongly influences genomic predictive ability in sweet sorghum (Sorghum bicolor [L.] Moench)
- Elucidating the role of glucose-mediated redox homeostasis, carbohydrate metabolism, and secondary metabolite production in enhancing photosynthetic activity, ionomics, and yield in two okra (Abelmoschus esculentus) varieties
- Designed nanofiber immunogens prime antibody responsesto diverse conformations of the HIV-1 fusion peptide
BibTeX
@misc{shenhar2026designed,
title = {{Designed nutrient-gradient phenotyping enables predictive ionomics of tropical leafy greens}},
author = {I. Shenhar and M. Pebes-Trujillo and A. Harikumar and Z. Zhao and L. Y. Tan and M. I. Setyawati and J. He and I. Herrmann and K. W. Ng and M. Gavish and M. Moshelion},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.16.751971},
url = {https://www.biorxiv.org/content/10.64898/2026.09.16.751971v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - Designed nutrient-gradient phenotyping enables predictive ionomics of tropical leafy greens
AU - I. Shenhar
AU - M. Pebes-Trujillo
AU - A. Harikumar
AU - Z. Zhao
AU - L. Y. Tan
AU - M. I. Setyawati
AU - J. He
AU - I. Herrmann
AU - K. W. Ng
AU - M. Gavish
AU - M. Moshelion
PY - 2026
DA - 2026/09/16
PB - bioRxiv
DO - 10.64898/2026.09.16.751971
UR - https://www.biorxiv.org/content/10.64898/2026.09.16.751971v1
AB - Accurate prediction of edible-leaf mineral composition is challenging because tissue ionomes integrate nutrient supply, plant identity, growth dilution, water-balance regulation and cumulative environmental exposure. We combined a designed nutrient-gradient experimental framework with machine learning to predict leaf ionome using 1,163 Chinese spinach (Amaranthus dubius) and Chinese broccoli (Brassica oleracea Alboglabra Group) plants grown across 16 designed nutrient-gradient experiments in a semi-controlled tropical greenhouse. Targeted perturbations of N, P, K, Ca, Mg, Fe and Mo were combined with cumulative transpiration, integrated microclimate, shoot dry weight and laboratory quantification of 12 harvested-leaf mineral targets. The resulting ionome was broad, non-Gaussian and species dependent, with coordinated off-target shifts also evident for minerals whose supplied concentrations were held constant. We benchmarked AutoGluon and TabPFN using five-fold leakage-free, distribution-balanced grouped cross-validation, in which all biological replicates from each dosing condition were withheld together. Across previously unseen nutrient conditions, pooled out-of-fold R2 ranged from 0.72 to 0.92, with broadly comparable performance between architectures. Learning curves showed rapid early gains for several targets but persistent condition-level generalization gaps for total reduced nitrogen, K, Mn and Zn. Model-agnostic Shapley additive explanations identified target-specific combinations of nutrient inputs, plant type, substrate, cumulative environment and physiological traits, while cross-model attribution agreement varied among minerals. Finally, reduced-feature models were tested on an independent grower-operated cohort of 99 plants. Calibration was closest for NO3, Mg and B, whereas Mn and Na showed substantial external bias. These results establish leakage-aware predictive ionomics as a robust framework for post-harvest lab-free crop mineral estimation while defining the calibration and sensing requirements for commercial deployment.
ER -