Roth et al. (2026) Characterizing yield through wheat’s perception of chronological progression: a multi-omics plant time warping approach

⚠️ Warning: This summary was generated from the abstract only, as the full text was not available.

Identification

• Journal: Journal of Experimental Botany
• Year: 2026
• Date: 2026-02-14
• Authors: Lukas Roth, Juan M. Herrera, Lilia Levy Häner, Didier Pellet, Mike Boss, X. Chen, Paraskevi Nousi, Michele Volpi
• DOI: 10.1093/jxb/erag085

Research Groups

[Not specified]

Short Summary

The study introduces Plant Time Warping (PTW), a deep learning model that integrates phenomic, genomic, and environmental data to predict wheat yield. PTW outperforms traditional genomic prediction models by capturing genotype-specific physiological responses to temperature and vapor pressure deficit across diverse European environments.

Objective

• To improve the prediction of wheat yield in unseen environments by integrating high-throughput field phenotyping (image time series) with genomic markers and environmental covariates.

Study Configuration

• Spatial Scale: 48 year-locations across Europe.
• Temporal Scale: Not specified (covers various phenological stages).

Methodology and Data

• Models used: Plant Time Warping (PTW), a deep learning model.
• Data sources: High-throughput field phenotyping (image time series), genetic markers, and environmental covariates (temperature and vapor pressure deficit).

Main Results

• PTW demonstrates superior yield prediction performance in unseen environments compared to models relying solely on genomic data.
• The model identifies non-linear growth responses that vary by phenological stage.
• Varieties with higher yield stability exhibit reduced sensitivity to vapor pressure deficit around $1.5\text{ kPa}$.
• Distinct temperature response patterns were identified during the emergence and senescence stages as key drivers of yield performance and stability.

Contributions

• Provides a framework for integrating phenomic, genomic, and enviromic data to overcome generalization challenges in crop yield prediction.
• Enables retrospective and prospective yield predictions to support location-specific variety recommendations and targeted breeding for climate adaptation.

Funding

[Not specified]

Citation

@article{Roth2026Characterizing,
  author = {Roth, Lukas and Herrera, Juan M. and Häner, Lilia Levy and Pellet, Didier and Fossati, Dario and Boss, Mike and Chen, X. and Nousi, Paraskevi and Volpi, Michele},
  title = {Characterizing yield through wheat’s perception of chronological progression: a multi-omics plant time warping approach},
  journal = {Journal of Experimental Botany},
  year = {2026},
  doi = {10.1093/jxb/erag085},
  url = {https://doi.org/10.1093/jxb/erag085}
}