Year-independent prediction of rice grain protein content using machine learning with agronomy-aligned multi-year field data
Frontiers in Plant Science · 01.06.2026 · 17
DOI: 10.3389/fpls.2026.1818096 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Plant Science, online erschienen am 01.06.2026. Verfasst von Hyun-Jin Jung und 4 weiteren Autor:innen. Beteiligte Einrichtung: Winter Crop Research Division, National Institute of Crop and Food Science, Rural Development Administration, Wanju, Republic of Korea. Die Arbeit nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Rice grain protein content exhibits substantial inter-annual variability due to interactions between management practices and environmental conditions, making robust prediction under realistic field conditions challenging. This study evaluated the year-independent predictability of rice grain protein content using multi-year field data and machine learning approaches, with a focus on data structuring and validation strategies. Models were trained using both plot-level and replicate-mean datasets, and evaluated using leave-one-year-out cross-validation to simulate prediction under unseen growing seasons. Replicate aggregation consistently improved predictive robustness by reducing plot-level variability, while year-independent validation provided a more conservative and realistic assessment of model generalization. Despite this stringent framework, predictive performance remained relatively stable, and residual diagnostics indicated no clear systematic bias across protein levels or nitrogen application rates. Anomaly-based analysis further suggested that deviations from year–variety baselines could be predicted with meaningful accuracy, indicating that relative variations beyond dominant temporal effects were effectively captured. These results suggest that aligning data structuring and validation strategies with agronomic experimental design may be important for reliable year-independent prediction. The proposed framework may provide a transferable approach for integrating machine learning with agronomic knowledge to support crop quality prediction and adaptive nitrogen management under variable field conditions.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Winter Crop Research Division, National Institute of Crop and Food Science, Rural Development Administration, Wanju, Republic of Korea.
- Crop Production and Physiology Division, National Institute of Crop and Food Science, Rural Development Administration, Wanju, Republic of Korea.
- Central-Northern Region Crop Research Center, National Institute of Crop and Food Science, Rural Development Administration, Suwon, Republic of Korea.
- Department of Smart Agro-Industry, Gyeongsang National University, Jinju, Republic of Korea.
- Department of Crop Science, Chungbuk National University, Cheongju, Republic of Korea.
Zitieren
APA
Jung, H. J., Lee, Y. H., Lee, C., Cho, S. W., & Hwang, T. Y. (2026). Year-independent prediction of rice grain protein content using machine learning with agronomy-aligned multi-year field data. Frontiers in Plant Science, 17. https://doi.org/10.3389/fpls.2026.1818096
Vancouver
Jung HJ, Lee YH, Lee C, Cho SW, Hwang TY. Year-independent prediction of rice grain protein content using machine learning with agronomy-aligned multi-year field data. Frontiers in Plant Science. 2026;17. doi:10.3389/fpls.2026.1818096
BibTeX
@article{Jung2026,
author = {Jung, Hyun-Jin and Lee, Yun-Ho and Lee, ChungGen and Cho, Seong-Woo and Hwang, Tae-Young},
title = {Year-independent prediction of rice grain protein content using machine learning with agronomy-aligned multi-year field data},
journal = {Frontiers in Plant Science},
year = {2026},
volume = {17},
doi = {10.3389/fpls.2026.1818096}
}
EUVIMED