Claim · model-written summary
For JSendra, XGBoost achieved R2 of 0.74 at 110 DAS.
Oryza sativaNot reportedGeneCompoundOrgan / stageInteractorInteractor roleSecond interactorSecond interactor roleTreatmentSettingDirection
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“XGB systematically outperformed RF, achieving at 110 and 130 DAS (days after showing), R2 values of 0.74 and 0.85 and RMSE values of 0.63 and 0.28 t·ha−1 for ‘JSendra’ and ‘Bomba’”
t0“Rice Yield Prediction”
Title
Rubén Simeón; Alba Agenjos-Moreno; Constanza Rubio; et al. Agriculture 2026. doi:10.3390/agriculture16020201
Other claims from this paper (10)
- Method / resource XGBoost outperformed Random Forest for rice yield prediction.
- Method / resource For Bomba, XGBoost achieved R2 of 0.85 at 130 DAS.
- Method / resource For JSendra, XGBoost RMSE was 0.63 t·ha−1.
- Method / resource For Bomba, XGBoost RMSE was 0.28 t·ha−1.
- Method / resource Prediction accuracy increased as the season progressed.
- Method / resource Models using all spectral bands outperformed spectral-index configurations.
- Method / resource NIR reflectance made the dominant contribution to model prediction.
- Method / resource Prediction errors occurred at field edges and headlands.
- Method / resource Central pixels were predicted more accurately.
- Method / resource The approach generated spatial rice yield maps capturing within-field variability.