Claim · model-written summary
SVM with NDVI phenology metrics had the highest maize yield prediction accuracy.
- Outcome
- accuracy for maize yield predictione0
- Direction
- higheste0
- Value
- R2 = 0.935, RMSE = 0.558 t ha−1, MAE = 0.399 t ha−1e0
Not reportedMaterialGeneCompoundOrgan / stageInteractorInteractor roleSecond interactorSecond interactor roleTreatmentComparatorSettingQualifier
Organisms pictured · Representative pictures of the matched species, not figures from the paper.

Verbatim
e0“The results suggested that the SVM method based on NDVI phenology metrics produced the highest accuracy for maize yield prediction (R2 = 0.935, RMSE = 0.558 t ha−1, MAE = 0.399 t ha−1).”
Title
Dorijan Radočaj; Ivan Plaščak; Željko Barač; et al. OTO 2025 2026. doi:10.3390/engproc2026125001
Other claims from this paper (3)
- Method / resource Vegetation index values at greenup, dormancy and peak of season were the most important yield prediction covariates.
- Method / resource Occurrence day of year of the vegetation index metrics had only a minor effect on yield prediction accuracy.
- Method / resource NDVI outperformed NDVI3RE for maize yield prediction when combined with phenology metrics.