Claim · model-written summary
XGBoost performed poorly on unseen fields or years, whereas the Extra Tree regressor was a more reliable model for predicting missing data.
- Outcome
- unseen fields or yearse3
- Direction
- performed poorlye3
- Qualifier
- XGBooste3
- Comparator
- Extra Tree regressore3
Not reportedMaterialGeneCompoundOrgan / stageInteractorInteractor roleSecond interactorSecond interactor roleTreatmentSettingValue
Organisms pictured · Representative pictures of the matched species, not figures from the paper.

Verbatim
e0“Corn (Zea mays L.) silage yield monitor data offer crucial insights into spatial and temporal yield variability”
e3“However, XGBoost performed poorly when applied to unseen fields or years, whereas Extra Tree regressor, followed closely by Random Forest, emerged as a more reliable model for predicting missing data”
Title
Exploring the Use of High-Resolution Satellite Images to Estimate Corn Silage Yield Within Field
Srinivasagan N. Subhashree; Manuel Marcaida; Shajahan Sunoj; et al. Remote Sensing 2024. doi:10.3390/rs16214081
Other claims from this paper (4)
- Observation Topography and vegetation index features (EVI2 at Farm A, elevation at Farm B) were the most prominent yield predictors.
- Method / resource Ensemble-based models exhibited superior predictive performance for corn silage yield.
- Method / resource The best model estimated missing field yield at 6.46 Mg/ha, which fell short of the 4.9 Mg/ha acceptable error threshold.
- Method / resource The best model estimated missing year yield at 5.51 Mg/ha, which fell short of the 4.9 Mg/ha acceptable error threshold.