Abstract
The aim of this study is to determine the reliability of regular and spatial cross-validation methods in predicting subfield-scale maize yields using phenological measures derived by Sentinel-2. Three maize fields from eastern Croatia were monitored during the 2023 growing season, with high-resolution ground truth yield data collected using combine harvester sensors. Sentinel-2 time series were used to compute two vegetation indices, Enhanced Vegetation Index (EVI) and Wide Dynamic Range Vegetation Index (WDRVI). These features served as inputs for three machine learning models, including Random Forest (RF) and Bayesian Generalized Linear Model (BGLM), which were trained and evaluated using both regular and spatial 10-fold cross-validation. Results showed that spatial cross-validation produced a more realistic and conservative estimate of the performance of the model, while regular cross-validation overestimated predictive accuracy systematically because of spatial dependence among the samples. EVI-based models were more reliable than WDRVI, generating more accurate phenomenological fits and yield predictions across parcels. These results emphasize the importance of spatially explicit validation for subfield yield modeling and suggest that overlooking spatial structure can lead to misleading conclusions about model accuracy and generalizability.
Abstract from the paper’s OpenAlex record; open copy licensed cc-by. Read at the source ↗
The text the model read, with the source record’s inline markup (italics, sub- and superscripts) rendered and its character entities decoded; quote offsets refer to the raw text.
Claims 6
Claim · model-written summary
Spatial cross-validation gave a more realistic and conservative estimate of maize yield model performance.
- Outcome
- estimate of the performance of the modele0
- Direction
- more realistic and conservativee0
- Comparator
- spatial cross-validatione0
Zea maysOrganisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“spatial cross-validation produced a more realistic and conservative estimate of the performance of the model”
t0“Maize Yield”
Claim · model-written summary
Regular cross-validation systematically overestimated predictive accuracy because samples were spatially dependent.
- Outcome
- predictive accuracye0
- Direction
- overestimatede0
- Qualifier
- because of spatial dependence among the samplese0
- Comparator
- regular cross-validatione0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“regular cross-validation overestimated predictive accuracy systematically because of spatial dependence among the samples”
t0“Maize Yield”
Claim · model-written summary
EVI-based models were more reliable than WDRVI models.
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“EVI-based models were more reliable than WDRVI”
t0“Maize Yield”
Claim · model-written summary
EVI-based models produced more accurate phenological fits than WDRVI across parcels.
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“EVI-based models were more reliable than WDRVI, generating more accurate phenomenological fits and yield predictions across parcels”
t0“Maize Yield”
Claim · model-written summary
EVI-based models produced more accurate yield predictions than WDRVI across parcels.
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“EVI-based models were more reliable than WDRVI, generating more accurate phenomenological fits and yield predictions across parcels”
t0“Maize Yield”
Claim · model-written summary
The authors recommend spatially explicit validation for subfield yield modeling.
- Outcome
- spatially explicit validation for subfield yield modelinge0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“These results emphasize the importance of spatially explicit validation for subfield yield modeling”
t0“Maize Yield”