What type of study is this?

This is a Cohort Study study (also classified as: Quantitative Study).

October 11, 2025Eng—Advances in EngineeringOpen Access

A Comparative Assessment of Regular and Spatial Cross-Validation in Subfield Machine Learning Prediction of Maize Yield from Sentinel-2 Phenology

View Full Paper

Ask AI

Bookmark

Authors

DRDorijan RadočajUniversity of Osijek IPIvan PlašćakUniversity of Osijek MJMladen JurišićUniversity of Osijek

Discussion

Member takes

Implication

This analysis compares regular and spatial cross-validation methods for machine learning in maize yield prediction, highlighting significant differences in model accuracy.

Key Points

Spatial cross-validation led to more accurate model performance estimates compared to regular cross-validation.
EVI-based models provided more reliable yield predictions than those based on WDRVI in the study.
The analysis utilized 10-fold cross-validation methods and high-resolution data from eastern Croatia.
Ignoring spatial structure can generate misleading conclusions about the accuracy and generalizability of predictive models.

Cite This Study

Radočaj et al. (2025) studied this question.

synapsesocial.com/papers/68e9b1d0ba7d64b6fc132cd1 https://doi.org/10.3390/eng6100270

View Full Paper

Ask AI

Bookmark

October 11, 2025Eng—Advances in EngineeringOpen Access

A Comparative Assessment of Regular and Spatial Cross-Validation in Subfield Machine Learning Prediction of Maize Yield from Sentinel-2 Phenology

View Full Paper

Ask AI

Bookmark

Authors

DRDorijan RadočajUniversity of Osijek IPIvan PlašćakUniversity of Osijek MJMladen JurišićUniversity of Osijek

Discussion

Member takes

Implication

This analysis compares regular and spatial cross-validation methods for machine learning in maize yield prediction, highlighting significant differences in model accuracy.

Key Points

Spatial cross-validation led to more accurate model performance estimates compared to regular cross-validation.
EVI-based models provided more reliable yield predictions than those based on WDRVI in the study.
The analysis utilized 10-fold cross-validation methods and high-resolution data from eastern Croatia.
Ignoring spatial structure can generate misleading conclusions about the accuracy and generalizability of predictive models.

Cite This Study

Radočaj et al. (2025) studied this question.

synapsesocial.com/papers/68e9b1d0ba7d64b6fc132cd1 https://doi.org/10.3390/eng6100270

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark