Abstract
Abstract On‐farm precision experimentation (OFPE) is increasingly conducted using variable‐rate technology and precision agriculture (PA) equipment to measure the effect of changes in input application rates on yields and profits at specific fields. Classical linear regression models and new Bayesian and machine learning regressions for spatial data can be used to investigate site‐specific crop response from georeferenced data. The objective of this work was to compare statistical models that can be used by researchers analyzing OFPE data to estimate crop response and better describe its spatial within‐field variability. Three statistical models estimating the responses to N rates, seed rates, and site‐specific soil properties from eight OFPEs were compared: (a) linear regression (LR) for spatially correlated errors, (b) Bayesian regression (BR) with random site effects, and (c) random forest regression (RF) with kriged residuals. Models were adjusted to account for spatial variation in yield response, and with and without field characteristic covariates. Modeling spatial correlation and including plot covariates improved yield predictions. Differences among methods proved to be indistinguishable with respect to average explained variance, correlation between predicted and observed values, and mean square prediction errors (PEs). However, BR and RF outperformed LR in site‐specific prediction accuracy, with BR predictions having lower predictive uncertainty than RF predictions. The hierarchical Bayesian model for spatial data is a useful tool to process OFPE data, allowing direct derivation of linear coefficients and prediction uncertainty measures related to site‐specific yield responses.
Abstract from the paper’s OpenAlex record; open copy licensed cc-by-nc-sa. 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 5
Claim · model-written summary
Spatial correlation modeling and plot covariates improved yield predictions.
- Treatment
- Modeling spatial correlation and including plot covariatese0
- Outcome
- yield predictionse0
- Direction
- improvede0
Not reportedTaxonComparatorValue
Verbatim
e0“Modeling spatial correlation and including plot covariates improved yield predictions.”
Claim · model-written summary
The methods were indistinguishable in average explained variance, predicted–observed correlation and mean square prediction errors.
Verbatim
e0“Differences among methods proved to be indistinguishable with respect to average explained variance, correlation between predicted and observed values, and mean square prediction errors (PEs).”
Claim · model-written summary
BR and RF exceeded LR in site-specific prediction accuracy.
Verbatim
e0“BR and RF outperformed LR in site‐specific prediction accuracy”
Claim · model-written summary
BR predictions had lower predictive uncertainty than RF predictions.
Verbatim
e0“BR predictions having lower predictive uncertainty than RF predictions”
Claim · model-written summary
The hierarchical Bayesian model permits direct derivation of linear coefficients and uncertainty measures for site-specific yield response.
- Outcome
- linear coefficients and prediction uncertainty measures related to site‐specific yield responsese0
- Comparator
- OFPE datae0
Not reportedValue
Verbatim
e0“The hierarchical Bayesian model for spatial data is a useful tool to process OFPE data, allowing direct derivation of linear coefficients and prediction uncertainty measures related to site‐specific yield responses.”