PreprintCase ReportVersion 1Preserved in Portico This version is not peer-reviewed
Choosing the Best Model for Crop Yield Prediction by the Means of Regression Analysis on the Example of “Crop Yield – Water Use” Simulations Through Best Subsets Approach
Version 1
: Received: 20 March 2023 / Approved: 21 March 2023 / Online: 21 March 2023 (07:10:49 CET)
How to cite:
Lykhovyd, P.; Vozhehova, R.; Piliarska, O.; Zaiets, S. Choosing the Best Model for Crop Yield Prediction by the Means of Regression Analysis on the Example of “Crop Yield – Water Use” Simulations Through Best Subsets Approach. Preprints2023, 2023030372. https://doi.org/10.20944/preprints202303.0372.v1
Lykhovyd, P.; Vozhehova, R.; Piliarska, O.; Zaiets, S. Choosing the Best Model for Crop Yield Prediction by the Means of Regression Analysis on the Example of “Crop Yield – Water Use” Simulations Through Best Subsets Approach. Preprints 2023, 2023030372. https://doi.org/10.20944/preprints202303.0372.v1
Lykhovyd, P.; Vozhehova, R.; Piliarska, O.; Zaiets, S. Choosing the Best Model for Crop Yield Prediction by the Means of Regression Analysis on the Example of “Crop Yield – Water Use” Simulations Through Best Subsets Approach. Preprints2023, 2023030372. https://doi.org/10.20944/preprints202303.0372.v1
APA Style
Lykhovyd, P., Vozhehova, R., Piliarska, O., & Zaiets, S. (2023). Choosing the Best Model for Crop Yield Prediction by the Means of Regression Analysis on the Example of “Crop Yield – Water Use” Simulations Through Best Subsets Approach. Preprints. https://doi.org/10.20944/preprints202303.0372.v1
Chicago/Turabian Style
Lykhovyd, P., Olena Piliarska and Sergiy Zaiets. 2023 "Choosing the Best Model for Crop Yield Prediction by the Means of Regression Analysis on the Example of “Crop Yield – Water Use” Simulations Through Best Subsets Approach" Preprints. https://doi.org/10.20944/preprints202303.0372.v1
Abstract
Crop yield prediction is relevant subject of current agricultural science. There are various mathematical approaches to crop yield prediction, and regression analysis, notwithstanding the fact that it is somewhat outdated, is still one of the most used ones in this purpose. The quality of predictive model is of great importance, and it is strongly dependent on the rational choice of the target function. The goal of this study is to find out the best regression model for winter wheat, soybeans, and grain corn yield prediction depending on the crops’ water use. The data on true crops’ yields and water use were collected within 1970-2020 at the experimental fields of the Institute of Climate-Smart Agriculture, Kherson region, Ukraine. In total, 145 data pairs were processed by the best subsets regression to find out the best model in terms of fitting quality (assessed by the Pearson’s coefficient of correlation), and prediction accuracy (assessed by the values of the minimum and maximum absolute errors and mean average percentage error). As a result, it was established that the best fitting quality for all the studied crops is attributed to cubic function, while the best accuracy is recorded for hyperbolic (reverse) function in soybeans (mean absolute percentage error is 12.27%), quadratic and hyperbolic functions in winter wheat (mean absolute percentage error is 20.54%), and cubic function in grain corn (mean absolute percentage error is 14.92%). To sum up the results of the study, it is recommended to apply cubic regression function for modeling crops’ yields in agricultural studies.
Biology and Life Sciences, Agricultural Science and Agronomy
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.