Soybean Yield Estimation and Its Components: A Linear Regression Approach
Soybean yield estimation is either based on yield monitors or agro-meteorological and satellite imagery data, but they present several limiting factors regarding on-farm decision level. Aware that machine learning approaches have been largely applied to estimate soybean yield and the availability of...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-08-01
|
| Series: | Agriculture |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0472/10/8/348 |
| _version_ | 1797558931940179968 |
|---|---|
| author | Marcelo Chan Fu Wei José Paulo Molin |
| author_facet | Marcelo Chan Fu Wei José Paulo Molin |
| author_sort | Marcelo Chan Fu Wei |
| collection | DOAJ |
| description | Soybean yield estimation is either based on yield monitors or agro-meteorological and satellite imagery data, but they present several limiting factors regarding on-farm decision level. Aware that machine learning approaches have been largely applied to estimate soybean yield and the availability of data regarding soybean yield and its components (number of grains (NG) and thousand grains weight (TGW)), there is an opportunity to study their relationships. The objective was to explore the relationships between soybean yield and its components, generate equations to estimate yield and evaluate its prediction accuracy. The training dataset was composed of soybean yield and its components’ data from 2010 to 2019. Linear regression models based on NG, TGW and yield were fitted on the training dataset and applied to a validation dataset composed of 58 on-field collected samples. It was found that globally TGW and NG presented weak (r = 0.50) and strong (r = 0.92) linear relationships with yield, respectively. In addition to that, applying the fitted models to the validation dataset, model based on NG presented the highest accuracy, coefficient of determination (R<sup>2</sup>) of 0.70, mean absolute error (MAE) of 639.99 kg ha<sup>−1</sup> and root mean squared error (RMSE) of 726.67 kg ha<sup>−1</sup>. |
| first_indexed | 2024-03-10T17:38:26Z |
| format | Article |
| id | doaj.art-437e9c5aedb44f3bbaa9501b21e79858 |
| institution | Directory Open Access Journal |
| issn | 2077-0472 |
| language | English |
| last_indexed | 2024-03-10T17:38:26Z |
| publishDate | 2020-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agriculture |
| spelling | doaj.art-437e9c5aedb44f3bbaa9501b21e798582023-11-20T09:46:25ZengMDPI AGAgriculture2077-04722020-08-0110834810.3390/agriculture10080348Soybean Yield Estimation and Its Components: A Linear Regression ApproachMarcelo Chan Fu Wei0José Paulo Molin1College of Agriculture “Luiz de Queiroz”, University of Sao Paulo, 11 Padua Dias Avenue, Piracicaba 13418-900, BrazilCollege of Agriculture “Luiz de Queiroz”, University of Sao Paulo, 11 Padua Dias Avenue, Piracicaba 13418-900, BrazilSoybean yield estimation is either based on yield monitors or agro-meteorological and satellite imagery data, but they present several limiting factors regarding on-farm decision level. Aware that machine learning approaches have been largely applied to estimate soybean yield and the availability of data regarding soybean yield and its components (number of grains (NG) and thousand grains weight (TGW)), there is an opportunity to study their relationships. The objective was to explore the relationships between soybean yield and its components, generate equations to estimate yield and evaluate its prediction accuracy. The training dataset was composed of soybean yield and its components’ data from 2010 to 2019. Linear regression models based on NG, TGW and yield were fitted on the training dataset and applied to a validation dataset composed of 58 on-field collected samples. It was found that globally TGW and NG presented weak (r = 0.50) and strong (r = 0.92) linear relationships with yield, respectively. In addition to that, applying the fitted models to the validation dataset, model based on NG presented the highest accuracy, coefficient of determination (R<sup>2</sup>) of 0.70, mean absolute error (MAE) of 639.99 kg ha<sup>−1</sup> and root mean squared error (RMSE) of 726.67 kg ha<sup>−1</sup>.https://www.mdpi.com/2077-0472/10/8/348hundred grains weightmachine learningnumber of grainsprecision agriculturethousand grains weight |
| spellingShingle | Marcelo Chan Fu Wei José Paulo Molin Soybean Yield Estimation and Its Components: A Linear Regression Approach Agriculture hundred grains weight machine learning number of grains precision agriculture thousand grains weight |
| title | Soybean Yield Estimation and Its Components: A Linear Regression Approach |
| title_full | Soybean Yield Estimation and Its Components: A Linear Regression Approach |
| title_fullStr | Soybean Yield Estimation and Its Components: A Linear Regression Approach |
| title_full_unstemmed | Soybean Yield Estimation and Its Components: A Linear Regression Approach |
| title_short | Soybean Yield Estimation and Its Components: A Linear Regression Approach |
| title_sort | soybean yield estimation and its components a linear regression approach |
| topic | hundred grains weight machine learning number of grains precision agriculture thousand grains weight |
| url | https://www.mdpi.com/2077-0472/10/8/348 |
| work_keys_str_mv | AT marcelochanfuwei soybeanyieldestimationanditscomponentsalinearregressionapproach AT josepaulomolin soybeanyieldestimationanditscomponentsalinearregressionapproach |