The Effect of Bioclimatic Covariates on Ensemble Machine Learning Prediction of Total Soil Carbon in the Pannonian Biogeoregion
This study employed an ensemble machine learning approach to evaluate the effect of bioclimatic covariates on the prediction accuracy of soil total carbon (TC) in the Pannonian biogeoregion. The analysis involved two main segments: (1) evaluation of base environmental covariates, including surface r...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Agronomy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4395/13/10/2516 |
| _version_ | 1827722056372846592 |
|---|---|
| author | Dorijan Radočaj Mladen Jurišić Vjekoslav Tadić |
| author_facet | Dorijan Radočaj Mladen Jurišić Vjekoslav Tadić |
| author_sort | Dorijan Radočaj |
| collection | DOAJ |
| description | This study employed an ensemble machine learning approach to evaluate the effect of bioclimatic covariates on the prediction accuracy of soil total carbon (TC) in the Pannonian biogeoregion. The analysis involved two main segments: (1) evaluation of base environmental covariates, including surface reflectance, phenology, and derived covariates, compared to the addition of bioclimatic covariates; and (2) assessment of three individual machine learning methods, including random forest (RF), extreme gradient boosting (XGB), and support vector machine (SVM), as well as their ensemble for soil TC prediction. Among the evaluated machine learning methods, the ensemble approach resulted in the highest prediction accuracy overall, outperforming the individual models. The ensemble method with bioclimatic covariates achieved an R<sup>2</sup> of 0.580 and an RMSE of 10.392, demonstrating its effectiveness in capturing complex relationships among environmental covariates. The results of this study suggest that the ensemble model consistently outperforms individual machine learning methods (RF, XGB, and SVM), and adding bioclimatic covariates improves the predictive performance of all methods. The study highlights the importance of integrating bioclimatic covariates when modeling environmental covariates and demonstrates the benefits of ensemble machine learning for the geospatial prediction of soil TC. |
| first_indexed | 2024-03-10T21:30:20Z |
| format | Article |
| id | doaj.art-6a830e1b6f65455e8b1425bb98beb30f |
| institution | Directory Open Access Journal |
| issn | 2073-4395 |
| language | English |
| last_indexed | 2024-03-10T21:30:20Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agronomy |
| spelling | doaj.art-6a830e1b6f65455e8b1425bb98beb30f2023-11-19T15:21:18ZengMDPI AGAgronomy2073-43952023-09-011310251610.3390/agronomy13102516The Effect of Bioclimatic Covariates on Ensemble Machine Learning Prediction of Total Soil Carbon in the Pannonian BiogeoregionDorijan Radočaj0Mladen Jurišić1Vjekoslav Tadić2Faculty of Agrobiotechnical Sciences Osijek, Josip Juraj Strossmayer University of Osijek, Vladimira Preloga 1, 31000 Osijek, CroatiaFaculty of Agrobiotechnical Sciences Osijek, Josip Juraj Strossmayer University of Osijek, Vladimira Preloga 1, 31000 Osijek, CroatiaFaculty of Agrobiotechnical Sciences Osijek, Josip Juraj Strossmayer University of Osijek, Vladimira Preloga 1, 31000 Osijek, CroatiaThis study employed an ensemble machine learning approach to evaluate the effect of bioclimatic covariates on the prediction accuracy of soil total carbon (TC) in the Pannonian biogeoregion. The analysis involved two main segments: (1) evaluation of base environmental covariates, including surface reflectance, phenology, and derived covariates, compared to the addition of bioclimatic covariates; and (2) assessment of three individual machine learning methods, including random forest (RF), extreme gradient boosting (XGB), and support vector machine (SVM), as well as their ensemble for soil TC prediction. Among the evaluated machine learning methods, the ensemble approach resulted in the highest prediction accuracy overall, outperforming the individual models. The ensemble method with bioclimatic covariates achieved an R<sup>2</sup> of 0.580 and an RMSE of 10.392, demonstrating its effectiveness in capturing complex relationships among environmental covariates. The results of this study suggest that the ensemble model consistently outperforms individual machine learning methods (RF, XGB, and SVM), and adding bioclimatic covariates improves the predictive performance of all methods. The study highlights the importance of integrating bioclimatic covariates when modeling environmental covariates and demonstrates the benefits of ensemble machine learning for the geospatial prediction of soil TC.https://www.mdpi.com/2073-4395/13/10/2516WorldClimGEMASremote sensingenvironmental covariateshyperparameter tuning |
| spellingShingle | Dorijan Radočaj Mladen Jurišić Vjekoslav Tadić The Effect of Bioclimatic Covariates on Ensemble Machine Learning Prediction of Total Soil Carbon in the Pannonian Biogeoregion Agronomy WorldClim GEMAS remote sensing environmental covariates hyperparameter tuning |
| title | The Effect of Bioclimatic Covariates on Ensemble Machine Learning Prediction of Total Soil Carbon in the Pannonian Biogeoregion |
| title_full | The Effect of Bioclimatic Covariates on Ensemble Machine Learning Prediction of Total Soil Carbon in the Pannonian Biogeoregion |
| title_fullStr | The Effect of Bioclimatic Covariates on Ensemble Machine Learning Prediction of Total Soil Carbon in the Pannonian Biogeoregion |
| title_full_unstemmed | The Effect of Bioclimatic Covariates on Ensemble Machine Learning Prediction of Total Soil Carbon in the Pannonian Biogeoregion |
| title_short | The Effect of Bioclimatic Covariates on Ensemble Machine Learning Prediction of Total Soil Carbon in the Pannonian Biogeoregion |
| title_sort | effect of bioclimatic covariates on ensemble machine learning prediction of total soil carbon in the pannonian biogeoregion |
| topic | WorldClim GEMAS remote sensing environmental covariates hyperparameter tuning |
| url | https://www.mdpi.com/2073-4395/13/10/2516 |
| work_keys_str_mv | AT dorijanradocaj theeffectofbioclimaticcovariatesonensemblemachinelearningpredictionoftotalsoilcarboninthepannonianbiogeoregion AT mladenjurisic theeffectofbioclimaticcovariatesonensemblemachinelearningpredictionoftotalsoilcarboninthepannonianbiogeoregion AT vjekoslavtadic theeffectofbioclimaticcovariatesonensemblemachinelearningpredictionoftotalsoilcarboninthepannonianbiogeoregion AT dorijanradocaj effectofbioclimaticcovariatesonensemblemachinelearningpredictionoftotalsoilcarboninthepannonianbiogeoregion AT mladenjurisic effectofbioclimaticcovariatesonensemblemachinelearningpredictionoftotalsoilcarboninthepannonianbiogeoregion AT vjekoslavtadic effectofbioclimaticcovariatesonensemblemachinelearningpredictionoftotalsoilcarboninthepannonianbiogeoregion |