Ensemble Modeling on Near-Infrared Spectra as Rapid Tool for Assessment of Soil Health Indicators for Sustainable Food Production Systems
A novel total ensemble (TE) algorithm was developed and compared with random forest optimization (RFO), gradient boosted machines (GBM), partial least squares (PLS), Cubist and Bayesian additive regression tree (BART) algorithms to predict numerous soil health indicators in soils with diverse climat...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Soil Systems |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2571-8789/5/4/69 |
| _version_ | 1797500502886318080 |
|---|---|
| author | John Walker Recha Kennedy O. Olale Andrew Sila Gebermedihin Ambaw Maren Radeny Dawit Solomon |
| author_facet | John Walker Recha Kennedy O. Olale Andrew Sila Gebermedihin Ambaw Maren Radeny Dawit Solomon |
| author_sort | John Walker Recha |
| collection | DOAJ |
| description | A novel total ensemble (TE) algorithm was developed and compared with random forest optimization (RFO), gradient boosted machines (GBM), partial least squares (PLS), Cubist and Bayesian additive regression tree (BART) algorithms to predict numerous soil health indicators in soils with diverse climate-smart land uses at different soil depths. The study investigated how land-use practices affect several soil health indicators. Good predictions using the ensemble method were obtained for total carbon (R<sup>2</sup> = 0.87; RMSE = 0.39; RPIQ = 1.36 and RPD = 1.51), total nitrogen (R<sup>2</sup> = 0.82; RMSE = 0.03; RPIQ = 2.00 and RPD = 1.60), and exchangeable bases, m3. Cu, m3. Fe, m3. B, m3. Mn, exchangeable Na, Ca (R<sup>2</sup> > 0.70). The performances of algorithms were in order of TE > Cubist > BART > PLS > GBM > RFO. Soil properties differed significantly among land uses and between soil depths. In Kenya, however, soil pH was not significant, except at depths of 45–100 cm, while the Fe levels in Tanzanian grassland were significantly high at all depths. Ugandan agroforestry had a substantially high concentration of ExCa at 0–15 cm. The total ensemble method showed better predictions as compared to other algorithms. Climate-smart land-use practices to preserve soil quality can be adopted for sustainable food production systems. |
| first_indexed | 2024-03-10T03:04:45Z |
| format | Article |
| id | doaj.art-54937cca26574c88982e384c25e0919e |
| institution | Directory Open Access Journal |
| issn | 2571-8789 |
| language | English |
| last_indexed | 2024-03-10T03:04:45Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Soil Systems |
| spelling | doaj.art-54937cca26574c88982e384c25e0919e2023-11-23T10:34:33ZengMDPI AGSoil Systems2571-87892021-11-01546910.3390/soilsystems5040069Ensemble Modeling on Near-Infrared Spectra as Rapid Tool for Assessment of Soil Health Indicators for Sustainable Food Production SystemsJohn Walker Recha0Kennedy O. Olale1Andrew Sila2Gebermedihin Ambaw3Maren Radeny4Dawit Solomon5CGIAR Research Program on Climate Change, Agriculture and Food Security (CCAFS) East Africa, International Livestock Research Institute (ILRI), Nairobi P.O. Box 30709-00100, KenyaDepartment of Chemistry, School of Pure and Applied Sciences, Kisii University, Kisii P.O. Box 408-40209, KenyaWorld Agroforestry (ICRAF), United Nations Avenue, Nairobi P.O. Box 30677-00100, KenyaCGIAR Research Program on Climate Change, Agriculture and Food Security (CCAFS) East Africa, International Livestock Research Institute (ILRI), Nairobi P.O. Box 30709-00100, KenyaCGIAR Research Program on Climate Change, Agriculture and Food Security (CCAFS) East Africa, International Livestock Research Institute (ILRI), Nairobi P.O. Box 30709-00100, KenyaCGIAR Research Program on Climate Change, Agriculture and Food Security (CCAFS) East Africa, International Livestock Research Institute (ILRI), Nairobi P.O. Box 30709-00100, KenyaA novel total ensemble (TE) algorithm was developed and compared with random forest optimization (RFO), gradient boosted machines (GBM), partial least squares (PLS), Cubist and Bayesian additive regression tree (BART) algorithms to predict numerous soil health indicators in soils with diverse climate-smart land uses at different soil depths. The study investigated how land-use practices affect several soil health indicators. Good predictions using the ensemble method were obtained for total carbon (R<sup>2</sup> = 0.87; RMSE = 0.39; RPIQ = 1.36 and RPD = 1.51), total nitrogen (R<sup>2</sup> = 0.82; RMSE = 0.03; RPIQ = 2.00 and RPD = 1.60), and exchangeable bases, m3. Cu, m3. Fe, m3. B, m3. Mn, exchangeable Na, Ca (R<sup>2</sup> > 0.70). The performances of algorithms were in order of TE > Cubist > BART > PLS > GBM > RFO. Soil properties differed significantly among land uses and between soil depths. In Kenya, however, soil pH was not significant, except at depths of 45–100 cm, while the Fe levels in Tanzanian grassland were significantly high at all depths. Ugandan agroforestry had a substantially high concentration of ExCa at 0–15 cm. The total ensemble method showed better predictions as compared to other algorithms. Climate-smart land-use practices to preserve soil quality can be adopted for sustainable food production systems.https://www.mdpi.com/2571-8789/5/4/69algorithmsclimate-smartsoil qualityland use |
| spellingShingle | John Walker Recha Kennedy O. Olale Andrew Sila Gebermedihin Ambaw Maren Radeny Dawit Solomon Ensemble Modeling on Near-Infrared Spectra as Rapid Tool for Assessment of Soil Health Indicators for Sustainable Food Production Systems Soil Systems algorithms climate-smart soil quality land use |
| title | Ensemble Modeling on Near-Infrared Spectra as Rapid Tool for Assessment of Soil Health Indicators for Sustainable Food Production Systems |
| title_full | Ensemble Modeling on Near-Infrared Spectra as Rapid Tool for Assessment of Soil Health Indicators for Sustainable Food Production Systems |
| title_fullStr | Ensemble Modeling on Near-Infrared Spectra as Rapid Tool for Assessment of Soil Health Indicators for Sustainable Food Production Systems |
| title_full_unstemmed | Ensemble Modeling on Near-Infrared Spectra as Rapid Tool for Assessment of Soil Health Indicators for Sustainable Food Production Systems |
| title_short | Ensemble Modeling on Near-Infrared Spectra as Rapid Tool for Assessment of Soil Health Indicators for Sustainable Food Production Systems |
| title_sort | ensemble modeling on near infrared spectra as rapid tool for assessment of soil health indicators for sustainable food production systems |
| topic | algorithms climate-smart soil quality land use |
| url | https://www.mdpi.com/2571-8789/5/4/69 |
| work_keys_str_mv | AT johnwalkerrecha ensemblemodelingonnearinfraredspectraasrapidtoolforassessmentofsoilhealthindicatorsforsustainablefoodproductionsystems AT kennedyoolale ensemblemodelingonnearinfraredspectraasrapidtoolforassessmentofsoilhealthindicatorsforsustainablefoodproductionsystems AT andrewsila ensemblemodelingonnearinfraredspectraasrapidtoolforassessmentofsoilhealthindicatorsforsustainablefoodproductionsystems AT gebermedihinambaw ensemblemodelingonnearinfraredspectraasrapidtoolforassessmentofsoilhealthindicatorsforsustainablefoodproductionsystems AT marenradeny ensemblemodelingonnearinfraredspectraasrapidtoolforassessmentofsoilhealthindicatorsforsustainablefoodproductionsystems AT dawitsolomon ensemblemodelingonnearinfraredspectraasrapidtoolforassessmentofsoilhealthindicatorsforsustainablefoodproductionsystems |