NextGen agroadvisory expanding in scope and extent: The effort to cover more crops and bundle with lime advisory
Accurate crop yield prediction is crucial for optimizing agricultural practices and ensuring food security. The NextGen advisory is a fertilizer recommendation system that can be customized for different farming systems, crop types, and locations. The system uses machine learning models to predict s...
| Autores principales: | , , , , , , , , , , |
|---|---|
| Formato: | Informe técnico |
| Lenguaje: | Inglés |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | https://hdl.handle.net/10568/134945 |
| _version_ | 1855524666062405632 |
|---|---|
| author | Tilaye, Asmalu Abera, Wuletawu Liben, Feyera Ali, Ashenafi Assefa, Feben Tibebe, Degefie Ebrahim, Mohammed Mesfin, Tewodros Erkossa, Teklu Chernet, Meklit Tamene, Lulseged D. |
| author_browse | Abera, Wuletawu Ali, Ashenafi Assefa, Feben Chernet, Meklit Ebrahim, Mohammed Erkossa, Teklu Liben, Feyera Mesfin, Tewodros Tamene, Lulseged D. Tibebe, Degefie Tilaye, Asmalu |
| author_facet | Tilaye, Asmalu Abera, Wuletawu Liben, Feyera Ali, Ashenafi Assefa, Feben Tibebe, Degefie Ebrahim, Mohammed Mesfin, Tewodros Erkossa, Teklu Chernet, Meklit Tamene, Lulseged D. |
| author_sort | Tilaye, Asmalu |
| collection | Repository of Agricultural Research Outputs (CGSpace) |
| description | Accurate crop yield prediction is crucial for optimizing agricultural practices and ensuring food security. The NextGen advisory is a fertilizer recommendation system that can be customized for different farming systems, crop types, and locations. The system uses machine learning models to predict site-specific fertilizer rates using filed trial and covariates (soil, topography, and climate) data. In this study, we investigated the effectiveness of four machine learning models – random forest, support vector machine (SVM), k-nearest neighbor (KNN), and classification and regression tree (CART) – in predicting crop yields for barley, maize, and teff in Ethiopia. We employed repeated cross-validation with 10 folds and 3 repeats for each model to evaluate their performance. The models were assessed using three metrics: mean absolute error (MAE), root mean square error (RMSE), and R-square (R2). Our evaluation demonstrated that the random forest model outperformed the other models for all crops based with an R-square with training 074, 0.74, 0.71 and testing 0.74, 0.76, and 0.72 for barely, maize and teff respectively. This suggests that the random forest algorithm effectively captured the complex relationships between input features and crop yield. We are currently collecting additional data on crop response to fertilizer for barley, maize, and teff, as well as other crops. This additional data will be incorporated into the model to further enhance its predictive capabilities. Additionally, the model's performance will be validated in the 2023/2024 season in collaboration with government and private sector actors. Digital Green, Lersha, and the Ministry of Agriculture (MoA) have expressed interest in piloting the advisory service on smaller sites while the validation process is ongoing. The system is also being used to develop site-specific lime recommendations for acidic soils. The lime advisory tool can help to improve fertilizer use efficiency, reduce fertilizer costs, enhance soil health, and reduce the environmental impact of agriculture. These benefits can lead to sustainable crop production and profit from investment in inorganic and organic fertilizers. |
| format | Informe técnico |
| id | CGSpace134945 |
| institution | CGIAR Consortium |
| language | Inglés |
| publishDate | 2023 |
| publishDateRange | 2023 |
| publishDateSort | 2023 |
| record_format | dspace |
| spelling | CGSpace1349452025-11-05T11:38:48Z NextGen agroadvisory expanding in scope and extent: The effort to cover more crops and bundle with lime advisory Tilaye, Asmalu Abera, Wuletawu Liben, Feyera Ali, Ashenafi Assefa, Feben Tibebe, Degefie Ebrahim, Mohammed Mesfin, Tewodros Erkossa, Teklu Chernet, Meklit Tamene, Lulseged D. agronomic practices advisory services modelling decision support systems bundling random forest, agroadvisory, nextgen, site-specific Accurate crop yield prediction is crucial for optimizing agricultural practices and ensuring food security. The NextGen advisory is a fertilizer recommendation system that can be customized for different farming systems, crop types, and locations. The system uses machine learning models to predict site-specific fertilizer rates using filed trial and covariates (soil, topography, and climate) data. In this study, we investigated the effectiveness of four machine learning models – random forest, support vector machine (SVM), k-nearest neighbor (KNN), and classification and regression tree (CART) – in predicting crop yields for barley, maize, and teff in Ethiopia. We employed repeated cross-validation with 10 folds and 3 repeats for each model to evaluate their performance. The models were assessed using three metrics: mean absolute error (MAE), root mean square error (RMSE), and R-square (R2). Our evaluation demonstrated that the random forest model outperformed the other models for all crops based with an R-square with training 074, 0.74, 0.71 and testing 0.74, 0.76, and 0.72 for barely, maize and teff respectively. This suggests that the random forest algorithm effectively captured the complex relationships between input features and crop yield. We are currently collecting additional data on crop response to fertilizer for barley, maize, and teff, as well as other crops. This additional data will be incorporated into the model to further enhance its predictive capabilities. Additionally, the model's performance will be validated in the 2023/2024 season in collaboration with government and private sector actors. Digital Green, Lersha, and the Ministry of Agriculture (MoA) have expressed interest in piloting the advisory service on smaller sites while the validation process is ongoing. The system is also being used to develop site-specific lime recommendations for acidic soils. The lime advisory tool can help to improve fertilizer use efficiency, reduce fertilizer costs, enhance soil health, and reduce the environmental impact of agriculture. These benefits can lead to sustainable crop production and profit from investment in inorganic and organic fertilizers. 2023-11-26 2023-12-04T12:46:39Z 2023-12-04T12:46:39Z Report https://hdl.handle.net/10568/134945 en Open Access application/pdf Tilaye, A.; Abera, W.; Liben, F.; Ali, A.; Assefa, F.; Tibebe, D.; Ebrahim, M.; Mesfin, T.; Erkossa, T.; Chernet, M.; Tamene, L. (2023) NextGen agroadvisory expanding in scope and extent: The effort to cover more crops and bundle with lime advisory. 13 p. |
| spellingShingle | agronomic practices advisory services modelling decision support systems bundling random forest, agroadvisory, nextgen, site-specific Tilaye, Asmalu Abera, Wuletawu Liben, Feyera Ali, Ashenafi Assefa, Feben Tibebe, Degefie Ebrahim, Mohammed Mesfin, Tewodros Erkossa, Teklu Chernet, Meklit Tamene, Lulseged D. NextGen agroadvisory expanding in scope and extent: The effort to cover more crops and bundle with lime advisory |
| title | NextGen agroadvisory expanding in scope and extent: The effort to cover more crops and bundle with lime advisory |
| title_full | NextGen agroadvisory expanding in scope and extent: The effort to cover more crops and bundle with lime advisory |
| title_fullStr | NextGen agroadvisory expanding in scope and extent: The effort to cover more crops and bundle with lime advisory |
| title_full_unstemmed | NextGen agroadvisory expanding in scope and extent: The effort to cover more crops and bundle with lime advisory |
| title_short | NextGen agroadvisory expanding in scope and extent: The effort to cover more crops and bundle with lime advisory |
| title_sort | nextgen agroadvisory expanding in scope and extent the effort to cover more crops and bundle with lime advisory |
| topic | agronomic practices advisory services modelling decision support systems bundling random forest, agroadvisory, nextgen, site-specific |
| url | https://hdl.handle.net/10568/134945 |
| work_keys_str_mv | AT tilayeasmalu nextgenagroadvisoryexpandinginscopeandextenttheefforttocovermorecropsandbundlewithlimeadvisory AT aberawuletawu nextgenagroadvisoryexpandinginscopeandextenttheefforttocovermorecropsandbundlewithlimeadvisory AT libenfeyera nextgenagroadvisoryexpandinginscopeandextenttheefforttocovermorecropsandbundlewithlimeadvisory AT aliashenafi nextgenagroadvisoryexpandinginscopeandextenttheefforttocovermorecropsandbundlewithlimeadvisory AT assefafeben nextgenagroadvisoryexpandinginscopeandextenttheefforttocovermorecropsandbundlewithlimeadvisory AT tibebedegefie nextgenagroadvisoryexpandinginscopeandextenttheefforttocovermorecropsandbundlewithlimeadvisory AT ebrahimmohammed nextgenagroadvisoryexpandinginscopeandextenttheefforttocovermorecropsandbundlewithlimeadvisory AT mesfintewodros nextgenagroadvisoryexpandinginscopeandextenttheefforttocovermorecropsandbundlewithlimeadvisory AT erkossateklu nextgenagroadvisoryexpandinginscopeandextenttheefforttocovermorecropsandbundlewithlimeadvisory AT chernetmeklit nextgenagroadvisoryexpandinginscopeandextenttheefforttocovermorecropsandbundlewithlimeadvisory AT tamenelulsegedd nextgenagroadvisoryexpandinginscopeandextenttheefforttocovermorecropsandbundlewithlimeadvisory |