Pixels to pasture: Using machine learning and multispectral remote sensing to predict biomass and nutrient quality in tropical grasslands
The livestock sector in rural Colombia is critical for employment and food security but is heavily affected by climate and its change. There is a need for solutions to address key challenges arising from vulnerabilities that impact the productivity and sustainability of forages and the livestock sec...
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Journal Article |
| Lenguaje: | Inglés |
| Publicado: |
Elsevier
2024
|
| Materias: | |
| Acceso en línea: | https://hdl.handle.net/10568/149009 |
| _version_ | 1855539048102232064 |
|---|---|
| author | Zwick, Mike Cardoso, Juan Andres Gutiérrez-Zapata, Diana María Cerón-Muñoz, Mario Gutiérrez, Jhon Freddy Raab, Christoph Jonsson, Nicholas Escobar, Miller Roberts, Kenny Barrett, Brian |
| author_browse | Barrett, Brian Cardoso, Juan Andres Cerón-Muñoz, Mario Escobar, Miller Gutiérrez, Jhon Freddy Gutiérrez-Zapata, Diana María Jonsson, Nicholas Raab, Christoph Roberts, Kenny Zwick, Mike |
| author_facet | Zwick, Mike Cardoso, Juan Andres Gutiérrez-Zapata, Diana María Cerón-Muñoz, Mario Gutiérrez, Jhon Freddy Raab, Christoph Jonsson, Nicholas Escobar, Miller Roberts, Kenny Barrett, Brian |
| author_sort | Zwick, Mike |
| collection | Repository of Agricultural Research Outputs (CGSpace) |
| description | The livestock sector in rural Colombia is critical for employment and food security but is heavily affected by climate and its change. There is a need for solutions to address key challenges arising from vulnerabilities that impact the productivity and sustainability of forages and the livestock sector. Increasing the yields of forage crops can improve the availability and affordability of livestock products while also easing the pressure on land resources. This study aims to develop remote sensing-based approaches for forage monitoring and biomass prediction in Colombia to support decision-making towards increased productivity, competitiveness and reduction of environmental impacts. Ten locations were sampled between 2018 and 2021 across climatically distinct areas in Colombia, comprising five farms in Patía in Cauca department, four farms in Antioquia department, and one research farm at Palmira in Valle de Cauca department. Ash content (Ash), crude protein (CP %), dry matter content (DM g/m2) and in-vitro digestibility (IVD %) were measured from Kikuyu and Brachiaria grasses during the field sampling campaigns. Multispectral bands from coincident Planetscope acquisitions along with various derived vegetation indices (VIs) were used as predictors in the model development. For each site and forage parameter, the importance of specific predictors varied, with the NIR band and Red-Green ratio generally performing best. To determine the optimum models, the effects of using a 1) averaging kernel, 2) feature selection approaches, 3) various regression algorithms and 4) meta learners (simple ensembling and stacks) were explored. Algorithms belonging to classes of commonly used models; Decision Trees, Support Vector Machines, Neural Networks, distance-based methods, and linear approaches were tested. The performance evaluation based on unseen test data revealed that CP and DM prediction performed moderately well for all three sites (R2 0.52 – 0.75, RMSE 1.7 – 2 % and R2 0.47 – 0.65, RMSE 182 – 112 g/m2 respectively). The best performing models varied by site and response variable, with Regularized Random Forest, Partial Least Squares, Random Forests, Bagged Multivariate Adaptive Regression and Bayesian Regularized Neural Networks being the top performing algorithms and Random Forest Stack being the best performing meta learner. The workflow and thorough analysis of performance affecting factors presented in this study can benefit timely grassland monitoring and biomass prediction at the local level and help contribute to the sustainable management of tropical grasslands in Colombia. |
| format | Journal Article |
| id | CGSpace149009 |
| institution | CGIAR Consortium |
| language | Inglés |
| publishDate | 2024 |
| publishDateRange | 2024 |
| publishDateSort | 2024 |
| publisher | Elsevier |
| publisherStr | Elsevier |
| record_format | dspace |
| spelling | CGSpace1490092025-11-11T19:05:33Z Pixels to pasture: Using machine learning and multispectral remote sensing to predict biomass and nutrient quality in tropical grasslands Zwick, Mike Cardoso, Juan Andres Gutiérrez-Zapata, Diana María Cerón-Muñoz, Mario Gutiérrez, Jhon Freddy Raab, Christoph Jonsson, Nicholas Escobar, Miller Roberts, Kenny Barrett, Brian machine learning monitoring and evaluation remote sensing forage biomass multispectral imagery grasslands The livestock sector in rural Colombia is critical for employment and food security but is heavily affected by climate and its change. There is a need for solutions to address key challenges arising from vulnerabilities that impact the productivity and sustainability of forages and the livestock sector. Increasing the yields of forage crops can improve the availability and affordability of livestock products while also easing the pressure on land resources. This study aims to develop remote sensing-based approaches for forage monitoring and biomass prediction in Colombia to support decision-making towards increased productivity, competitiveness and reduction of environmental impacts. Ten locations were sampled between 2018 and 2021 across climatically distinct areas in Colombia, comprising five farms in Patía in Cauca department, four farms in Antioquia department, and one research farm at Palmira in Valle de Cauca department. Ash content (Ash), crude protein (CP %), dry matter content (DM g/m2) and in-vitro digestibility (IVD %) were measured from Kikuyu and Brachiaria grasses during the field sampling campaigns. Multispectral bands from coincident Planetscope acquisitions along with various derived vegetation indices (VIs) were used as predictors in the model development. For each site and forage parameter, the importance of specific predictors varied, with the NIR band and Red-Green ratio generally performing best. To determine the optimum models, the effects of using a 1) averaging kernel, 2) feature selection approaches, 3) various regression algorithms and 4) meta learners (simple ensembling and stacks) were explored. Algorithms belonging to classes of commonly used models; Decision Trees, Support Vector Machines, Neural Networks, distance-based methods, and linear approaches were tested. The performance evaluation based on unseen test data revealed that CP and DM prediction performed moderately well for all three sites (R2 0.52 – 0.75, RMSE 1.7 – 2 % and R2 0.47 – 0.65, RMSE 182 – 112 g/m2 respectively). The best performing models varied by site and response variable, with Regularized Random Forest, Partial Least Squares, Random Forests, Bagged Multivariate Adaptive Regression and Bayesian Regularized Neural Networks being the top performing algorithms and Random Forest Stack being the best performing meta learner. The workflow and thorough analysis of performance affecting factors presented in this study can benefit timely grassland monitoring and biomass prediction at the local level and help contribute to the sustainable management of tropical grasslands in Colombia. 2024-11 2024-07-10T07:29:21Z 2024-07-10T07:29:21Z Journal Article https://hdl.handle.net/10568/149009 en Open Access application/pdf Elsevier Zwick, M.; Cardoso, J.A.; Gutiérrez-Zapata, D.M.; Cerón-Muñoz, M.; Gutiérrez, J.F.; Raab, C.; Jonsson, N.; Escobar, M.; Roberts, K.; Barrett, B. (2024) Pixels to pasture: Using machine learning and multispectral remote sensing to predict biomass and nutrient quality in tropical grasslands. Remote Sensing Applications: Society and Environment 36: 101282. ISSN: 2352-9385 |
| spellingShingle | machine learning monitoring and evaluation remote sensing forage biomass multispectral imagery grasslands Zwick, Mike Cardoso, Juan Andres Gutiérrez-Zapata, Diana María Cerón-Muñoz, Mario Gutiérrez, Jhon Freddy Raab, Christoph Jonsson, Nicholas Escobar, Miller Roberts, Kenny Barrett, Brian Pixels to pasture: Using machine learning and multispectral remote sensing to predict biomass and nutrient quality in tropical grasslands |
| title | Pixels to pasture: Using machine learning and multispectral remote sensing to predict biomass and nutrient quality in tropical grasslands |
| title_full | Pixels to pasture: Using machine learning and multispectral remote sensing to predict biomass and nutrient quality in tropical grasslands |
| title_fullStr | Pixels to pasture: Using machine learning and multispectral remote sensing to predict biomass and nutrient quality in tropical grasslands |
| title_full_unstemmed | Pixels to pasture: Using machine learning and multispectral remote sensing to predict biomass and nutrient quality in tropical grasslands |
| title_short | Pixels to pasture: Using machine learning and multispectral remote sensing to predict biomass and nutrient quality in tropical grasslands |
| title_sort | pixels to pasture using machine learning and multispectral remote sensing to predict biomass and nutrient quality in tropical grasslands |
| topic | machine learning monitoring and evaluation remote sensing forage biomass multispectral imagery grasslands |
| url | https://hdl.handle.net/10568/149009 |
| work_keys_str_mv | AT zwickmike pixelstopastureusingmachinelearningandmultispectralremotesensingtopredictbiomassandnutrientqualityintropicalgrasslands AT cardosojuanandres pixelstopastureusingmachinelearningandmultispectralremotesensingtopredictbiomassandnutrientqualityintropicalgrasslands AT gutierrezzapatadianamaria pixelstopastureusingmachinelearningandmultispectralremotesensingtopredictbiomassandnutrientqualityintropicalgrasslands AT ceronmunozmario pixelstopastureusingmachinelearningandmultispectralremotesensingtopredictbiomassandnutrientqualityintropicalgrasslands AT gutierrezjhonfreddy pixelstopastureusingmachinelearningandmultispectralremotesensingtopredictbiomassandnutrientqualityintropicalgrasslands AT raabchristoph pixelstopastureusingmachinelearningandmultispectralremotesensingtopredictbiomassandnutrientqualityintropicalgrasslands AT jonssonnicholas pixelstopastureusingmachinelearningandmultispectralremotesensingtopredictbiomassandnutrientqualityintropicalgrasslands AT escobarmiller pixelstopastureusingmachinelearningandmultispectralremotesensingtopredictbiomassandnutrientqualityintropicalgrasslands AT robertskenny pixelstopastureusingmachinelearningandmultispectralremotesensingtopredictbiomassandnutrientqualityintropicalgrasslands AT barrettbrian pixelstopastureusingmachinelearningandmultispectralremotesensingtopredictbiomassandnutrientqualityintropicalgrasslands |