Using Random Forest to Improve the Downscaling of Global Livestock Census Data
Large scale, high-resolution global data on farm animal distributions are essential for spatially explicit assessments of the epidemiological, environmental and socio-economic impacts of the livestock sector. This has been the major motivation behind the development of the Gridded Livestock of the W...
| Autores principales: | , , , , , |
|---|---|
| Formato: | Journal Article |
| Lenguaje: | Inglés |
| Publicado: |
Public Library of Science
2016
|
| Materias: | |
| Acceso en línea: | https://hdl.handle.net/10568/129347 |
| _version_ | 1855521435435401216 |
|---|---|
| author | Nicolas, Gaëlle Robinson, Timothy P. Wint, G.R. William Conchedda, Giulia Cinardi, Giuseppina Gilbert, Marius |
| author_browse | Cinardi, Giuseppina Conchedda, Giulia Gilbert, Marius Nicolas, Gaëlle Robinson, Timothy P. Wint, G.R. William |
| author_facet | Nicolas, Gaëlle Robinson, Timothy P. Wint, G.R. William Conchedda, Giulia Cinardi, Giuseppina Gilbert, Marius |
| author_sort | Nicolas, Gaëlle |
| collection | Repository of Agricultural Research Outputs (CGSpace) |
| description | Large scale, high-resolution global data on farm animal distributions are essential for spatially explicit assessments of the epidemiological, environmental and socio-economic impacts of the livestock sector. This has been the major motivation behind the development of the Gridded Livestock of the World (GLW) database, which has been extensively used since its first publication in 2007. The database relies on a downscaling methodology whereby census counts of animals in sub-national administrative units are redistributed at the level of grid cells as a function of a series of spatial covariates. The recent upgrade of GLW1 to GLW2 involved automating the processing, improvement of input data, and downscaling at a spatial resolution of 1 km per cell (5 km per cell in the earlier version). The underlying statistical methodology, however, remained unchanged. In this paper, we evaluate new methods to downscale census data with a higher accuracy and increased processing efficiency. Two main factors were evaluated, based on sample census datasets of cattle in Africa and chickens in Asia. First, we implemented and evaluated Random Forest models (RF) instead of stratified regressions. Second, we investigated whether models that predicted the number of animals per rural person (per capita) could provide better downscaled estimates than the previous approach that predicted absolute densities (animals per km2). RF models consistently provided better predictions than the stratified regressions for both continents and species. The benefit of per capita over absolute density models varied according to the species and continent. In addition, different technical options were evaluated to reduce the processing time while maintaining their predictive power. Future GLW runs (GLW 3.0) will apply the new RF methodology with optimized modelling options. The potential benefit of per capita models will need to be further investigated with a better distinction between rural and agricultural populations. |
| format | Journal Article |
| id | CGSpace129347 |
| institution | CGIAR Consortium |
| language | Inglés |
| publishDate | 2016 |
| publishDateRange | 2016 |
| publishDateSort | 2016 |
| publisher | Public Library of Science |
| publisherStr | Public Library of Science |
| record_format | dspace |
| spelling | CGSpace1293472024-08-27T10:35:31Z Using Random Forest to Improve the Downscaling of Global Livestock Census Data Nicolas, Gaëlle Robinson, Timothy P. Wint, G.R. William Conchedda, Giulia Cinardi, Giuseppina Gilbert, Marius livestock data Large scale, high-resolution global data on farm animal distributions are essential for spatially explicit assessments of the epidemiological, environmental and socio-economic impacts of the livestock sector. This has been the major motivation behind the development of the Gridded Livestock of the World (GLW) database, which has been extensively used since its first publication in 2007. The database relies on a downscaling methodology whereby census counts of animals in sub-national administrative units are redistributed at the level of grid cells as a function of a series of spatial covariates. The recent upgrade of GLW1 to GLW2 involved automating the processing, improvement of input data, and downscaling at a spatial resolution of 1 km per cell (5 km per cell in the earlier version). The underlying statistical methodology, however, remained unchanged. In this paper, we evaluate new methods to downscale census data with a higher accuracy and increased processing efficiency. Two main factors were evaluated, based on sample census datasets of cattle in Africa and chickens in Asia. First, we implemented and evaluated Random Forest models (RF) instead of stratified regressions. Second, we investigated whether models that predicted the number of animals per rural person (per capita) could provide better downscaled estimates than the previous approach that predicted absolute densities (animals per km2). RF models consistently provided better predictions than the stratified regressions for both continents and species. The benefit of per capita over absolute density models varied according to the species and continent. In addition, different technical options were evaluated to reduce the processing time while maintaining their predictive power. Future GLW runs (GLW 3.0) will apply the new RF methodology with optimized modelling options. The potential benefit of per capita models will need to be further investigated with a better distinction between rural and agricultural populations. 2016-03-15 2023-03-10T14:33:33Z 2023-03-10T14:33:33Z Journal Article https://hdl.handle.net/10568/129347 en Open Access Public Library of Science Nicolas, Gaëlle; Robinson, Timothy P.; Wint, G.R. William; Conchedda, Giulia; Cinardi, Giuseppina; Gilbert, Marius. 2016. Using Random Forest to Improve the Downscaling of Global Livestock Census Data. PLOS ONE 11: e0150424 |
| spellingShingle | livestock data Nicolas, Gaëlle Robinson, Timothy P. Wint, G.R. William Conchedda, Giulia Cinardi, Giuseppina Gilbert, Marius Using Random Forest to Improve the Downscaling of Global Livestock Census Data |
| title | Using Random Forest to Improve the Downscaling of Global Livestock Census Data |
| title_full | Using Random Forest to Improve the Downscaling of Global Livestock Census Data |
| title_fullStr | Using Random Forest to Improve the Downscaling of Global Livestock Census Data |
| title_full_unstemmed | Using Random Forest to Improve the Downscaling of Global Livestock Census Data |
| title_short | Using Random Forest to Improve the Downscaling of Global Livestock Census Data |
| title_sort | using random forest to improve the downscaling of global livestock census data |
| topic | livestock data |
| url | https://hdl.handle.net/10568/129347 |
| work_keys_str_mv | AT nicolasgaelle usingrandomforesttoimprovethedownscalingofgloballivestockcensusdata AT robinsontimothyp usingrandomforesttoimprovethedownscalingofgloballivestockcensusdata AT wintgrwilliam usingrandomforesttoimprovethedownscalingofgloballivestockcensusdata AT concheddagiulia usingrandomforesttoimprovethedownscalingofgloballivestockcensusdata AT cinardigiuseppina usingrandomforesttoimprovethedownscalingofgloballivestockcensusdata AT gilbertmarius usingrandomforesttoimprovethedownscalingofgloballivestockcensusdata |