No silver bullet for digital soil mapping: country-specific soil organic carbon estimates across Latin America
- Autores
- Guevara, Mario; Olmedo, Guillermo Federico; Stell, Emma; Yigini, Yusuf; Aguilar Duarte, Yameli; Arellano Hernández, Carlos; Arévalo, Gloria E.; Arroyo-Cruz, Carlos Eduardo; Bolivar, Adriana; Bunning, Sally; Bustamante Cañas, Nelson; Cruz-Gaistardo, Carlos Omar; Davila, Fabian; Dell Acqua, Martín; Encina, Arnulfo; Figueredo Tacona, Hernán; Fontes, Fernando; Hernández Herrera, José Antonio; Ibelles Navarro, Alejandro Roberto; Loayza, Verónica; Manueles, Alexandra; Mendoza Jara, Fernando; Olivera, Carolina; Osorio Hermosilla, Rodrigo; Pereira, Gonzalo; Prieto, Pablo; Ramos, Iván Alexis; Rey Brina, Juan Carlos; Rivera, Rafael; Rodríguez-Rodríguez, Javier; Roopnarine, Ronald; Rosales Ibarra, Albán; Rosales Riveiro, Kenset Amaury; Schulz, Guillermo Andres; Spence, Adrián; Vargas, Ronald R.; Vargas, Rodrigo; Vasques, Gustavo M.
- Año de publicación
- 2018
- Idioma
- inglés
- Tipo de recurso
- artículo
- Estado
- versión publicada
- Descripción
- Country-specific soil organic carbon (SOC) estimates are the baseline for the Global SOC Map of the Global Soil Partnership (GSOCmap-GSP). This endeavor is key to explaining the uncertainty of global SOC estimates but requires harmonizing heterogeneous datasets and building country-specific capacities for digital soil mapping (DSM).We identified country-specific predictors for SOC and tested the performance of five predictive algorithms for mapping SOC across Latin America. The algorithms included support vector machines (SVMs), random forest (RF), kernel-weighted nearest neighbors (KK), partial least squares regression (PL), and regression kriging based on stepwise multiple linear models (RK). Country-specific training data and SOC predictors (5 5 km pixel resolution) were obtained from ISRIC – World Soil Information. Temperature, soil type, vegetation indices, and topographic constraints were the best predictors for SOC, but country-specific predictors and their respective weights varied across Latin America. We compared a large diversity of country-specific datasets and models, and were able to explain SOC variability in a range between 1 and 60 %, with no universal predictive algorithm among countries. A regional (nD11 268 SOC estimates) ensemble of these five algorithms was able to explain 39% of SOC variability from repeated 5-fold cross-validation.We report a combined SOC stock of 77.8 43.6 Pg (uncertainty represented by the full conditional response of independent model residuals) across Latin America. SOC stocks were higher in tropical forests (30 16.5 Pg) and croplands (13 8.1 Pg). Country-specific and regional ensembles revealed spatial discrepancies across geopolitical borders, higher elevations, and coastal plains, but provided similar regional stocks (77.8 42.2 and 76.8 45.1 Pg, respectively). These results are conservative compared to global estimates (e.g., SoilGrids250m 185.8 Pg, the Harmonized World Soil Database 138.4 Pg, or the GSOCmap-GSP 99.7 Pg). Countries with large area (i.e., Brazil, Bolivia, Mexico, Peru) and large spatial SOC heterogeneity had lower SOC stocks per unit area and larger uncertainty in their predictions. We highlight that expert opinion is needed to set boundary prediction limits to avoid unrealistically high modeling estimates. For maximizing explained variance while minimizing prediction bias, the selection of predictive algorithms for SOC mapping should consider density of available data and variability of country-specific environmental gradients. This study highlights the large degree of spatial uncertainty in SOC estimates across Latin America. We provide a framework for improving country-specific mapping efforts and reducing current discrepancy of global, regional, and country-specific SOC estimates.
Fil: Guevara, Mario. Universidad de Delaware. Department of Plant and Soil Sciences; Estados Unidos
Fil: Olmedo, Guillermo Federico. Instituto Nacional de Tecnología Agropecuaria (INTA). Estación Experimental Agropecuaria Mendoza; Argentina. FAO; Italia
Fil: Stell; Emma. University of Delaware, Department of Plant and Soil Sciences; Estados Unidos
Fil: Yigini, Yusuf. FAO; Italia
Fil: Aguilar Duarte, Yameli. Instituto Nacional de Investigaciones Forestales, Agrícolas y Pecuarias; México
Fil: Arellano Hernández, Carlos. Instituto Nacional de Estadísitica y Geografía; México
Fil: Arévalo, Gloria E. Zamorano. University of Honduras and Asociación Hondureña de la Ciencia del Suelo; Honduras
Fil: Arroyo-Cruz, Carlos Eduardo. National Commission for the Knowledge and Use of Biodiversity; México
Fil: Bolivar, Adriana. Instituto Geográfico Agustín Codazzi. Subdirección Agrología; Colombia
Fil: Bunning, Sally. FAO. Oficina Regional para América Latina y el Caribe; Chile
Fil: Bustamante Cañas, Nelson. Servicio Agrícola y Ganadero; Chile
Fil: Cruz-Gaistardo, Carlos Omar. Instituto Nacional de Estadísitica y Geografía; México
Dell Acqua, Martín. Ministerio de Ganadería, Agricultura y Pesca. Dirección General de Recursos Naturales; Uruguay
Fil: Encina, Arnulfo. Universidad Nacional de Asunción. Facultad de Ciencias Agrarias; Paraguay
Fil: Figueredo Tacona, Hernán. Ministry of Rural Development and Land. Land Viceministry; Bolivia
Fil: Fontes, Fernando. Ministerio de Ganadería, Agricultura y Pesca. Dirección General de Recursos Naturales; Uruguay
Fil: Hernández Herrera, José Antonio. Universidad Autónoma Agraria Antonio Narro. Unidad Laguna; México
Fil: Ibelles Navarro, Alejandro Roberto. Instituto Nacional de Estadísitica y Geografía; México
Fil: Loayza, Verónica. Ministerio de Agricultura y Ganaderia; Ecuador
Fil: Manueles, Alexandra M.. Zamorano University of Honduras and Asociación Hondureña de la Ciencia del Suelo; Honduras
Fil: Mendoza Jara, Fernando . Universidad Nacional Agraria; Nicaragua
Fil: Olivera, Carolina. FAO. Oficina Regional para América Latina y el Caribe; Colombia
Fil: Osorio Hermosilla, Rodrigo. Servicio Agrícola y Ganadero; Chile
Fil: Pereira, Gonzalo. Ministerio de Ganadería, Agricultura y Pesca. Dirección General de Recursos Naturales; Uruguay
Fil: Prieto, Pablo. Ministerio de Ganadería, Agricultura y Pesca. Dirección General de Recursos Naturales; Uruguay
Fil: Ramos, Iván Alexis . Instituto de Investigación Agropecuaria de Panamá; Panamá
Fil: Rey Brina, Juan Carlos. Sociedad Venezolana de la Ciencia del Suelo; Venezuela
Fil: Rivera, Rafael. Ministerio de Medio Ambiente; República Dominicana
Fil: Rodríguez-Rodríguez, Javier. National Commission for the Knowledge and Use of Biodiversity; México
Fil: Roopnarine, Ronald. Department of Natural and Life Sciences. COSTAATT; Trinidad y Tobago
Fil: Rosales Ibarra, Albán. Instituto de Innovación en Transferencia y Tecnología Agropecuaria; Costa Rica
Fil: Rosales Riveiro, Kenset Amaury. Ministerio de Ambiente y Recursos Naturales de Guatemala; Guatemala
Fil: Schulz, Guillermo Andrés. Instituto Nacional de Tecnología Agropecuaria (INTA). Instituto de Suelos; Argentina
Fil: Spence, Adrián. University of the West Indies. International Centre for Environmental and Nuclear Sciences; Jamaica
Fil: Vasques, Gustavo M. EMBRAPA Solos; Brasil
Fil: Vargas, Ronald R. FAO; Italia
Fil: Vargas, Rodrigo. University of Delaware. Department of Plant and Soil Sciences; Estados Unidos - Fuente
- Soil 4 (3) : 173-193 (Agosto 2018)
- Materia
-
Cartografía del Uso de la Tierra
Carbono Orgánico del Suelo
América Latina
Land Use Mapping
Soil Organic Carbon
Latin America
Soil
Suelo - Nivel de accesibilidad
- acceso abierto
- Condiciones de uso
- http://creativecommons.org/licenses/by-nc-sa/4.0/
- Repositorio
.jpg)
- Institución
- Instituto Nacional de Tecnología Agropecuaria
- OAI Identificador
- oai:localhost:20.500.12123/4788
Ver los metadatos del registro completo
| id |
INTADig_63b8d81d98f61e261ddcc98e0b5580ce |
|---|---|
| oai_identifier_str |
oai:localhost:20.500.12123/4788 |
| network_acronym_str |
INTADig |
| repository_id_str |
l |
| network_name_str |
INTA Digital (INTA) |
| spelling |
No silver bullet for digital soil mapping: country-specific soil organic carbon estimates across Latin AmericaGuevara, MarioOlmedo, Guillermo FedericoStell, EmmaYigini, YusufAguilar Duarte, YameliArellano Hernández, CarlosArévalo, Gloria E.Arroyo-Cruz, Carlos EduardoBolivar, AdrianaBunning, SallyBustamante Cañas, NelsonCruz-Gaistardo, Carlos OmarDavila, FabianDell Acqua, MartínEncina, ArnulfoFigueredo Tacona, HernánFontes, FernandoHernández Herrera, José AntonioIbelles Navarro, Alejandro RobertoLoayza, VerónicaManueles, AlexandraMendoza Jara, FernandoOlivera, CarolinaOsorio Hermosilla, RodrigoPereira, GonzaloPrieto, PabloRamos, Iván AlexisRey Brina, Juan CarlosRivera, RafaelRodríguez-Rodríguez, JavierRoopnarine, RonaldRosales Ibarra, AlbánRosales Riveiro, Kenset AmaurySchulz, Guillermo AndresSpence, AdriánVargas, Ronald R.Vargas, RodrigoVasques, Gustavo M.Cartografía del Uso de la TierraCarbono Orgánico del SueloAmérica LatinaLand Use MappingSoil Organic CarbonLatin AmericaSoilSueloCountry-specific soil organic carbon (SOC) estimates are the baseline for the Global SOC Map of the Global Soil Partnership (GSOCmap-GSP). This endeavor is key to explaining the uncertainty of global SOC estimates but requires harmonizing heterogeneous datasets and building country-specific capacities for digital soil mapping (DSM).We identified country-specific predictors for SOC and tested the performance of five predictive algorithms for mapping SOC across Latin America. The algorithms included support vector machines (SVMs), random forest (RF), kernel-weighted nearest neighbors (KK), partial least squares regression (PL), and regression kriging based on stepwise multiple linear models (RK). Country-specific training data and SOC predictors (5 5 km pixel resolution) were obtained from ISRIC – World Soil Information. Temperature, soil type, vegetation indices, and topographic constraints were the best predictors for SOC, but country-specific predictors and their respective weights varied across Latin America. We compared a large diversity of country-specific datasets and models, and were able to explain SOC variability in a range between 1 and 60 %, with no universal predictive algorithm among countries. A regional (nD11 268 SOC estimates) ensemble of these five algorithms was able to explain 39% of SOC variability from repeated 5-fold cross-validation.We report a combined SOC stock of 77.8 43.6 Pg (uncertainty represented by the full conditional response of independent model residuals) across Latin America. SOC stocks were higher in tropical forests (30 16.5 Pg) and croplands (13 8.1 Pg). Country-specific and regional ensembles revealed spatial discrepancies across geopolitical borders, higher elevations, and coastal plains, but provided similar regional stocks (77.8 42.2 and 76.8 45.1 Pg, respectively). These results are conservative compared to global estimates (e.g., SoilGrids250m 185.8 Pg, the Harmonized World Soil Database 138.4 Pg, or the GSOCmap-GSP 99.7 Pg). Countries with large area (i.e., Brazil, Bolivia, Mexico, Peru) and large spatial SOC heterogeneity had lower SOC stocks per unit area and larger uncertainty in their predictions. We highlight that expert opinion is needed to set boundary prediction limits to avoid unrealistically high modeling estimates. For maximizing explained variance while minimizing prediction bias, the selection of predictive algorithms for SOC mapping should consider density of available data and variability of country-specific environmental gradients. This study highlights the large degree of spatial uncertainty in SOC estimates across Latin America. We provide a framework for improving country-specific mapping efforts and reducing current discrepancy of global, regional, and country-specific SOC estimates.Fil: Guevara, Mario. Universidad de Delaware. Department of Plant and Soil Sciences; Estados UnidosFil: Olmedo, Guillermo Federico. Instituto Nacional de Tecnología Agropecuaria (INTA). Estación Experimental Agropecuaria Mendoza; Argentina. FAO; ItaliaFil: Stell; Emma. University of Delaware, Department of Plant and Soil Sciences; Estados UnidosFil: Yigini, Yusuf. FAO; ItaliaFil: Aguilar Duarte, Yameli. Instituto Nacional de Investigaciones Forestales, Agrícolas y Pecuarias; MéxicoFil: Arellano Hernández, Carlos. Instituto Nacional de Estadísitica y Geografía; MéxicoFil: Arévalo, Gloria E. Zamorano. University of Honduras and Asociación Hondureña de la Ciencia del Suelo; HondurasFil: Arroyo-Cruz, Carlos Eduardo. National Commission for the Knowledge and Use of Biodiversity; MéxicoFil: Bolivar, Adriana. Instituto Geográfico Agustín Codazzi. Subdirección Agrología; ColombiaFil: Bunning, Sally. FAO. Oficina Regional para América Latina y el Caribe; ChileFil: Bustamante Cañas, Nelson. Servicio Agrícola y Ganadero; ChileFil: Cruz-Gaistardo, Carlos Omar. Instituto Nacional de Estadísitica y Geografía; MéxicoDell Acqua, Martín. Ministerio de Ganadería, Agricultura y Pesca. Dirección General de Recursos Naturales; UruguayFil: Encina, Arnulfo. Universidad Nacional de Asunción. Facultad de Ciencias Agrarias; ParaguayFil: Figueredo Tacona, Hernán. Ministry of Rural Development and Land. Land Viceministry; BoliviaFil: Fontes, Fernando. Ministerio de Ganadería, Agricultura y Pesca. Dirección General de Recursos Naturales; UruguayFil: Hernández Herrera, José Antonio. Universidad Autónoma Agraria Antonio Narro. Unidad Laguna; MéxicoFil: Ibelles Navarro, Alejandro Roberto. Instituto Nacional de Estadísitica y Geografía; MéxicoFil: Loayza, Verónica. Ministerio de Agricultura y Ganaderia; EcuadorFil: Manueles, Alexandra M.. Zamorano University of Honduras and Asociación Hondureña de la Ciencia del Suelo; HondurasFil: Mendoza Jara, Fernando . Universidad Nacional Agraria; NicaraguaFil: Olivera, Carolina. FAO. Oficina Regional para América Latina y el Caribe; ColombiaFil: Osorio Hermosilla, Rodrigo. Servicio Agrícola y Ganadero; ChileFil: Pereira, Gonzalo. Ministerio de Ganadería, Agricultura y Pesca. Dirección General de Recursos Naturales; UruguayFil: Prieto, Pablo. Ministerio de Ganadería, Agricultura y Pesca. Dirección General de Recursos Naturales; UruguayFil: Ramos, Iván Alexis . Instituto de Investigación Agropecuaria de Panamá; PanamáFil: Rey Brina, Juan Carlos. Sociedad Venezolana de la Ciencia del Suelo; VenezuelaFil: Rivera, Rafael. Ministerio de Medio Ambiente; República DominicanaFil: Rodríguez-Rodríguez, Javier. National Commission for the Knowledge and Use of Biodiversity; MéxicoFil: Roopnarine, Ronald. Department of Natural and Life Sciences. COSTAATT; Trinidad y TobagoFil: Rosales Ibarra, Albán. Instituto de Innovación en Transferencia y Tecnología Agropecuaria; Costa RicaFil: Rosales Riveiro, Kenset Amaury. Ministerio de Ambiente y Recursos Naturales de Guatemala; GuatemalaFil: Schulz, Guillermo Andrés. Instituto Nacional de Tecnología Agropecuaria (INTA). Instituto de Suelos; ArgentinaFil: Spence, Adrián. University of the West Indies. International Centre for Environmental and Nuclear Sciences; JamaicaFil: Vasques, Gustavo M. EMBRAPA Solos; BrasilFil: Vargas, Ronald R. FAO; ItaliaFil: Vargas, Rodrigo. University of Delaware. Department of Plant and Soil Sciences; Estados Unidos2019-04-01T10:58:05Z2019-04-01T10:58:05Z2018-08info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfhttp://hdl.handle.net/20.500.12123/4788https://www.soil-journal.net/4/173/2018/https://doi.org/10.5194/soil-4-173-2018Soil 4 (3) : 173-193 (Agosto 2018)reponame:INTA Digital (INTA)instname:Instituto Nacional de Tecnología Agropecuariaenginfo:eu-repograntAgreement/INTA/PNSUELO/1134032/AR./Bases conceptuales y nuevas herramientas para la cartografía de suelos.info:eu-repo/semantics/openAccesshttp://creativecommons.org/licenses/by-nc-sa/4.0/Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)2025-10-16T09:29:29Zoai:localhost:20.500.12123/4788instacron:INTAInstitucionalhttp://repositorio.inta.gob.ar/Organismo científico-tecnológicoNo correspondehttp://repositorio.inta.gob.ar/oai/requesttripaldi.nicolas@inta.gob.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:l2025-10-16 09:29:29.59INTA Digital (INTA) - Instituto Nacional de Tecnología Agropecuariafalse |
| dc.title.none.fl_str_mv |
No silver bullet for digital soil mapping: country-specific soil organic carbon estimates across Latin America |
| title |
No silver bullet for digital soil mapping: country-specific soil organic carbon estimates across Latin America |
| spellingShingle |
No silver bullet for digital soil mapping: country-specific soil organic carbon estimates across Latin America Guevara, Mario Cartografía del Uso de la Tierra Carbono Orgánico del Suelo América Latina Land Use Mapping Soil Organic Carbon Latin America Soil Suelo |
| title_short |
No silver bullet for digital soil mapping: country-specific soil organic carbon estimates across Latin America |
| title_full |
No silver bullet for digital soil mapping: country-specific soil organic carbon estimates across Latin America |
| title_fullStr |
No silver bullet for digital soil mapping: country-specific soil organic carbon estimates across Latin America |
| title_full_unstemmed |
No silver bullet for digital soil mapping: country-specific soil organic carbon estimates across Latin America |
| title_sort |
No silver bullet for digital soil mapping: country-specific soil organic carbon estimates across Latin America |
| dc.creator.none.fl_str_mv |
Guevara, Mario Olmedo, Guillermo Federico Stell, Emma Yigini, Yusuf Aguilar Duarte, Yameli Arellano Hernández, Carlos Arévalo, Gloria E. Arroyo-Cruz, Carlos Eduardo Bolivar, Adriana Bunning, Sally Bustamante Cañas, Nelson Cruz-Gaistardo, Carlos Omar Davila, Fabian Dell Acqua, Martín Encina, Arnulfo Figueredo Tacona, Hernán Fontes, Fernando Hernández Herrera, José Antonio Ibelles Navarro, Alejandro Roberto Loayza, Verónica Manueles, Alexandra Mendoza Jara, Fernando Olivera, Carolina Osorio Hermosilla, Rodrigo Pereira, Gonzalo Prieto, Pablo Ramos, Iván Alexis Rey Brina, Juan Carlos Rivera, Rafael Rodríguez-Rodríguez, Javier Roopnarine, Ronald Rosales Ibarra, Albán Rosales Riveiro, Kenset Amaury Schulz, Guillermo Andres Spence, Adrián Vargas, Ronald R. Vargas, Rodrigo Vasques, Gustavo M. |
| author |
Guevara, Mario |
| author_facet |
Guevara, Mario Olmedo, Guillermo Federico Stell, Emma Yigini, Yusuf Aguilar Duarte, Yameli Arellano Hernández, Carlos Arévalo, Gloria E. Arroyo-Cruz, Carlos Eduardo Bolivar, Adriana Bunning, Sally Bustamante Cañas, Nelson Cruz-Gaistardo, Carlos Omar Davila, Fabian Dell Acqua, Martín Encina, Arnulfo Figueredo Tacona, Hernán Fontes, Fernando Hernández Herrera, José Antonio Ibelles Navarro, Alejandro Roberto Loayza, Verónica Manueles, Alexandra Mendoza Jara, Fernando Olivera, Carolina Osorio Hermosilla, Rodrigo Pereira, Gonzalo Prieto, Pablo Ramos, Iván Alexis Rey Brina, Juan Carlos Rivera, Rafael Rodríguez-Rodríguez, Javier Roopnarine, Ronald Rosales Ibarra, Albán Rosales Riveiro, Kenset Amaury Schulz, Guillermo Andres Spence, Adrián Vargas, Ronald R. Vargas, Rodrigo Vasques, Gustavo M. |
| author_role |
author |
| author2 |
Olmedo, Guillermo Federico Stell, Emma Yigini, Yusuf Aguilar Duarte, Yameli Arellano Hernández, Carlos Arévalo, Gloria E. Arroyo-Cruz, Carlos Eduardo Bolivar, Adriana Bunning, Sally Bustamante Cañas, Nelson Cruz-Gaistardo, Carlos Omar Davila, Fabian Dell Acqua, Martín Encina, Arnulfo Figueredo Tacona, Hernán Fontes, Fernando Hernández Herrera, José Antonio Ibelles Navarro, Alejandro Roberto Loayza, Verónica Manueles, Alexandra Mendoza Jara, Fernando Olivera, Carolina Osorio Hermosilla, Rodrigo Pereira, Gonzalo Prieto, Pablo Ramos, Iván Alexis Rey Brina, Juan Carlos Rivera, Rafael Rodríguez-Rodríguez, Javier Roopnarine, Ronald Rosales Ibarra, Albán Rosales Riveiro, Kenset Amaury Schulz, Guillermo Andres Spence, Adrián Vargas, Ronald R. Vargas, Rodrigo Vasques, Gustavo M. |
| author2_role |
author author author author author author author author author author author author author author author author author author author author author author author author author author author author author author author author author author author author author |
| dc.subject.none.fl_str_mv |
Cartografía del Uso de la Tierra Carbono Orgánico del Suelo América Latina Land Use Mapping Soil Organic Carbon Latin America Soil Suelo |
| topic |
Cartografía del Uso de la Tierra Carbono Orgánico del Suelo América Latina Land Use Mapping Soil Organic Carbon Latin America Soil Suelo |
| dc.description.none.fl_txt_mv |
Country-specific soil organic carbon (SOC) estimates are the baseline for the Global SOC Map of the Global Soil Partnership (GSOCmap-GSP). This endeavor is key to explaining the uncertainty of global SOC estimates but requires harmonizing heterogeneous datasets and building country-specific capacities for digital soil mapping (DSM).We identified country-specific predictors for SOC and tested the performance of five predictive algorithms for mapping SOC across Latin America. The algorithms included support vector machines (SVMs), random forest (RF), kernel-weighted nearest neighbors (KK), partial least squares regression (PL), and regression kriging based on stepwise multiple linear models (RK). Country-specific training data and SOC predictors (5 5 km pixel resolution) were obtained from ISRIC – World Soil Information. Temperature, soil type, vegetation indices, and topographic constraints were the best predictors for SOC, but country-specific predictors and their respective weights varied across Latin America. We compared a large diversity of country-specific datasets and models, and were able to explain SOC variability in a range between 1 and 60 %, with no universal predictive algorithm among countries. A regional (nD11 268 SOC estimates) ensemble of these five algorithms was able to explain 39% of SOC variability from repeated 5-fold cross-validation.We report a combined SOC stock of 77.8 43.6 Pg (uncertainty represented by the full conditional response of independent model residuals) across Latin America. SOC stocks were higher in tropical forests (30 16.5 Pg) and croplands (13 8.1 Pg). Country-specific and regional ensembles revealed spatial discrepancies across geopolitical borders, higher elevations, and coastal plains, but provided similar regional stocks (77.8 42.2 and 76.8 45.1 Pg, respectively). These results are conservative compared to global estimates (e.g., SoilGrids250m 185.8 Pg, the Harmonized World Soil Database 138.4 Pg, or the GSOCmap-GSP 99.7 Pg). Countries with large area (i.e., Brazil, Bolivia, Mexico, Peru) and large spatial SOC heterogeneity had lower SOC stocks per unit area and larger uncertainty in their predictions. We highlight that expert opinion is needed to set boundary prediction limits to avoid unrealistically high modeling estimates. For maximizing explained variance while minimizing prediction bias, the selection of predictive algorithms for SOC mapping should consider density of available data and variability of country-specific environmental gradients. This study highlights the large degree of spatial uncertainty in SOC estimates across Latin America. We provide a framework for improving country-specific mapping efforts and reducing current discrepancy of global, regional, and country-specific SOC estimates. Fil: Guevara, Mario. Universidad de Delaware. Department of Plant and Soil Sciences; Estados Unidos Fil: Olmedo, Guillermo Federico. Instituto Nacional de Tecnología Agropecuaria (INTA). Estación Experimental Agropecuaria Mendoza; Argentina. FAO; Italia Fil: Stell; Emma. University of Delaware, Department of Plant and Soil Sciences; Estados Unidos Fil: Yigini, Yusuf. FAO; Italia Fil: Aguilar Duarte, Yameli. Instituto Nacional de Investigaciones Forestales, Agrícolas y Pecuarias; México Fil: Arellano Hernández, Carlos. Instituto Nacional de Estadísitica y Geografía; México Fil: Arévalo, Gloria E. Zamorano. University of Honduras and Asociación Hondureña de la Ciencia del Suelo; Honduras Fil: Arroyo-Cruz, Carlos Eduardo. National Commission for the Knowledge and Use of Biodiversity; México Fil: Bolivar, Adriana. Instituto Geográfico Agustín Codazzi. Subdirección Agrología; Colombia Fil: Bunning, Sally. FAO. Oficina Regional para América Latina y el Caribe; Chile Fil: Bustamante Cañas, Nelson. Servicio Agrícola y Ganadero; Chile Fil: Cruz-Gaistardo, Carlos Omar. Instituto Nacional de Estadísitica y Geografía; México Dell Acqua, Martín. Ministerio de Ganadería, Agricultura y Pesca. Dirección General de Recursos Naturales; Uruguay Fil: Encina, Arnulfo. Universidad Nacional de Asunción. Facultad de Ciencias Agrarias; Paraguay Fil: Figueredo Tacona, Hernán. Ministry of Rural Development and Land. Land Viceministry; Bolivia Fil: Fontes, Fernando. Ministerio de Ganadería, Agricultura y Pesca. Dirección General de Recursos Naturales; Uruguay Fil: Hernández Herrera, José Antonio. Universidad Autónoma Agraria Antonio Narro. Unidad Laguna; México Fil: Ibelles Navarro, Alejandro Roberto. Instituto Nacional de Estadísitica y Geografía; México Fil: Loayza, Verónica. Ministerio de Agricultura y Ganaderia; Ecuador Fil: Manueles, Alexandra M.. Zamorano University of Honduras and Asociación Hondureña de la Ciencia del Suelo; Honduras Fil: Mendoza Jara, Fernando . Universidad Nacional Agraria; Nicaragua Fil: Olivera, Carolina. FAO. Oficina Regional para América Latina y el Caribe; Colombia Fil: Osorio Hermosilla, Rodrigo. Servicio Agrícola y Ganadero; Chile Fil: Pereira, Gonzalo. Ministerio de Ganadería, Agricultura y Pesca. Dirección General de Recursos Naturales; Uruguay Fil: Prieto, Pablo. Ministerio de Ganadería, Agricultura y Pesca. Dirección General de Recursos Naturales; Uruguay Fil: Ramos, Iván Alexis . Instituto de Investigación Agropecuaria de Panamá; Panamá Fil: Rey Brina, Juan Carlos. Sociedad Venezolana de la Ciencia del Suelo; Venezuela Fil: Rivera, Rafael. Ministerio de Medio Ambiente; República Dominicana Fil: Rodríguez-Rodríguez, Javier. National Commission for the Knowledge and Use of Biodiversity; México Fil: Roopnarine, Ronald. Department of Natural and Life Sciences. COSTAATT; Trinidad y Tobago Fil: Rosales Ibarra, Albán. Instituto de Innovación en Transferencia y Tecnología Agropecuaria; Costa Rica Fil: Rosales Riveiro, Kenset Amaury. Ministerio de Ambiente y Recursos Naturales de Guatemala; Guatemala Fil: Schulz, Guillermo Andrés. Instituto Nacional de Tecnología Agropecuaria (INTA). Instituto de Suelos; Argentina Fil: Spence, Adrián. University of the West Indies. International Centre for Environmental and Nuclear Sciences; Jamaica Fil: Vasques, Gustavo M. EMBRAPA Solos; Brasil Fil: Vargas, Ronald R. FAO; Italia Fil: Vargas, Rodrigo. University of Delaware. Department of Plant and Soil Sciences; Estados Unidos |
| description |
Country-specific soil organic carbon (SOC) estimates are the baseline for the Global SOC Map of the Global Soil Partnership (GSOCmap-GSP). This endeavor is key to explaining the uncertainty of global SOC estimates but requires harmonizing heterogeneous datasets and building country-specific capacities for digital soil mapping (DSM).We identified country-specific predictors for SOC and tested the performance of five predictive algorithms for mapping SOC across Latin America. The algorithms included support vector machines (SVMs), random forest (RF), kernel-weighted nearest neighbors (KK), partial least squares regression (PL), and regression kriging based on stepwise multiple linear models (RK). Country-specific training data and SOC predictors (5 5 km pixel resolution) were obtained from ISRIC – World Soil Information. Temperature, soil type, vegetation indices, and topographic constraints were the best predictors for SOC, but country-specific predictors and their respective weights varied across Latin America. We compared a large diversity of country-specific datasets and models, and were able to explain SOC variability in a range between 1 and 60 %, with no universal predictive algorithm among countries. A regional (nD11 268 SOC estimates) ensemble of these five algorithms was able to explain 39% of SOC variability from repeated 5-fold cross-validation.We report a combined SOC stock of 77.8 43.6 Pg (uncertainty represented by the full conditional response of independent model residuals) across Latin America. SOC stocks were higher in tropical forests (30 16.5 Pg) and croplands (13 8.1 Pg). Country-specific and regional ensembles revealed spatial discrepancies across geopolitical borders, higher elevations, and coastal plains, but provided similar regional stocks (77.8 42.2 and 76.8 45.1 Pg, respectively). These results are conservative compared to global estimates (e.g., SoilGrids250m 185.8 Pg, the Harmonized World Soil Database 138.4 Pg, or the GSOCmap-GSP 99.7 Pg). Countries with large area (i.e., Brazil, Bolivia, Mexico, Peru) and large spatial SOC heterogeneity had lower SOC stocks per unit area and larger uncertainty in their predictions. We highlight that expert opinion is needed to set boundary prediction limits to avoid unrealistically high modeling estimates. For maximizing explained variance while minimizing prediction bias, the selection of predictive algorithms for SOC mapping should consider density of available data and variability of country-specific environmental gradients. This study highlights the large degree of spatial uncertainty in SOC estimates across Latin America. We provide a framework for improving country-specific mapping efforts and reducing current discrepancy of global, regional, and country-specific SOC estimates. |
| publishDate |
2018 |
| dc.date.none.fl_str_mv |
2018-08 2019-04-01T10:58:05Z 2019-04-01T10:58:05Z |
| dc.type.none.fl_str_mv |
info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion http://purl.org/coar/resource_type/c_6501 info:ar-repo/semantics/articulo |
| format |
article |
| status_str |
publishedVersion |
| dc.identifier.none.fl_str_mv |
http://hdl.handle.net/20.500.12123/4788 https://www.soil-journal.net/4/173/2018/ https://doi.org/10.5194/soil-4-173-2018 |
| url |
http://hdl.handle.net/20.500.12123/4788 https://www.soil-journal.net/4/173/2018/ https://doi.org/10.5194/soil-4-173-2018 |
| dc.language.none.fl_str_mv |
eng |
| language |
eng |
| dc.relation.none.fl_str_mv |
info:eu-repograntAgreement/INTA/PNSUELO/1134032/AR./Bases conceptuales y nuevas herramientas para la cartografía de suelos. |
| dc.rights.none.fl_str_mv |
info:eu-repo/semantics/openAccess http://creativecommons.org/licenses/by-nc-sa/4.0/ Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) |
| eu_rights_str_mv |
openAccess |
| rights_invalid_str_mv |
http://creativecommons.org/licenses/by-nc-sa/4.0/ Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) |
| dc.format.none.fl_str_mv |
application/pdf |
| dc.source.none.fl_str_mv |
Soil 4 (3) : 173-193 (Agosto 2018) reponame:INTA Digital (INTA) instname:Instituto Nacional de Tecnología Agropecuaria |
| reponame_str |
INTA Digital (INTA) |
| collection |
INTA Digital (INTA) |
| instname_str |
Instituto Nacional de Tecnología Agropecuaria |
| repository.name.fl_str_mv |
INTA Digital (INTA) - Instituto Nacional de Tecnología Agropecuaria |
| repository.mail.fl_str_mv |
tripaldi.nicolas@inta.gob.ar |
| _version_ |
1846143512642322432 |
| score |
12.712165 |