Machine learning in space and time for modelling soil organic carbon change
Spatially resolved estimates of change in soil organic carbon (SOC) stocks are necessary for supporting national and international policies aimed at achieving land degradation neutrality and climate change mitigation. In this work we report on the development, implementation and application of a dat...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | info:ar-repo/semantics/artículo |
| Language: | Inglés |
| Published: |
Wiley
2020
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/20.500.12123/8054 https://onlinelibrary.wiley.com/doi/full/10.1111/ejss.12998 https://doi.org/10.1111/ejss.12998 |
| _version_ | 1855035968269058048 |
|---|---|
| author | Heuvelink, Gerard B.M. Angelini, Marcos Esteban Poggio, Laura Bai, Zhanguo Batjes, Niels H. van den Bosch, Rik Bossio, Deborah Estella, Sergio Lehmann, Johannes Olmedo, Guillermo Federico Sanderman, Jonathan |
| author_browse | Angelini, Marcos Esteban Bai, Zhanguo Batjes, Niels H. Bossio, Deborah Estella, Sergio Heuvelink, Gerard B.M. Lehmann, Johannes Olmedo, Guillermo Federico Poggio, Laura Sanderman, Jonathan van den Bosch, Rik |
| author_facet | Heuvelink, Gerard B.M. Angelini, Marcos Esteban Poggio, Laura Bai, Zhanguo Batjes, Niels H. van den Bosch, Rik Bossio, Deborah Estella, Sergio Lehmann, Johannes Olmedo, Guillermo Federico Sanderman, Jonathan |
| author_sort | Heuvelink, Gerard B.M. |
| collection | INTA Digital |
| description | Spatially resolved estimates of change in soil organic carbon (SOC) stocks are necessary for supporting national and international policies aimed at achieving land degradation neutrality and climate change mitigation. In this work we report on the development, implementation and application of a data-driven, statistical method for mapping SOC stocks in space and time, using Argentina as a pilot. We used quantile regression forest machine learning to predict annual SOC stock at 0–30 cm depth at 250 m resolution for Argentina between 1982 and 2017. The model was calibrated using over 5,000 SOC stock values from the 36-year time period and 35 environmental covariates. We preprocessed normalized difference vegetation index (NDVI) dynamic covariates using a temporal low-pass filter to allow the SOC stock for a given year to depend on the NDVI of the current as well as preceding years. Predictions had modest temporal variation, with an average decrease for the entire country from 2.55 to 2.48 kg C m−2 over the 36-year period (equivalent to a decline of 211 Gg C, 3.0% of the total 0–30 cm SOC stock in Argentina). The Pampa region had a larger estimated SOC stock decrease from 4.62 to 4.34 kg C m−2 (5.9%) during the same period. For the 2001–2015 period, predicted temporal variation was seven-fold larger than that obtained using the Tier 1 approach of the Intergovernmental Panel on Climate Change and United Nations Convention to Combat Desertification. Prediction uncertainties turned out to be substantial, mainly due to the limited number and poor spatial and static, whereas SOC is dynamic and SOC dynamics are of particular interest to carbon sequestration and land degradation studies. Thus, there is a clear need to extend spatial SOC mapping to space–time SOC mapping.
temporal distribution of the calibration data, and the limited explanatory power of the covariates. Cross-validation confirmed that SOC stock prediction accuracy was limited, with a mean error of 0.03 kg C m−2 and a root mean squared error of 2.04 kg C m−2. In spite of the large uncertainties, this work showed that machine learning methods can be used for space–time SOC mapping and may yield valuable information to land managers and policymakers, provided that SOC observation density in space and time is sufficiently large. |
| format | info:ar-repo/semantics/artículo |
| id | INTA8054 |
| institution | Instituto Nacional de Tecnología Agropecuaria (INTA -Argentina) |
| language | Inglés |
| publishDate | 2020 |
| publishDateRange | 2020 |
| publishDateSort | 2020 |
| publisher | Wiley |
| publisherStr | Wiley |
| record_format | dspace |
| spelling | INTA80542020-10-15T11:47:31Z Machine learning in space and time for modelling soil organic carbon change Heuvelink, Gerard B.M. Angelini, Marcos Esteban Poggio, Laura Bai, Zhanguo Batjes, Niels H. van den Bosch, Rik Bossio, Deborah Estella, Sergio Lehmann, Johannes Olmedo, Guillermo Federico Sanderman, Jonathan Argentina Estimación de las Existencias de Carbono Cambio Climático Degradación de Tierras Carbon Stock Assessments Climate Change Land Degradation Quantile Regression Rorest Space-time Mapping Bosque de Regresión de Cuantiles Mapeo Espacio-tiempo Spatially resolved estimates of change in soil organic carbon (SOC) stocks are necessary for supporting national and international policies aimed at achieving land degradation neutrality and climate change mitigation. In this work we report on the development, implementation and application of a data-driven, statistical method for mapping SOC stocks in space and time, using Argentina as a pilot. We used quantile regression forest machine learning to predict annual SOC stock at 0–30 cm depth at 250 m resolution for Argentina between 1982 and 2017. The model was calibrated using over 5,000 SOC stock values from the 36-year time period and 35 environmental covariates. We preprocessed normalized difference vegetation index (NDVI) dynamic covariates using a temporal low-pass filter to allow the SOC stock for a given year to depend on the NDVI of the current as well as preceding years. Predictions had modest temporal variation, with an average decrease for the entire country from 2.55 to 2.48 kg C m−2 over the 36-year period (equivalent to a decline of 211 Gg C, 3.0% of the total 0–30 cm SOC stock in Argentina). The Pampa region had a larger estimated SOC stock decrease from 4.62 to 4.34 kg C m−2 (5.9%) during the same period. For the 2001–2015 period, predicted temporal variation was seven-fold larger than that obtained using the Tier 1 approach of the Intergovernmental Panel on Climate Change and United Nations Convention to Combat Desertification. Prediction uncertainties turned out to be substantial, mainly due to the limited number and poor spatial and static, whereas SOC is dynamic and SOC dynamics are of particular interest to carbon sequestration and land degradation studies. Thus, there is a clear need to extend spatial SOC mapping to space–time SOC mapping. temporal distribution of the calibration data, and the limited explanatory power of the covariates. Cross-validation confirmed that SOC stock prediction accuracy was limited, with a mean error of 0.03 kg C m−2 and a root mean squared error of 2.04 kg C m−2. In spite of the large uncertainties, this work showed that machine learning methods can be used for space–time SOC mapping and may yield valuable information to land managers and policymakers, provided that SOC observation density in space and time is sufficiently large. Fil: Heuvelink, Gerard B.M. ISRIC - World soil information; Holanda. Wageningen University. Soil Geography and Landscape Group; Holanda Fil: Angelici, Marcos E. Instituto Nacional de Tecnología Agropecuaria (INTA). Instituto de Suelos; Argentina Fil: Poggio, Laura ISRIC - World soil information, Wageningen; Holanda Fil: Bai, Zhanguo ISRIC - World soil information, Wageningen, The Netherlands Fil: Batjes, Niels H. ISRIC - World soil information, Wageningen, The Netherlands Fil: an den Bosch, Rik ISRIC - World soil information, Wageningen, The Netherlands Fil: Bossio, Deborah The Nature Conservancy; Estados Unidos Fil: Estella, Sergio Vizzuality; España Fil: Lehmann, Jhoannes. Cornell University. Soil and Crop Sciences; Estados Unidos Fil: Olmedo, Guillermo F. Instituto Nacional de Tecnología Agropecuaria (INTA). Estación Experimental Agropecuaria Mendoza; Argentina Fil: Sandermann, Jonathan. Woods Hole Research Center; Estados Unidos 2020-10-15T11:17:38Z 2020-10-15T11:17:38Z 2020-05-20 info:ar-repo/semantics/artículo info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion http://hdl.handle.net/20.500.12123/8054 https://onlinelibrary.wiley.com/doi/full/10.1111/ejss.12998 1365-2389 https://doi.org/10.1111/ejss.12998 eng 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) application/pdf Wiley European Journal of Soil Science : 1-17 (First published: 20 May 2020) |
| spellingShingle | Argentina Estimación de las Existencias de Carbono Cambio Climático Degradación de Tierras Carbon Stock Assessments Climate Change Land Degradation Quantile Regression Rorest Space-time Mapping Bosque de Regresión de Cuantiles Mapeo Espacio-tiempo Heuvelink, Gerard B.M. Angelini, Marcos Esteban Poggio, Laura Bai, Zhanguo Batjes, Niels H. van den Bosch, Rik Bossio, Deborah Estella, Sergio Lehmann, Johannes Olmedo, Guillermo Federico Sanderman, Jonathan Machine learning in space and time for modelling soil organic carbon change |
| title | Machine learning in space and time for modelling soil organic carbon change |
| title_full | Machine learning in space and time for modelling soil organic carbon change |
| title_fullStr | Machine learning in space and time for modelling soil organic carbon change |
| title_full_unstemmed | Machine learning in space and time for modelling soil organic carbon change |
| title_short | Machine learning in space and time for modelling soil organic carbon change |
| title_sort | machine learning in space and time for modelling soil organic carbon change |
| topic | Argentina Estimación de las Existencias de Carbono Cambio Climático Degradación de Tierras Carbon Stock Assessments Climate Change Land Degradation Quantile Regression Rorest Space-time Mapping Bosque de Regresión de Cuantiles Mapeo Espacio-tiempo |
| url | http://hdl.handle.net/20.500.12123/8054 https://onlinelibrary.wiley.com/doi/full/10.1111/ejss.12998 https://doi.org/10.1111/ejss.12998 |
| work_keys_str_mv | AT heuvelinkgerardbm machinelearninginspaceandtimeformodellingsoilorganiccarbonchange AT angelinimarcosesteban machinelearninginspaceandtimeformodellingsoilorganiccarbonchange AT poggiolaura machinelearninginspaceandtimeformodellingsoilorganiccarbonchange AT baizhanguo machinelearninginspaceandtimeformodellingsoilorganiccarbonchange AT batjesnielsh machinelearninginspaceandtimeformodellingsoilorganiccarbonchange AT vandenboschrik machinelearninginspaceandtimeformodellingsoilorganiccarbonchange AT bossiodeborah machinelearninginspaceandtimeformodellingsoilorganiccarbonchange AT estellasergio machinelearninginspaceandtimeformodellingsoilorganiccarbonchange AT lehmannjohannes machinelearninginspaceandtimeformodellingsoilorganiccarbonchange AT olmedoguillermofederico machinelearninginspaceandtimeformodellingsoilorganiccarbonchange AT sandermanjonathan machinelearninginspaceandtimeformodellingsoilorganiccarbonchange |