A map of global peatland extent created using machine learning (Peat-ML)
Peatlands store large amounts of soil carbon and freshwater, constituting an important component of the global carbon and hydrologic cycles. Accurate information on the global extent and distribution of peatlands is presently lacking but is needed by Earth system models (ESMs) to simulate the effect...
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Journal Article |
| Lenguaje: | Inglés |
| Publicado: |
Copernicus GmbH
2022
|
| Materias: | |
| Acceso en línea: | https://hdl.handle.net/10568/119957 |
| _version_ | 1855539273296510976 |
|---|---|
| author | Melton, Joe R. Chan, Ed Millard, Koreen Fortier, Matthew Winton, R. Scott Martin López, Javier Mauricio Cadillo-Quiroz, Hinsby Kidd, Darren Verchot, Louis V. |
| author_browse | Cadillo-Quiroz, Hinsby Chan, Ed Fortier, Matthew Kidd, Darren Martin López, Javier Mauricio Melton, Joe R. Millard, Koreen Verchot, Louis V. Winton, R. Scott |
| author_facet | Melton, Joe R. Chan, Ed Millard, Koreen Fortier, Matthew Winton, R. Scott Martin López, Javier Mauricio Cadillo-Quiroz, Hinsby Kidd, Darren Verchot, Louis V. |
| author_sort | Melton, Joe R. |
| collection | Repository of Agricultural Research Outputs (CGSpace) |
| description | Peatlands store large amounts of soil carbon and freshwater, constituting an important component of the global carbon and hydrologic cycles. Accurate information on the global extent and distribution of peatlands is presently lacking but is needed by Earth system models (ESMs) to simulate the effects of climate change on the global carbon and hydrologic balance. Here, we present Peat-ML, a spatially continuous global map of peatland fractional coverage generated using machine learning (ML) techniques suitable for use as a prescribed geophysical field in an ESM. Inputs to our statistical model follow drivers of peatland formation and include spatially distributed climate, geomorphological and soil data, and remotely sensed vegetation indices. Available maps of peatland fractional coverage for 14 relatively extensive regions were used along with mapped ecoregions of non-peatland areas to train the statistical model. In addition to qualitative comparisons to other maps in the literature, we estimated model error in two ways. The first estimate used the training data in a blocked leave-one-out cross-validation strategy designed to minimize the influence of spatial autocorrelation. That approach yielded an average r2 of 0.73 with a root-mean-square error and mean bias error of 9.11 % and −0.36 %, respectively. Our second error estimate was generated by comparing Peat-ML against a high-quality, extensively ground-truthed map generated by Ducks Unlimited Canada for the Canadian Boreal Plains region. This comparison suggests our map to be of comparable quality to mapping products generated through more traditional approaches, at least for boreal peatlands. |
| format | Journal Article |
| id | CGSpace119957 |
| institution | CGIAR Consortium |
| language | Inglés |
| publishDate | 2022 |
| publishDateRange | 2022 |
| publishDateSort | 2022 |
| publisher | Copernicus GmbH |
| publisherStr | Copernicus GmbH |
| record_format | dspace |
| spelling | CGSpace1199572025-11-11T19:05:49Z A map of global peatland extent created using machine learning (Peat-ML) Melton, Joe R. Chan, Ed Millard, Koreen Fortier, Matthew Winton, R. Scott Martin López, Javier Mauricio Cadillo-Quiroz, Hinsby Kidd, Darren Verchot, Louis V. peatlands machine learning climate change turberas aprendizaje electrónico cambio climático Peatlands store large amounts of soil carbon and freshwater, constituting an important component of the global carbon and hydrologic cycles. Accurate information on the global extent and distribution of peatlands is presently lacking but is needed by Earth system models (ESMs) to simulate the effects of climate change on the global carbon and hydrologic balance. Here, we present Peat-ML, a spatially continuous global map of peatland fractional coverage generated using machine learning (ML) techniques suitable for use as a prescribed geophysical field in an ESM. Inputs to our statistical model follow drivers of peatland formation and include spatially distributed climate, geomorphological and soil data, and remotely sensed vegetation indices. Available maps of peatland fractional coverage for 14 relatively extensive regions were used along with mapped ecoregions of non-peatland areas to train the statistical model. In addition to qualitative comparisons to other maps in the literature, we estimated model error in two ways. The first estimate used the training data in a blocked leave-one-out cross-validation strategy designed to minimize the influence of spatial autocorrelation. That approach yielded an average r2 of 0.73 with a root-mean-square error and mean bias error of 9.11 % and −0.36 %, respectively. Our second error estimate was generated by comparing Peat-ML against a high-quality, extensively ground-truthed map generated by Ducks Unlimited Canada for the Canadian Boreal Plains region. This comparison suggests our map to be of comparable quality to mapping products generated through more traditional approaches, at least for boreal peatlands. 2022-06-20 2022-06-28T08:06:59Z 2022-06-28T08:06:59Z Journal Article https://hdl.handle.net/10568/119957 en Open Access application/pdf Copernicus GmbH Melton, J.R.; Chan, E.; Millard, K.; Fortier, M.; Winton, R.S.; Martín-López, J.M.; Cadillo-Quiroz, H.; Kidd, D.; Verchot, L.V. (2022) A map of global peatland extent created using machine learning (Peat-ML). Geoscientific Model Development 15 (12) p. 4709–4738. ISSN: 1991-959X |
| spellingShingle | peatlands machine learning climate change turberas aprendizaje electrónico cambio climático Melton, Joe R. Chan, Ed Millard, Koreen Fortier, Matthew Winton, R. Scott Martin López, Javier Mauricio Cadillo-Quiroz, Hinsby Kidd, Darren Verchot, Louis V. A map of global peatland extent created using machine learning (Peat-ML) |
| title | A map of global peatland extent created using machine learning (Peat-ML) |
| title_full | A map of global peatland extent created using machine learning (Peat-ML) |
| title_fullStr | A map of global peatland extent created using machine learning (Peat-ML) |
| title_full_unstemmed | A map of global peatland extent created using machine learning (Peat-ML) |
| title_short | A map of global peatland extent created using machine learning (Peat-ML) |
| title_sort | map of global peatland extent created using machine learning peat ml |
| topic | peatlands machine learning climate change turberas aprendizaje electrónico cambio climático |
| url | https://hdl.handle.net/10568/119957 |
| work_keys_str_mv | AT meltonjoer amapofglobalpeatlandextentcreatedusingmachinelearningpeatml AT chaned amapofglobalpeatlandextentcreatedusingmachinelearningpeatml AT millardkoreen amapofglobalpeatlandextentcreatedusingmachinelearningpeatml AT fortiermatthew amapofglobalpeatlandextentcreatedusingmachinelearningpeatml AT wintonrscott amapofglobalpeatlandextentcreatedusingmachinelearningpeatml AT martinlopezjaviermauricio amapofglobalpeatlandextentcreatedusingmachinelearningpeatml AT cadilloquirozhinsby amapofglobalpeatlandextentcreatedusingmachinelearningpeatml AT kidddarren amapofglobalpeatlandextentcreatedusingmachinelearningpeatml AT verchotlouisv amapofglobalpeatlandextentcreatedusingmachinelearningpeatml AT meltonjoer mapofglobalpeatlandextentcreatedusingmachinelearningpeatml AT chaned mapofglobalpeatlandextentcreatedusingmachinelearningpeatml AT millardkoreen mapofglobalpeatlandextentcreatedusingmachinelearningpeatml AT fortiermatthew mapofglobalpeatlandextentcreatedusingmachinelearningpeatml AT wintonrscott mapofglobalpeatlandextentcreatedusingmachinelearningpeatml AT martinlopezjaviermauricio mapofglobalpeatlandextentcreatedusingmachinelearningpeatml AT cadilloquirozhinsby mapofglobalpeatlandextentcreatedusingmachinelearningpeatml AT kidddarren mapofglobalpeatlandextentcreatedusingmachinelearningpeatml AT verchotlouisv mapofglobalpeatlandextentcreatedusingmachinelearningpeatml |