High-Resolution Land Use Land Cover Dataset for Meteorological Modelling—Part 2: ECOCLIMAP-SG-ML an Ensemble Land Cover Map
While the surface of the Earth plays a key role in weather forecasting through its interaction with the atmosphere, in ensemble numerical weather predictions the uncertainty on the surface is only represented with perturbations in the parameterisations representing the surface processes. Data repres...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-11-01
|
| Series: | Land |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-445X/13/11/1875 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850068667694317568 |
|---|---|
| author | Thomas Rieutord Geoffrey Bessardon Emily Gleeson |
| author_facet | Thomas Rieutord Geoffrey Bessardon Emily Gleeson |
| author_sort | Thomas Rieutord |
| collection | DOAJ |
| description | While the surface of the Earth plays a key role in weather forecasting through its interaction with the atmosphere, in ensemble numerical weather predictions the uncertainty on the surface is only represented with perturbations in the parameterisations representing the surface processes. Data representing the surface, such as the land cover, are not perturbed. As fully data-driven forecasts without parameterisations are growing in importance, sampling the uncertainty on the land cover data brings a new way of making ensemble forecasts. Our work describes a method of generating ensemble land cover maps for numerical weather prediction. The target land cover map has the ECOCLIMAP-SG labels used in the SURFEX surface model and therefore is expected to have all relevant labels for surface-atmosphere interactions. The method translates the ESA WorldCover map to ECOCLIMAP-SG labels and resolution using auto-encoders. The land cover ensemble members are obtained by sampling the land cover probabilities in the output of the neural network. This paper builds upon the work done in a companion paper describing the high-resolution version of ECOCLIMAP-SG, called ECOCLIMAP-SG+, used for the training and evaluation of the neural network. The output map presented here, called ECOCLIMAP-SG-ML, improves upon the ECOCLIMAP-SG map in terms of resolution (from 300 m to 60 m), overall accuracy (from 0.41 to 0.63), and the ability to produce ensemble members. |
| format | Article |
| id | doaj-art-fe9d0206eb8249fc90e138cff7715eab |
| institution | DOAJ |
| issn | 2073-445X |
| language | English |
| publishDate | 2024-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Land |
| spelling | doaj-art-fe9d0206eb8249fc90e138cff7715eab2025-08-20T02:47:59ZengMDPI AGLand2073-445X2024-11-011311187510.3390/land13111875High-Resolution Land Use Land Cover Dataset for Meteorological Modelling—Part 2: ECOCLIMAP-SG-ML an Ensemble Land Cover MapThomas Rieutord0Geoffrey Bessardon1Emily Gleeson2Met Éireann, 65/67 Glasnevin Hill, D09 Y921 Dublin, IrelandMet Éireann, 65/67 Glasnevin Hill, D09 Y921 Dublin, IrelandMet Éireann, 65/67 Glasnevin Hill, D09 Y921 Dublin, IrelandWhile the surface of the Earth plays a key role in weather forecasting through its interaction with the atmosphere, in ensemble numerical weather predictions the uncertainty on the surface is only represented with perturbations in the parameterisations representing the surface processes. Data representing the surface, such as the land cover, are not perturbed. As fully data-driven forecasts without parameterisations are growing in importance, sampling the uncertainty on the land cover data brings a new way of making ensemble forecasts. Our work describes a method of generating ensemble land cover maps for numerical weather prediction. The target land cover map has the ECOCLIMAP-SG labels used in the SURFEX surface model and therefore is expected to have all relevant labels for surface-atmosphere interactions. The method translates the ESA WorldCover map to ECOCLIMAP-SG labels and resolution using auto-encoders. The land cover ensemble members are obtained by sampling the land cover probabilities in the output of the neural network. This paper builds upon the work done in a companion paper describing the high-resolution version of ECOCLIMAP-SG, called ECOCLIMAP-SG+, used for the training and evaluation of the neural network. The output map presented here, called ECOCLIMAP-SG-ML, improves upon the ECOCLIMAP-SG map in terms of resolution (from 300 m to 60 m), overall accuracy (from 0.41 to 0.63), and the ability to produce ensemble members.https://www.mdpi.com/2073-445X/13/11/1875land cover land usemachine learningmeteorology |
| spellingShingle | Thomas Rieutord Geoffrey Bessardon Emily Gleeson High-Resolution Land Use Land Cover Dataset for Meteorological Modelling—Part 2: ECOCLIMAP-SG-ML an Ensemble Land Cover Map Land land cover land use machine learning meteorology |
| title | High-Resolution Land Use Land Cover Dataset for Meteorological Modelling—Part 2: ECOCLIMAP-SG-ML an Ensemble Land Cover Map |
| title_full | High-Resolution Land Use Land Cover Dataset for Meteorological Modelling—Part 2: ECOCLIMAP-SG-ML an Ensemble Land Cover Map |
| title_fullStr | High-Resolution Land Use Land Cover Dataset for Meteorological Modelling—Part 2: ECOCLIMAP-SG-ML an Ensemble Land Cover Map |
| title_full_unstemmed | High-Resolution Land Use Land Cover Dataset for Meteorological Modelling—Part 2: ECOCLIMAP-SG-ML an Ensemble Land Cover Map |
| title_short | High-Resolution Land Use Land Cover Dataset for Meteorological Modelling—Part 2: ECOCLIMAP-SG-ML an Ensemble Land Cover Map |
| title_sort | high resolution land use land cover dataset for meteorological modelling part 2 ecoclimap sg ml an ensemble land cover map |
| topic | land cover land use machine learning meteorology |
| url | https://www.mdpi.com/2073-445X/13/11/1875 |
| work_keys_str_mv | AT thomasrieutord highresolutionlanduselandcoverdatasetformeteorologicalmodellingpart2ecoclimapsgmlanensemblelandcovermap AT geoffreybessardon highresolutionlanduselandcoverdatasetformeteorologicalmodellingpart2ecoclimapsgmlanensemblelandcovermap AT emilygleeson highresolutionlanduselandcoverdatasetformeteorologicalmodellingpart2ecoclimapsgmlanensemblelandcovermap |