Calibration of sea ice drift forecasts using random forest algorithms
Developing accurate sea ice drift forecasts is essential to support the decision-making of maritime end-users operating in the Arctic. In this study, two calibration methods have been developed for improving 10 d sea ice drift forecasts from an operational sea ice prediction system (TOPAZ4). The met...
Published in: | The Cryosphere |
---|---|
Main Authors: | , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Copernicus Publications
2021
|
Subjects: | |
Online Access: | https://doi.org/10.5194/tc-15-3989-2021 https://tc.copernicus.org/articles/15/3989/2021/tc-15-3989-2021.pdf https://doaj.org/article/df4bee2204ec4b21806acbe59201e082 |
id |
fttriple:oai:gotriple.eu:oai:doaj.org/article:df4bee2204ec4b21806acbe59201e082 |
---|---|
record_format |
openpolar |
spelling |
fttriple:oai:gotriple.eu:oai:doaj.org/article:df4bee2204ec4b21806acbe59201e082 2023-05-15T15:04:26+02:00 Calibration of sea ice drift forecasts using random forest algorithms C. Palerme M. Müller 2021-08-01 https://doi.org/10.5194/tc-15-3989-2021 https://tc.copernicus.org/articles/15/3989/2021/tc-15-3989-2021.pdf https://doaj.org/article/df4bee2204ec4b21806acbe59201e082 en eng Copernicus Publications doi:10.5194/tc-15-3989-2021 1994-0416 1994-0424 https://tc.copernicus.org/articles/15/3989/2021/tc-15-3989-2021.pdf https://doaj.org/article/df4bee2204ec4b21806acbe59201e082 undefined The Cryosphere, Vol 15, Pp 3989-4004 (2021) geo envir Journal Article https://vocabularies.coar-repositories.org/resource_types/c_6501/ 2021 fttriple https://doi.org/10.5194/tc-15-3989-2021 2023-01-22T19:11:22Z Developing accurate sea ice drift forecasts is essential to support the decision-making of maritime end-users operating in the Arctic. In this study, two calibration methods have been developed for improving 10 d sea ice drift forecasts from an operational sea ice prediction system (TOPAZ4). The methods are based on random forest models (supervised machine learning) which were trained using target variables either from drifting buoy or synthetic-aperture radar (SAR) observations. Depending on the calibration method, the mean absolute error is reduced, on average, between 3.3 % and 8.0 % for the direction and between 2.5 % and 7.1 % for the speed of sea ice drift. Overall, the algorithms trained with buoy observations have the best performances when the forecasts are evaluated using drifting buoys as reference. However, there is a large spatial variability in these results, and the models trained with buoy observations have particularly poor performances for predicting the speed of sea ice drift near the Greenland and Russian coastlines compared to the models trained with SAR observations. Article in Journal/Newspaper Arctic Greenland Sea ice The Cryosphere Unknown Arctic Greenland The Cryosphere 15 8 3989 4004 |
institution |
Open Polar |
collection |
Unknown |
op_collection_id |
fttriple |
language |
English |
topic |
geo envir |
spellingShingle |
geo envir C. Palerme M. Müller Calibration of sea ice drift forecasts using random forest algorithms |
topic_facet |
geo envir |
description |
Developing accurate sea ice drift forecasts is essential to support the decision-making of maritime end-users operating in the Arctic. In this study, two calibration methods have been developed for improving 10 d sea ice drift forecasts from an operational sea ice prediction system (TOPAZ4). The methods are based on random forest models (supervised machine learning) which were trained using target variables either from drifting buoy or synthetic-aperture radar (SAR) observations. Depending on the calibration method, the mean absolute error is reduced, on average, between 3.3 % and 8.0 % for the direction and between 2.5 % and 7.1 % for the speed of sea ice drift. Overall, the algorithms trained with buoy observations have the best performances when the forecasts are evaluated using drifting buoys as reference. However, there is a large spatial variability in these results, and the models trained with buoy observations have particularly poor performances for predicting the speed of sea ice drift near the Greenland and Russian coastlines compared to the models trained with SAR observations. |
format |
Article in Journal/Newspaper |
author |
C. Palerme M. Müller |
author_facet |
C. Palerme M. Müller |
author_sort |
C. Palerme |
title |
Calibration of sea ice drift forecasts using random forest algorithms |
title_short |
Calibration of sea ice drift forecasts using random forest algorithms |
title_full |
Calibration of sea ice drift forecasts using random forest algorithms |
title_fullStr |
Calibration of sea ice drift forecasts using random forest algorithms |
title_full_unstemmed |
Calibration of sea ice drift forecasts using random forest algorithms |
title_sort |
calibration of sea ice drift forecasts using random forest algorithms |
publisher |
Copernicus Publications |
publishDate |
2021 |
url |
https://doi.org/10.5194/tc-15-3989-2021 https://tc.copernicus.org/articles/15/3989/2021/tc-15-3989-2021.pdf https://doaj.org/article/df4bee2204ec4b21806acbe59201e082 |
geographic |
Arctic Greenland |
geographic_facet |
Arctic Greenland |
genre |
Arctic Greenland Sea ice The Cryosphere |
genre_facet |
Arctic Greenland Sea ice The Cryosphere |
op_source |
The Cryosphere, Vol 15, Pp 3989-4004 (2021) |
op_relation |
doi:10.5194/tc-15-3989-2021 1994-0416 1994-0424 https://tc.copernicus.org/articles/15/3989/2021/tc-15-3989-2021.pdf https://doaj.org/article/df4bee2204ec4b21806acbe59201e082 |
op_rights |
undefined |
op_doi |
https://doi.org/10.5194/tc-15-3989-2021 |
container_title |
The Cryosphere |
container_volume |
15 |
container_issue |
8 |
container_start_page |
3989 |
op_container_end_page |
4004 |
_version_ |
1766336206502625280 |