A machine learning correction model of the winter clear-sky temperature bias over the Arctic Sea ice in atmospheric reanalyses
Atmospheric reanalyses are widely used to estimate the past atmospheric near-surface state over sea ice. They provide boundary conditions for sea ice and ocean numerical simulations and relevant information for studying polar variability and anthropogenic climate change. Previous research revealed t...
Published in: | Monthly Weather Review |
---|---|
Other Authors: | , , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
2023
|
Subjects: | |
Online Access: | https://doi.org/10.1175/MWR-D-22-0130.1 |
id |
ftncar:oai:drupal-site.org:articles_26366 |
---|---|
record_format |
openpolar |
spelling |
ftncar:oai:drupal-site.org:articles_26366 2023-10-01T03:53:39+02:00 A machine learning correction model of the winter clear-sky temperature bias over the Arctic Sea ice in atmospheric reanalyses Zampieri, Lorenzo (author) Arduini, Gabriele (author) Holland, Marika (author) Keeley, Sarah P. E. (author) Mogensen, Kristian (author) Shupe, Matthew D. (author) Tietsche, Steffen (author) 2023-06 https://doi.org/10.1175/MWR-D-22-0130.1 en eng Monthly Weather Review--0027-0644--1520-0493 articles:26366 doi:10.1175/MWR-D-22-0130.1 ark:/85065/d7k93cjc Copyright 2023 American Meteorological Society (AMS). article Text 2023 ftncar https://doi.org/10.1175/MWR-D-22-0130.1 2023-09-04T18:18:39Z Atmospheric reanalyses are widely used to estimate the past atmospheric near-surface state over sea ice. They provide boundary conditions for sea ice and ocean numerical simulations and relevant information for studying polar variability and anthropogenic climate change. Previous research revealed the existence of large near-surface temperature biases (mostly warm) over the Arctic sea ice in the current generation of atmospheric reanalyses, which is linked to a poor representation of the snow over the sea ice and the stably stratified boundary layer in the forecast models used to produce the reanalyses. These errors can compromise the employment of reanalysis products in support of polar research. Here, we train a fully connected neural network that learns from remote sensing infrared temperature observations to correct the exist-ing generation of uncoupled atmospheric reanalyses (ERA5, JRA-55) based on a set of sea ice and atmospheric predictors, which are themselves reanalysis products. The advantages of the proposed correction scheme over previous calibration at-tempts are the consideration of the synoptic weather and cloud state, compatibility of the predictors with the mechanism re-sponsible for the bias, and a self-emerging seasonality and multidecadal trend consistent with the declining sea ice state in the Arctic. The correction leads on average to a 27% temperature bias reduction for ERA5 and 7% for JRA-55 if compared to independent in situ observations from the MOSAiC campaign (respectively, 32% and 10% under clear-sky conditions). These improvements can be beneficial for forced sea ice and ocean simulations, which rely on reanalyses surface fields as boundary conditions. SIGNIFICANCE STATEMENT: This study illustrates a novel method based on machine learning for reducing the systematic surface temperature errors that characterize multiple atmospheric reanalyses in sea ice-covered regions of the Arctic under clear-sky conditions. The correction applied to the temperature field is consistent with the ... Article in Journal/Newspaper Arctic Climate change Sea ice OpenSky (NCAR/UCAR - National Center for Atmospheric Research/University Corporation for Atmospheric Research) Arctic Monthly Weather Review 151 6 1443 1458 |
institution |
Open Polar |
collection |
OpenSky (NCAR/UCAR - National Center for Atmospheric Research/University Corporation for Atmospheric Research) |
op_collection_id |
ftncar |
language |
English |
description |
Atmospheric reanalyses are widely used to estimate the past atmospheric near-surface state over sea ice. They provide boundary conditions for sea ice and ocean numerical simulations and relevant information for studying polar variability and anthropogenic climate change. Previous research revealed the existence of large near-surface temperature biases (mostly warm) over the Arctic sea ice in the current generation of atmospheric reanalyses, which is linked to a poor representation of the snow over the sea ice and the stably stratified boundary layer in the forecast models used to produce the reanalyses. These errors can compromise the employment of reanalysis products in support of polar research. Here, we train a fully connected neural network that learns from remote sensing infrared temperature observations to correct the exist-ing generation of uncoupled atmospheric reanalyses (ERA5, JRA-55) based on a set of sea ice and atmospheric predictors, which are themselves reanalysis products. The advantages of the proposed correction scheme over previous calibration at-tempts are the consideration of the synoptic weather and cloud state, compatibility of the predictors with the mechanism re-sponsible for the bias, and a self-emerging seasonality and multidecadal trend consistent with the declining sea ice state in the Arctic. The correction leads on average to a 27% temperature bias reduction for ERA5 and 7% for JRA-55 if compared to independent in situ observations from the MOSAiC campaign (respectively, 32% and 10% under clear-sky conditions). These improvements can be beneficial for forced sea ice and ocean simulations, which rely on reanalyses surface fields as boundary conditions. SIGNIFICANCE STATEMENT: This study illustrates a novel method based on machine learning for reducing the systematic surface temperature errors that characterize multiple atmospheric reanalyses in sea ice-covered regions of the Arctic under clear-sky conditions. The correction applied to the temperature field is consistent with the ... |
author2 |
Zampieri, Lorenzo (author) Arduini, Gabriele (author) Holland, Marika (author) Keeley, Sarah P. E. (author) Mogensen, Kristian (author) Shupe, Matthew D. (author) Tietsche, Steffen (author) |
format |
Article in Journal/Newspaper |
title |
A machine learning correction model of the winter clear-sky temperature bias over the Arctic Sea ice in atmospheric reanalyses |
spellingShingle |
A machine learning correction model of the winter clear-sky temperature bias over the Arctic Sea ice in atmospheric reanalyses |
title_short |
A machine learning correction model of the winter clear-sky temperature bias over the Arctic Sea ice in atmospheric reanalyses |
title_full |
A machine learning correction model of the winter clear-sky temperature bias over the Arctic Sea ice in atmospheric reanalyses |
title_fullStr |
A machine learning correction model of the winter clear-sky temperature bias over the Arctic Sea ice in atmospheric reanalyses |
title_full_unstemmed |
A machine learning correction model of the winter clear-sky temperature bias over the Arctic Sea ice in atmospheric reanalyses |
title_sort |
machine learning correction model of the winter clear-sky temperature bias over the arctic sea ice in atmospheric reanalyses |
publishDate |
2023 |
url |
https://doi.org/10.1175/MWR-D-22-0130.1 |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic Climate change Sea ice |
genre_facet |
Arctic Climate change Sea ice |
op_relation |
Monthly Weather Review--0027-0644--1520-0493 articles:26366 doi:10.1175/MWR-D-22-0130.1 ark:/85065/d7k93cjc |
op_rights |
Copyright 2023 American Meteorological Society (AMS). |
op_doi |
https://doi.org/10.1175/MWR-D-22-0130.1 |
container_title |
Monthly Weather Review |
container_volume |
151 |
container_issue |
6 |
container_start_page |
1443 |
op_container_end_page |
1458 |
_version_ |
1778520395927781376 |