A Machine Learning Correction Model of the Winter Clear-Sky Temperature Bias over the Arctic Sea Ice in Atmospheric Reanalyses
Abstract
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 existing 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 attempts are the consideration of the synoptic weather and cloud state, compatibility of the predictors with the mechanism responsible 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 averagemore »
- Authors:
-
[1];
- National Center for Atmospheric Research, Boulder, CO (United States)
- European Centre for Medium-Range Weather Forecasts, Reading (United Kingdom); European Centre for Medium-Range Weather Forecasts, Bonn (Germany)
- University of Colorado, Boulder, CO (United States); National Oceanic and Atmospheric Administration, Boulder, CO (United States)
- Publication Date:
- Research Org.:
- Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States). Atmospheric Radiation Measurement (ARM) Data Center
- Sponsoring Org.:
- USDOE Office of Science (SC), Biological and Environmental Research (BER)
- Contributing Org.:
- Pacific Northwest National Laboratory (PNNL); Brookhaven National Laboratory (BNL); Argonne National Laboratory (ANL); Oak Ridge National Laboratory (ORNL)
- OSTI Identifier:
- 1975734
- Grant/Contract Number:
- SC0021341
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Monthly Weather Review
- Additional Journal Information:
- Journal Volume: 151; Journal Issue: 6; Journal ID: ISSN 0027-0644
- Publisher:
- American Meteorological Society
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 54 ENVIRONMENTAL SCIENCES; Arctic; Sea ice; Surface temperature; Neural networks; Reanalysis data; Machine learning
Citation Formats
Zampieri, Lorenzo, Arduini, Gabriele, Holland, Marika, Keeley, Sarah P. E., Mogensen, Kristian, Shupe, Matthew D., and Tietsche, Steffen. A Machine Learning Correction Model of the Winter Clear-Sky Temperature Bias over the Arctic Sea Ice in Atmospheric Reanalyses. United States: N. p., 2023.
Web. doi:10.1175/mwr-d-22-0130.1.
Zampieri, Lorenzo, Arduini, Gabriele, Holland, Marika, Keeley, Sarah P. E., Mogensen, Kristian, Shupe, Matthew D., & Tietsche, Steffen. A Machine Learning Correction Model of the Winter Clear-Sky Temperature Bias over the Arctic Sea Ice in Atmospheric Reanalyses. United States. https://doi.org/10.1175/mwr-d-22-0130.1
Zampieri, Lorenzo, Arduini, Gabriele, Holland, Marika, Keeley, Sarah P. E., Mogensen, Kristian, Shupe, Matthew D., and Tietsche, Steffen. Thu .
"A Machine Learning Correction Model of the Winter Clear-Sky Temperature Bias over the Arctic Sea Ice in Atmospheric Reanalyses". United States. https://doi.org/10.1175/mwr-d-22-0130.1. https://www.osti.gov/servlets/purl/1975734.
@article{osti_1975734,
title = {A Machine Learning Correction Model of the Winter Clear-Sky Temperature Bias over the Arctic Sea Ice in Atmospheric Reanalyses},
author = {Zampieri, Lorenzo and Arduini, Gabriele and Holland, Marika and Keeley, Sarah P. E. and Mogensen, Kristian and Shupe, Matthew D. and Tietsche, Steffen},
abstractNote = {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 existing 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 attempts are the consideration of the synoptic weather and cloud state, compatibility of the predictors with the mechanism responsible 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.},
doi = {10.1175/mwr-d-22-0130.1},
journal = {Monthly Weather Review},
number = 6,
volume = 151,
place = {United States},
year = {Thu Jun 01 00:00:00 EDT 2023},
month = {Thu Jun 01 00:00:00 EDT 2023}
}
Search WorldCat to find libraries that may hold this journal