Improving Climate Bias and Variability via CNN‐Based State‐Dependent Model‐Error Corrections

Abstract We develop an approach to correct biases in the atmospheric component of the Community Earth System Model using convolutional neural networks (CNNs) to create a corrective model parameterization for online bias reduction. By predicting systematic nudging increments derived from nudging towa...

Full description

Saved in:
Bibliographic Details
Main Authors: William E. Chapman, Judith Berner
Format: Article
Language:English
Published: Wiley 2025-03-01
Series:Geophysical Research Letters
Subjects:
Online Access:https://doi.org/10.1029/2024GL114106
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849314194727370752
author William E. Chapman
Judith Berner
author_facet William E. Chapman
Judith Berner
author_sort William E. Chapman
collection DOAJ
description Abstract We develop an approach to correct biases in the atmospheric component of the Community Earth System Model using convolutional neural networks (CNNs) to create a corrective model parameterization for online bias reduction. By predicting systematic nudging increments derived from nudging toward the ERA5‐reanalysis, our method dynamically adjusts the model state, outperforming traditional corrections based on climatological increments alone. Our results show significant root mean squared error improvements across all state variables, with land precipitation biases reduced by 25%–35%, seasonally dependent. Notably, we observe an improvement to the Madden‐Julian Oscillation (MJO), where the CNN‐corrected model successfully propagates the MJO across the maritime continent, a challenge for many current climate models. This advancement underscores the potential of using CNNs for real‐time model correction, providing a robust framework for improving climate simulations. This advancement highlights the potential of CNNs for real‐time model correction, improving climate simulations and bridging observed and simulated dynamics.
format Article
id doaj-art-39a0d89b878b43ddbf64340d70b3a2ca
institution Kabale University
issn 0094-8276
1944-8007
language English
publishDate 2025-03-01
publisher Wiley
record_format Article
series Geophysical Research Letters
spelling doaj-art-39a0d89b878b43ddbf64340d70b3a2ca2025-08-20T03:52:32ZengWileyGeophysical Research Letters0094-82761944-80072025-03-01526n/an/a10.1029/2024GL114106Improving Climate Bias and Variability via CNN‐Based State‐Dependent Model‐Error CorrectionsWilliam E. Chapman0Judith Berner1U.S. National Science Foundation National Center for Atmospheric Research Boulder CO USAU.S. National Science Foundation National Center for Atmospheric Research Boulder CO USAAbstract We develop an approach to correct biases in the atmospheric component of the Community Earth System Model using convolutional neural networks (CNNs) to create a corrective model parameterization for online bias reduction. By predicting systematic nudging increments derived from nudging toward the ERA5‐reanalysis, our method dynamically adjusts the model state, outperforming traditional corrections based on climatological increments alone. Our results show significant root mean squared error improvements across all state variables, with land precipitation biases reduced by 25%–35%, seasonally dependent. Notably, we observe an improvement to the Madden‐Julian Oscillation (MJO), where the CNN‐corrected model successfully propagates the MJO across the maritime continent, a challenge for many current climate models. This advancement underscores the potential of using CNNs for real‐time model correction, providing a robust framework for improving climate simulations. This advancement highlights the potential of CNNs for real‐time model correction, improving climate simulations and bridging observed and simulated dynamics.https://doi.org/10.1029/2024GL114106Madden Julian Oscillationmachine learningclimatemodeling
spellingShingle William E. Chapman
Judith Berner
Improving Climate Bias and Variability via CNN‐Based State‐Dependent Model‐Error Corrections
Geophysical Research Letters
Madden Julian Oscillation
machine learning
climate
modeling
title Improving Climate Bias and Variability via CNN‐Based State‐Dependent Model‐Error Corrections
title_full Improving Climate Bias and Variability via CNN‐Based State‐Dependent Model‐Error Corrections
title_fullStr Improving Climate Bias and Variability via CNN‐Based State‐Dependent Model‐Error Corrections
title_full_unstemmed Improving Climate Bias and Variability via CNN‐Based State‐Dependent Model‐Error Corrections
title_short Improving Climate Bias and Variability via CNN‐Based State‐Dependent Model‐Error Corrections
title_sort improving climate bias and variability via cnn based state dependent model error corrections
topic Madden Julian Oscillation
machine learning
climate
modeling
url https://doi.org/10.1029/2024GL114106
work_keys_str_mv AT williamechapman improvingclimatebiasandvariabilityviacnnbasedstatedependentmodelerrorcorrections
AT judithberner improvingclimatebiasandvariabilityviacnnbasedstatedependentmodelerrorcorrections