A Simple Emulator That Enables Interpretation of Parameter‐Output Relationships, Applied to Two Climate Model PPEs

Abstract We present a new additive method, referred to as sage for Simplified Additive Gaussian processes Emulator, for emulating climate model Perturbed Parameter Ensembles (PPEs). sage estimates the value of a climate model output as the sum of additive terms. Each additive term is the mean of a G...

Full description

Saved in:
Bibliographic Details
Main Authors: Qingyuan Yang, Gregory S. Elsaesser, Marcus van Lier‐Walqui, Trude Eidhammer
Format: Article
Language:English
Published: American Geophysical Union (AGU) 2025-05-01
Series:Journal of Advances in Modeling Earth Systems
Subjects:
Online Access:https://doi.org/10.1029/2024MS004766
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849327172300308480
author Qingyuan Yang
Gregory S. Elsaesser
Marcus van Lier‐Walqui
Trude Eidhammer
author_facet Qingyuan Yang
Gregory S. Elsaesser
Marcus van Lier‐Walqui
Trude Eidhammer
author_sort Qingyuan Yang
collection DOAJ
description Abstract We present a new additive method, referred to as sage for Simplified Additive Gaussian processes Emulator, for emulating climate model Perturbed Parameter Ensembles (PPEs). sage estimates the value of a climate model output as the sum of additive terms. Each additive term is the mean of a Gaussian Process, and corresponds to the impact of a parameter or parameter group on the variable of interest. This design caters to the sparsity of PPEs, which are characterized by limited ensemble members and high dimensionality of the parameter space and raise the issue of parameter sensitivity in the emulator design. sage quantifies the variability explained by different parameters and parameter groups, providing additional insights on the parameter‐climate model output relationship. We apply sage to two climate model PPEs and compare it to a fully connected Neural Network. The two methods have comparable performance with both PPEs, but sage provides insights on parameter and parameter group importance as well as diagnostics useful for optimizing PPE design. Insights gained from applying the method and comparing its performance with Neural Network are pointed out which have not been previously addressed. Our work highlights that analyzing the PPE used to train an emulator is different from analyzing data generated from an emulator trained on the PPE, as the former provides more insights on the data structure in the PPE which could help inform the emulator design. Our work also proposes new questions on the optimal way of working with climate model PPEs.
format Article
id doaj-art-99fbf8295f8146f98ba97fc8891f459e
institution Kabale University
issn 1942-2466
language English
publishDate 2025-05-01
publisher American Geophysical Union (AGU)
record_format Article
series Journal of Advances in Modeling Earth Systems
spelling doaj-art-99fbf8295f8146f98ba97fc8891f459e2025-08-20T03:47:57ZengAmerican Geophysical Union (AGU)Journal of Advances in Modeling Earth Systems1942-24662025-05-01175n/an/a10.1029/2024MS004766A Simple Emulator That Enables Interpretation of Parameter‐Output Relationships, Applied to Two Climate Model PPEsQingyuan Yang0Gregory S. Elsaesser1Marcus van Lier‐Walqui2Trude Eidhammer3Learning the Earth with Artificial Intelligence and Physics (LEAP) National Science Foundation (NSF) Science and Technology Center Columbia University New York NY USALearning the Earth with Artificial Intelligence and Physics (LEAP) National Science Foundation (NSF) Science and Technology Center Columbia University New York NY USALearning the Earth with Artificial Intelligence and Physics (LEAP) National Science Foundation (NSF) Science and Technology Center Columbia University New York NY USANSF National Center for Atmospheric Research Boulder CO USAAbstract We present a new additive method, referred to as sage for Simplified Additive Gaussian processes Emulator, for emulating climate model Perturbed Parameter Ensembles (PPEs). sage estimates the value of a climate model output as the sum of additive terms. Each additive term is the mean of a Gaussian Process, and corresponds to the impact of a parameter or parameter group on the variable of interest. This design caters to the sparsity of PPEs, which are characterized by limited ensemble members and high dimensionality of the parameter space and raise the issue of parameter sensitivity in the emulator design. sage quantifies the variability explained by different parameters and parameter groups, providing additional insights on the parameter‐climate model output relationship. We apply sage to two climate model PPEs and compare it to a fully connected Neural Network. The two methods have comparable performance with both PPEs, but sage provides insights on parameter and parameter group importance as well as diagnostics useful for optimizing PPE design. Insights gained from applying the method and comparing its performance with Neural Network are pointed out which have not been previously addressed. Our work highlights that analyzing the PPE used to train an emulator is different from analyzing data generated from an emulator trained on the PPE, as the former provides more insights on the data structure in the PPE which could help inform the emulator design. Our work also proposes new questions on the optimal way of working with climate model PPEs.https://doi.org/10.1029/2024MS004766perturbed parameter ensembleclimate modelemulatormachine learningglobal circulation model
spellingShingle Qingyuan Yang
Gregory S. Elsaesser
Marcus van Lier‐Walqui
Trude Eidhammer
A Simple Emulator That Enables Interpretation of Parameter‐Output Relationships, Applied to Two Climate Model PPEs
Journal of Advances in Modeling Earth Systems
perturbed parameter ensemble
climate model
emulator
machine learning
global circulation model
title A Simple Emulator That Enables Interpretation of Parameter‐Output Relationships, Applied to Two Climate Model PPEs
title_full A Simple Emulator That Enables Interpretation of Parameter‐Output Relationships, Applied to Two Climate Model PPEs
title_fullStr A Simple Emulator That Enables Interpretation of Parameter‐Output Relationships, Applied to Two Climate Model PPEs
title_full_unstemmed A Simple Emulator That Enables Interpretation of Parameter‐Output Relationships, Applied to Two Climate Model PPEs
title_short A Simple Emulator That Enables Interpretation of Parameter‐Output Relationships, Applied to Two Climate Model PPEs
title_sort simple emulator that enables interpretation of parameter output relationships applied to two climate model ppes
topic perturbed parameter ensemble
climate model
emulator
machine learning
global circulation model
url https://doi.org/10.1029/2024MS004766
work_keys_str_mv AT qingyuanyang asimpleemulatorthatenablesinterpretationofparameteroutputrelationshipsappliedtotwoclimatemodelppes
AT gregoryselsaesser asimpleemulatorthatenablesinterpretationofparameteroutputrelationshipsappliedtotwoclimatemodelppes
AT marcusvanlierwalqui asimpleemulatorthatenablesinterpretationofparameteroutputrelationshipsappliedtotwoclimatemodelppes
AT trudeeidhammer asimpleemulatorthatenablesinterpretationofparameteroutputrelationshipsappliedtotwoclimatemodelppes
AT qingyuanyang simpleemulatorthatenablesinterpretationofparameteroutputrelationshipsappliedtotwoclimatemodelppes
AT gregoryselsaesser simpleemulatorthatenablesinterpretationofparameteroutputrelationshipsappliedtotwoclimatemodelppes
AT marcusvanlierwalqui simpleemulatorthatenablesinterpretationofparameteroutputrelationshipsappliedtotwoclimatemodelppes
AT trudeeidhammer simpleemulatorthatenablesinterpretationofparameteroutputrelationshipsappliedtotwoclimatemodelppes