elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Data-Driven Cloud Cover Parameterizations for the ICON Earth System Model Using Deep Learning and Symbolic Regression

Grundner, Arthur (2023) Data-Driven Cloud Cover Parameterizations for the ICON Earth System Model Using Deep Learning and Symbolic Regression. Dissertation, Universität Bremen. doi: 10.26092/elib/2821.

[img] PDF
8MB

Official URL: https://media.suub.uni-bremen.de/handle/elib/7739

Abstract

This thesis delves into the improvement of cloud parameterizations in climate models through machine learning trained on coarse-grained output from high-resolution simulations. Utilizing the ICOsahedral Non-hydrostatic (ICON) modeling framework, it specifically targets the enhancement of cloud cover parameterization within the ICON Earth System Model. Three types of neural networks (NNs) differing in vertical locality are developed to estimate cloud cover, with globally trained NNs even applicable to distinct regional simulations. Interpretability analysis exposes model-specific biases and local relationships with the thermodynamic environment. Despite achieving high predictive performance, NNs necessitate post-hoc interpretation tools. To tackle this issue, a combined hierarchical modeling framework incorporating symbolic regression, feature selection, and physical constraints is proposed. The resulting equations, characterized by simplicity and physical consistency, attain performance comparable to NNs while demonstrating superior transferability to other realistic datasets. Our best equation adeptly captures cloud cover distributions across various regimes, notably excelling in representing marine stratocumulus clouds by learning to utilize the vertical relative humidity gradient. This research underscores the potential of deep learning in achieving accurate cloud parameterizations and emphasizes the effective role of symbolic regression in deriving interpretable, consistent equations for cloud cover.

Item URL in elib:https://elib.dlr.de/202993/
Document Type:Thesis (Dissertation)
Title:Data-Driven Cloud Cover Parameterizations for the ICON Earth System Model Using Deep Learning and Symbolic Regression
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iDORCID Put Code
Grundner, ArthurDLR, IPAhttps://orcid.org/0000-0002-3765-242XUNSPECIFIED
Date:25 October 2023
Journal or Publication Title:Staats- und Universitätsbibliothek Bremen
Refereed publication:No
Open Access:Yes
DOI:10.26092/elib/2821
Number of Pages:140
Status:Published
Keywords:Cloud Cover, Parameterization, Machine Learning, Symbolic Regression, Equation Discovery, Physical Constraints, PySR, Sequential Feature Selection, Pareto Frontier, ICON, SHAP, Deep Learning, Neural Networks
Institution:Universität Bremen
Department:Institut für Umweltphysik
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Earth Observation
DLR - Research area:Raumfahrt
DLR - Program:R EO - Earth Observation
DLR - Research theme (Project):R - Atmospheric and climate research
Location: Oberpfaffenhofen
Institutes and Institutions:Institute of Atmospheric Physics > Earth System Model Evaluation and Analysis
Deposited By: Grundner, Arthur
Deposited On:07 Mar 2024 11:30
Last Modified:07 Mar 2024 11:30

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Website and database design: Copyright © German Aerospace Center (DLR). All rights reserved.