Work

Deep Learning for Koopman Operator Estimation in Idealized Atmospheric Dynamics

Year: 2024

Type: conference-paper

Abstract: Deep learning is revolutionizing weather forecasting, with new data-driven models achieving accuracy on par with operational physical models for medium-term predictions. However, these models often lack interpretability, making their underlying dynamics difficult to understand and explain. This paper proposes methodologies to estimate the Koopman operator, providing a linear representation of complex nonlinear dynamics to enhance the transparency of data-driven models. Despite its potential, applying the Koopman operator to large-scale problems, such as atmospheric modeling, remains challenging. This study aims to identify the limitations of existing methods, refine these models to overcome various bottlenecks, and introduce novel convolutional neural network architectures that capture simplified dynamics.

Source: IEEE International Conference on Big Data (BigData)

DOI: 10.1109/bigdata62323.2024.10825166

Authors: David Millard, Arielle Carr, Stéphane Gaudreault

Institutions: Rochester Institute of Technology, Lehigh University, Environment and Climate Change Canada

Language: English

Topic: Model Reduction and Neural Networks

Subfield: Statistical and Nonlinear Physics

Field: Physics and Astronomy

Domain: Physical Sciences

SDG: Climate action

Open Access status: green

Funder: National Science Foundation