paper-with-me

홈 › Papers

Exploring Design Choices for Autoregressive Deep Learning Climate Models

2025-05-05 · Florian Gallusser, Simon Hentschel, Anna Krause, Andreas Hotho

Deep Learning models have achieved state-of-the-art performance in medium-range weather prediction but often fail to maintain physically consistent rollouts beyond 14 days. In contrast, a few atmospheric models demonstrate stability over decades, though the key design choices enabling this remain unclear. This study quantitatively compares the long-term stability of three prominent DL-MWP architectures - FourCastNet, SFNO, and ClimaX - trained on ERA5 reanalysis data at 5.625{\deg} resolution. We systematically assess the impact of autoregressive training steps, model capacity, and choice of prognostic variables, identifying configurations that enable stable 10-year rollouts while preserving the statistical properties of the reference dataset. Notably, rollouts with SFNO exhibit the greatest robustness to hyperparameter choices, yet all models can experience instability depending on the random seed and the set of prognostic variables

📄 PDF Abstract BibTeX arXiv:2505.02506

Code (1)

LSX-UniWue/dl-climate-models 공식 구현 pytorch

Tasks

Deep Learning

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Autoregressive Renaissance in Neural PDE Solvers

2023-10-30 · Yolanne Yi Ran Lee

Recent developments in the field of neural partial differential equation (PDE) solvers have placed a strong emphasis on neural operators. However, the paper "Message Passing Neural PDE Solver" by Brandstetter et al. publ…

Graph Neural Network

Machine Learning Workflows in Climate Modeling: Design Patterns and Insights from Case Studies

2025-09-30 · Tian Zheng, Subashree Venkatasubramanian, Shuolin Li, Amy Braverman 외 arxiv

Machine learning has been increasingly applied in climate modeling on system emulation acceleration, data-driven parameter inference, forecasting, and knowledge discovery, addressing challenges such as physical consisten…

Transfer Learning

ArchesClimate: Probabilistic Decadal Ensemble Generation With Flow Matching

2025-09-19 · Graham Clyne, Guillaume Couairon, Guillaume Gastineau, Claire Monteleoni 외 arxiv

Internal variability is a dominant contributor to the uncertainty of predictions at the interannual to decadal timescale. A typical approach to separating the internal variability from forced climate responses is to gene…

Exploring Monetary Policy Shocks with Large-Scale Bayesian VARs

2025-05-10 · Dimitris Korobilis

I introduce a high-dimensional Bayesian vector autoregressive (BVAR) framework designed to estimate the effects of conventional monetary policy shocks. The model captures structural shocks as latent factors, enabling com…

GUD: Generation with Unified Diffusion

2024-10-03 · Mathis Gerdes, Max Welling, Miranda C. N. Cheng

Diffusion generative models transform noise into data by inverting a process that progressively adds noise to data samples. Inspired by concepts from the renormalization group in physics, which analyzes systems across di…

Scheduling