A Generative Framework for Probabilistic, Spatiotemporally Coherent Downscaling of Climate Simulation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Schmidt, Jonathan, Schmidt, Luca, Strnad, Felix, Ludwig, Nicole, Hennig, Philipp
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914051626369024
author Schmidt, Jonathan
Schmidt, Luca
Strnad, Felix
Ludwig, Nicole
Hennig, Philipp
author_facet Schmidt, Jonathan
Schmidt, Luca
Strnad, Felix
Ludwig, Nicole
Hennig, Philipp
contents Local climate information is crucial for impact assessment and decision-making, yet coarse global climate simulations cannot capture small-scale phenomena. Current statistical downscaling methods infer these phenomena as temporally decoupled spatial patches. However, to preserve physical properties, estimating spatio-temporally coherent high-resolution weather dynamics for multiple variables across long time horizons is crucial. We present a novel generative framework that uses a score-based diffusion model trained on high-resolution reanalysis data to capture the statistical properties of local weather dynamics. After training, we condition on coarse climate model data to generate weather patterns consistent with the aggregate information. As this predictive task is inherently uncertain, we leverage the probabilistic nature of diffusion models and sample multiple trajectories. We evaluate our approach with high-resolution reanalysis information before applying it to the climate model downscaling task. We then demonstrate that the model generates spatially and temporally coherent weather dynamics that align with global climate output.
format Preprint
id arxiv_https___arxiv_org_abs_2412_15361
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Generative Framework for Probabilistic, Spatiotemporally Coherent Downscaling of Climate Simulation
Schmidt, Jonathan
Schmidt, Luca
Strnad, Felix
Ludwig, Nicole
Hennig, Philipp
Machine Learning
Atmospheric and Oceanic Physics
Local climate information is crucial for impact assessment and decision-making, yet coarse global climate simulations cannot capture small-scale phenomena. Current statistical downscaling methods infer these phenomena as temporally decoupled spatial patches. However, to preserve physical properties, estimating spatio-temporally coherent high-resolution weather dynamics for multiple variables across long time horizons is crucial. We present a novel generative framework that uses a score-based diffusion model trained on high-resolution reanalysis data to capture the statistical properties of local weather dynamics. After training, we condition on coarse climate model data to generate weather patterns consistent with the aggregate information. As this predictive task is inherently uncertain, we leverage the probabilistic nature of diffusion models and sample multiple trajectories. We evaluate our approach with high-resolution reanalysis information before applying it to the climate model downscaling task. We then demonstrate that the model generates spatially and temporally coherent weather dynamics that align with global climate output.
title A Generative Framework for Probabilistic, Spatiotemporally Coherent Downscaling of Climate Simulation
topic Machine Learning
Atmospheric and Oceanic Physics
url https://arxiv.org/abs/2412.15361