Field-Space Autoencoder for Scalable Climate Emulators

• URL: http://arxiv.org/abs/2601.15102v1
• Date: Wed, 21 Jan 2026 15:43:53 GMT
• Title: Field-Space Autoencoder for Scalable Climate Emulators
• Authors: Johannes Meuer, Maximilian Witte, Étiénne Plésiat, Thomas Ludwig, Christopher Kadow,
• Abstract summary: We present a scalable climate emulation framework based on a spherical compression model.<n>By utilizing Field-Space Attention, the model efficiently operates on native climate model output.<n>The model can simultaneously learn internal variability from abundant low-resolution data and sparse high-resolution data.
• Score: 1.3048920509133806
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Kilometer-scale Earth system models are essential for capturing local climate change. However, these models are computationally expensive and produce petabyte-scale outputs, which limits their utility for applications such as probabilistic risk assessment. Here, we present the Field-Space Autoencoder, a scalable climate emulation framework based on a spherical compression model that overcomes these challenges. By utilizing Field-Space Attention, the model efficiently operates on native climate model output and therefore avoids geometric distortions caused by forcing spherical data onto Euclidean grids. This approach preserves physical structures significantly better than convolutional baselines. By producing a structured compressed field, it serves as a good baseline for downstream generative emulation. In addition, the model can perform zero-shot super-resolution that maps low-resolution large ensembles and scarce high-resolution data into a shared representation. We train a generative diffusion model on these compressed fields. The model can simultaneously learn internal variability from abundant low-resolution data and fine-scale physics from sparse high-resolution data. Our work bridges the gap between the high volume of low-resolution ensemble statistics and the scarcity of high-resolution physical detail.

Related papers

• Toward generative machine learning for boosting ensembles of climate simulations [0.0]
  We develop a conditional Variational Autoencoder (cVAE) trained on a limited sample of climate simulations to generate arbitrary large ensembles.<n>We show that the cVAE model learns the underlying distribution of the data and generates physically consistent samples that reproduce realistic low and high moment statistics.
  arXiv  Detail & Related papers  (2026-02-06T00:54:19Z)
• MambaDS: Near-Surface Meteorological Field Downscaling with Topography Constrained Selective State Space Modeling [68.69647625472464]
  Downscaling, a crucial task in meteorological forecasting, enables the reconstruction of high-resolution meteorological states for target regions. Previous downscaling methods lacked tailored designs for meteorology and encountered structural limitations. We propose a novel model called MambaDS, which enhances the utilization of multivariable correlations and topography information.
  arXiv  Detail & Related papers  (2024-08-20T13:45:49Z)
• $\infty$-Brush: Controllable Large Image Synthesis with Diffusion Models in Infinite Dimensions [58.42011190989414]
  We introduce a novel conditional diffusion model in infinite dimensions, $infty$-Brush for controllable large image synthesis. To our best knowledge, $infty$-Brush is the first conditional diffusion model in function space, that can controllably synthesize images at arbitrary resolutions of up to $4096times4096$ pixels.
  arXiv  Detail & Related papers  (2024-07-20T00:04:49Z)
• Generative Adversarial Models for Extreme Geospatial Downscaling [0.0]
  This paper describes a conditional GAN-based geospatial downscaling method that can accommodate very high scaling factors. The method explicitly considers the uncertainty inherent to the downscaling process that tends to be ignored in existing methods. It produces a multitude of plausible high-resolution samples instead of one single deterministic result.
  arXiv  Detail & Related papers  (2024-02-21T18:25:04Z)
• Residual Corrective Diffusion Modeling for Km-scale Atmospheric Downscaling [58.456404022536425]
  State of the art for physical hazard prediction from weather and climate requires expensive km-scale numerical simulations driven by coarser resolution global inputs. Here, a generative diffusion architecture is explored for downscaling such global inputs to km-scale, as a cost-effective machine learning alternative. The model is trained to predict 2km data from a regional weather model over Taiwan, conditioned on a 25km global reanalysis.
  arXiv  Detail & Related papers  (2023-09-24T19:57:22Z)
• FaIRGP: A Bayesian Energy Balance Model for Surface Temperatures Emulation [13.745581787463962]
  We introduce FaIRGP, a data-driven emulator that satisfies the physical temperature response equations of an energy balance model. We show how FaIRGP can be used to obtain estimates of top-of-atmosphere radiative forcing. We hope that this work will contribute to widening the adoption of data-driven methods in climate emulation.
  arXiv  Detail & Related papers  (2023-07-14T08:43:36Z)
• Fourier Neural Operators for Arbitrary Resolution Climate Data Downscaling [16.890326773246414]
  We propose a downscaling method based on the Fourier neural operator. We show that our method significantly outperforms state-of-the-art convolutional and generative adversarial downscaling models. Overall, our work bridges the gap between simulation of a physical process and low-resolution output.
  arXiv  Detail & Related papers  (2023-05-23T18:25:08Z)
• ClimaX: A foundation model for weather and climate [51.208269971019504]
  ClimaX is a deep learning model for weather and climate science. It can be pre-trained with a self-supervised learning objective on climate datasets. It can be fine-tuned to address a breadth of climate and weather tasks.
  arXiv  Detail & Related papers  (2023-01-24T23:19:01Z)
• Towards Understanding and Mitigating Dimensional Collapse in Heterogeneous Federated Learning [112.69497636932955]
  Federated learning aims to train models across different clients without the sharing of data for privacy considerations. We study how data heterogeneity affects the representations of the globally aggregated models. We propose sc FedDecorr, a novel method that can effectively mitigate dimensional collapse in federated learning.
  arXiv  Detail & Related papers  (2022-10-01T09:04:17Z)
• Few Shot Generative Model Adaption via Relaxed Spatial Structural Alignment [130.84010267004803]
  Training a generative adversarial network (GAN) with limited data has been a challenging task. A feasible solution is to start with a GAN well-trained on a large scale source domain and adapt it to the target domain with a few samples, termed as few shot generative model adaption. We propose a relaxed spatial structural alignment method to calibrate the target generative models during the adaption.
  arXiv  Detail & Related papers  (2022-03-06T14:26:25Z)
• Learning the structure of wind: A data-driven nonlocal turbulence model for the atmospheric boundary layer [0.0]
  We develop a novel data-driven approach to modeling the atmospheric boundary layer. This approach leads to a nonlocal, anisotropic synthetic turbulence model which we refer to as the deep rapid distortion (DRD) model.
  arXiv  Detail & Related papers  (2021-07-23T06:41:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.