Score-based diffusion nowcasting of GOES imagery

• URL: http://arxiv.org/abs/2505.10432v1
• Date: Thu, 15 May 2025 15:51:41 GMT
• Title: Score-based diffusion nowcasting of GOES imagery
• Authors: Randy J. Chase, Katherine Haynes, Lander Ver Hoef, Imme Ebert-Uphoff,
• Abstract summary: We explore a newer method, named score-based diffusion, to nowcast (zero to three hour forecast) clouds and precipitation.<n>Our results show that the diffusion models are able to not only advect existing clouds, but also generate and decay clouds, including convective initiation.<n>The best of the three diffusion models tested was the CorrDiff approach, outperforming all other diffusion models, the traditional U-Net, and a persistence forecast by one to two kelvin on root mean squared error.
• Score: 0.6597195879147557
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Clouds and precipitation are important for understanding weather and climate. Simulating clouds and precipitation with traditional numerical weather prediction is challenging because of the sub-grid parameterizations required. Machine learning has been explored for forecasting clouds and precipitation, but early machine learning methods often created blurry forecasts. In this paper we explore a newer method, named score-based diffusion, to nowcast (zero to three hour forecast) clouds and precipitation. We discuss the background and intuition of score-based diffusion models - thus providing a starting point for the community - while exploring the methodology's use for nowcasting geostationary infrared imagery. We experiment with three main types of diffusion models: a standard score-based diffusion model (Diff); a residual correction diffusion model (CorrDiff); and a latent diffusion model (LDM). Our results show that the diffusion models are able to not only advect existing clouds, but also generate and decay clouds, including convective initiation. These results are surprising because the forecasts are initiated with only the past 20 mins of infrared satellite imagery. A case study qualitatively shows the preservation of high resolution features longer into the forecast than a conventional mean-squared error trained U-Net. The best of the three diffusion models tested was the CorrDiff approach, outperforming all other diffusion models, the traditional U-Net, and a persistence forecast by one to two kelvin on root mean squared error. The diffusion models also enable out-of-the-box ensemble generation, which shows skillful calibration, with the spread of the ensemble correlating well to the error.

Related papers

• Data-driven Mesoscale Weather Forecasting Combining Swin-Unet and Diffusion Models [0.0]
  This study proposes an architecture that combines a diffusion model with Swin-Unet as a deterministic model.<n>The proposed architecture trains the two models independently, allowing the diffusion model to remain unchanged when the deterministic model is updated.
  arXiv  Detail & Related papers  (2025-03-25T05:07:31Z)
• Downscaling Precipitation with Bias-informed Conditional Diffusion Model [10.545983522538085]
  Current Global Climate Models operate at spatial resolutions too coarse for localized analyses.<n>Deep learning-based statistical downscaling methods offer promising solutions.<n>We introduce a bias-informed conditional diffusion model for statistical downscaling of precipitation.
  arXiv  Detail & Related papers  (2024-12-19T05:36:52Z)
• PostCast: Generalizable Postprocessing for Precipitation Nowcasting via Unsupervised Blurriness Modeling [85.56969895866243]
  We propose an unsupervised postprocessing method to eliminate the blurriness without the requirement of training with the pairs of blurry predictions and corresponding ground truth. A zero-shot blur kernel estimation mechanism and an auto-scale denoise guidance strategy are introduced to adapt the unconditional correlations to any blurriness modes.
  arXiv  Detail & Related papers  (2024-10-08T08:38:23Z)
• Guided Diffusion from Self-Supervised Diffusion Features [49.78673164423208]
  Guidance serves as a key concept in diffusion models, yet its effectiveness is often limited by the need for extra data annotation or pretraining. We propose a framework to extract guidance from, and specifically for, diffusion models.
  arXiv  Detail & Related papers  (2023-12-14T11:19:11Z)
• DiffCast: A Unified Framework via Residual Diffusion for Precipitation Nowcasting [20.657502066923023]
  Precipitation nowcasting is an important task to predict the radar echoes sequences based on current observations, which can serve both meteorological science and smart city applications. Previous studies address the problem either from the perspectives of deterministic modeling or probabilistic modeling. We propose to decompose and model the chaotic evolutionary precipitation systems from the perspective of global deterministic motion and local variations with residual mechanism.
  arXiv  Detail & Related papers  (2023-12-11T11:26:32Z)
• Projection Regret: Reducing Background Bias for Novelty Detection via Diffusion Models [72.07462371883501]
  We propose emphProjection Regret (PR), an efficient novelty detection method that mitigates the bias of non-semantic information. PR computes the perceptual distance between the test image and its diffusion-based projection to detect abnormality. Extensive experiments demonstrate that PR outperforms the prior art of generative-model-based novelty detection methods by a significant margin.
  arXiv  Detail & Related papers  (2023-12-05T09:44:47Z)
• Precipitation nowcasting with generative diffusion models [0.0]
  We study the efficacy of diffusion models in handling the task of precipitation nowcasting. Our work is conducted in comparison to the performance of well-established U-Net models.
  arXiv  Detail & Related papers  (2023-08-13T09:51:16Z)
• Deceptive-NeRF/3DGS: Diffusion-Generated Pseudo-Observations for High-Quality Sparse-View Reconstruction [60.52716381465063]
  We introduce Deceptive-NeRF/3DGS to enhance sparse-view reconstruction with only a limited set of input images. Specifically, we propose a deceptive diffusion model turning noisy images rendered from few-view reconstructions into high-quality pseudo-observations. Our system progressively incorporates diffusion-generated pseudo-observations into the training image sets, ultimately densifying the sparse input observations by 5 to 10 times.
  arXiv  Detail & Related papers  (2023-05-24T14:00:32Z)
• Bi-Noising Diffusion: Towards Conditional Diffusion Models with Generative Restoration Priors [64.24948495708337]
  We introduce a new method that brings predicted samples to the training data manifold using a pretrained unconditional diffusion model. We perform comprehensive experiments to demonstrate the effectiveness of our approach on super-resolution, colorization, turbulence removal, and image-deraining tasks.
  arXiv  Detail & Related papers  (2022-12-14T17:26:35Z)
• Diffusion Models in Vision: A Survey [73.10116197883303]
  A diffusion model is a deep generative model that is based on two stages, a forward diffusion stage and a reverse diffusion stage.<n> Diffusion models are widely appreciated for the quality and diversity of the generated samples, despite their known computational burdens.
  arXiv  Detail & Related papers  (2022-09-10T22:00:30Z)

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.