Physics-Informed Diffusion Model for Generating Synthetic Extreme Rare Weather Events Data

• URL: http://arxiv.org/abs/2603.06782v1
• Date: Fri, 06 Mar 2026 18:54:55 GMT
• Title: Physics-Informed Diffusion Model for Generating Synthetic Extreme Rare Weather Events Data
• Abstract summary: Traditional data augmentation techniques fail to preserve the physical consistency and high-intensity gradients characteristic of rare Category 4-equivalent events.<n>We propose a physics-informed diffusion model based on the Context-UNet architecture to generate synthetic, multi-spectral satellite imagery of extreme weather events.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Data scarcity is a primary obstacle in developing robust Machine Learning (ML) models for detecting rapidly intensifying tropical cyclones. Traditional data augmentation techniques (rotation, flipping, brightness adjustment) fail to preserve the physical consistency and high-intensity gradients characteristic of rare Category 4-equivalent events, which constitute only 0.14\% of our dataset (202 of 140,514 samples). We propose a physics-informed diffusion model based on the Context-UNet architecture to generate synthetic, multi-spectral satellite imagery of extreme weather events. Our model is conditioned on critical atmospheric parameters such as average wind speed, type of Ocean and stage of development (early, mature, late etc) -- the known drivers of rapid intensification. Using a controlled pre-generated noise sampling strategy and mixed-precision training, we generated $16\times16$ wind-field samples that are cropped from multi-spectral satellite imagery which preserve realistic spatial autocorrelation and physical consistency. Results demonstrate that our model successfully learns discriminative features across ten distinct context classes, effectively mitigating the data bottleneck. Specifically, we address the extreme class imbalance in our dataset, where Class 4 (Ocean 2, early stage with average wind speed 50kn hurricane) contains only 202 samples compared to 79,768 samples in Class 0. This generative framework provides a scalable solution for augmenting training datasets for operational weather detection algorithms. The average Results yield an average Log-Spectral Distance (LSD) of 4.5dB, demonstrating a scalable framework for enhancing operational weather detection algorithms.

Related papers

• VMU-Diff: A Coarse-to-fine Multi-source Data Fusion Framework for Precipitation Nowcasting [9.702321405779513]
  Existing methods rely on single-source radar data to build either deterministic or probabilistic models.<n>This paper proposes a novel coarse-to-fine Vision Mamba Unet and residual Diffusion (VMU-Diff) based precipitation nowcasting framework.<n> Experiments on SWAN datasets demonstrate the improvements of our method over state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-05-14T09:05:30Z)
• A Data Efficiency Study of Synthetic Fog for Object Detection Using the Clear2Fog Pipeline [13.221137493760699]
  Object detection in adverse weather is critical for the safety of autonomous vehicles.<n>We propose Clear2Fog, an end-to-end, physics-based pipeline that simulates fog on clear-weather datasets.
  arXiv  Detail & Related papers  (2026-05-12T18:01:00Z)
• Physically-Induced Atmospheric Adversarial Perturbations: Enhancing Transferability and Robustness in Remote Sensing Image Classification [54.952203312050564]
  Adversarial attacks pose a severe threat to the reliability of deep learning models in remote sensing (RS) image classification.<n>We propose FogFool, a physically plausible adversarial framework that generates fog-based perturbations.<n>Experiments on two benchmark RS datasets demonstrate that FogFool achieves superior performance.
  arXiv  Detail & Related papers  (2026-04-16T05:47:57Z)
• Towards real-time assessment of infrasound event detection capability using deep learning-based transmission loss estimation [5.601176010173589]
  Accurate modeling of infrasound transmission loss is essential for evaluating the performance of the International Monitoring System.<n>State-of-the-art propagation modeling tools enable transmission loss to be finely simulated using atmospheric models.<n>Recent studies made use of a deep learning algorithm capable of making transmission loss predictions almost instantaneously.<n>In this study, we address these limitations by using both wind and temperature fields as inputs to a neural network, simulated up to 130 km altitude and 4,000 km distance.
  arXiv  Detail & Related papers  (2025-06-03T09:49:12Z)
• 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)
• Generative Data Assimilation of Sparse Weather Station Observations at Kilometer Scales [5.427841765899196]
  We demonstrate the viability of score-based data assimilation in the context of realistically complex km-scale weather.<n>By incorporating observations from 40 weather stations, 10% lower RMSEs on left-out stations are attained.<n>It is a ripe time to explore extensions that combine increasingly ambitious regional state generators with an increasing set of in situ, ground-based, and satellite remote sensing data streams.
  arXiv  Detail & Related papers  (2024-06-19T10:28:11Z)
• Learning Robust Precipitation Forecaster by Temporal Frame Interpolation [65.5045412005064]
  We develop a robust precipitation forecasting model that demonstrates resilience against spatial-temporal discrepancies. Our approach has led to significant improvements in forecasting precision, culminating in our model securing textit1st place in the transfer learning leaderboard of the textitWeather4cast'23 competition.
  arXiv  Detail & Related papers  (2023-11-30T08:22:08Z)
• 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)
• Vision in adverse weather: Augmentation using CycleGANs with various object detectors for robust perception in autonomous racing [70.16043883381677]
  In autonomous racing, the weather can change abruptly, causing significant degradation in perception, resulting in ineffective manoeuvres. In order to improve detection in adverse weather, deep-learning-based models typically require extensive datasets captured in such conditions. We introduce an approach of using synthesised adverse condition datasets in autonomous racing (generated using CycleGAN) to improve the performance of four out of five state-of-the-art detectors.
  arXiv  Detail & Related papers  (2022-01-10T10:02:40Z)
• Lidar Light Scattering Augmentation (LISA): Physics-based Simulation of Adverse Weather Conditions for 3D Object Detection [60.89616629421904]
  Lidar-based object detectors are critical parts of the 3D perception pipeline in autonomous navigation systems such as self-driving cars. They are sensitive to adverse weather conditions such as rain, snow and fog due to reduced signal-to-noise ratio (SNR) and signal-to-background ratio (SBR)
  arXiv  Detail & Related papers  (2021-07-14T21:10:47Z)

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.