Physics-Guided Learning of Meteorological Dynamics for Weather Downscaling and Forecasting

• URL: http://arxiv.org/abs/2505.14555v2
• Date: Fri, 23 May 2025 05:09:32 GMT
• Title: Physics-Guided Learning of Meteorological Dynamics for Weather Downscaling and Forecasting
• Authors: Yingtao Luo, Shikai Fang, Binqing Wu, Qingsong Wen, Liang Sun,
• Abstract summary: Weather forecasting is essential but remains computationally intensive and physically incomplete.<n>We propose PhyDL-NWP, a physics-guided deep learning framework that integrates physical equations with latent forceization into data-driven models.<n>Experiments show that PhyDL-NWP improves both forecasting performance and physical consistency.
• Score: 19.41746149629991
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Weather forecasting is essential but remains computationally intensive and physically incomplete in traditional numerical weather prediction (NWP) methods. Deep learning (DL) models offer efficiency and accuracy but often ignore physical laws, limiting interpretability and generalization. We propose PhyDL-NWP, a physics-guided deep learning framework that integrates physical equations with latent force parameterization into data-driven models. It predicts weather variables from arbitrary spatiotemporal coordinates, computes physical terms via automatic differentiation, and uses a physics-informed loss to align predictions with governing dynamics. PhyDL-NWP enables resolution-free downscaling by modeling weather as a continuous function and fine-tunes pre-trained models with minimal overhead, achieving up to 170x faster inference with only 55K parameters. Experiments show that PhyDL-NWP improves both forecasting performance and physical consistency.

Related papers

• Self-Supervised Learning with Probabilistic Density Labeling for Rainfall Probability Estimation [16.086011448639635]
  SSLPDL is a post-processing method for estimating rainfall probability by post-processing NWP forecasts.<n>We introduce a straightforward labeling approach based on probability density to address the class imbalance in extreme weather phenomena.<n> Experimental results show that SSLPDL surpasses other precipitation forecasting models in regional precipitation post-processing.
  arXiv  Detail & Related papers  (2024-12-08T05:56:09Z)
• Physics-guided Active Sample Reweighting for Urban Flow Prediction [75.24539704456791]
  Urban flow prediction is a nuanced-temporal modeling that estimates the throughput of transportation services like buses, taxis and ride-driven models. Some recent prediction solutions bring remedies with the notion of physics-guided machine learning (PGML) We develop a atized physics-guided network (PN), and propose a data-aware framework Physics-guided Active Sample Reweighting (P-GASR)
  arXiv  Detail & Related papers  (2024-07-18T15:44:23Z)
• Towards Physically Consistent Deep Learning For Climate Model Parameterizations [46.07009109585047]
  parameterizations are a major source of systematic errors and large uncertainties in climate projections. Deep learning (DL)-based parameterizations, trained on data from computationally expensive short, high-resolution simulations, have shown great promise for improving climate models. We propose an efficient supervised learning framework for DL-based parameterizations that leads to physically consistent models.
  arXiv  Detail & Related papers  (2024-06-06T10:02:49Z)
• Generalizing Weather Forecast to Fine-grained Temporal Scales via Physics-AI Hybrid Modeling [55.13352174687475]
  This paper proposes a physics-AI hybrid model (i.e., WeatherGFT) which generalizes weather forecasts to finer-grained temporal scales beyond training dataset.<n>Specifically, we employ a carefully designed PDE kernel to simulate physical evolution on a small time scale.<n>We also introduce a lead time-aware training framework to promote the generalization of the model at different lead times.
  arXiv  Detail & Related papers  (2024-05-22T16:21:02Z)
• ClimODE: Climate and Weather Forecasting with Physics-informed Neural ODEs [14.095897879222676]
  We present ClimODE, a continuous-time process that implements key principle of statistical mechanics. ClimODE models precise weather evolution with value-conserving dynamics, learning global weather transport as a neural flow. Our approach outperforms existing data-driven methods in global, regional forecasting with an order of magnitude smaller parameterization.
  arXiv  Detail & Related papers  (2024-04-15T06:38:21Z)
• Weather Prediction with Diffusion Guided by Realistic Forecast Processes [49.07556359513563]
  We introduce a novel method that applies diffusion models (DM) for weather forecasting. Our method can achieve both direct and iterative forecasting with the same modeling framework. The flexibility and controllability of our model empowers a more trustworthy DL system for the general weather community.
  arXiv  Detail & Related papers  (2024-02-06T21:28:42Z)
• ExtremeCast: Boosting Extreme Value Prediction for Global Weather Forecast [57.6987191099507]
  We introduce Exloss, a novel loss function that performs asymmetric optimization and highlights extreme values to obtain accurate extreme weather forecast. We also introduce ExBooster, which captures the uncertainty in prediction outcomes by employing multiple random samples. Our solution can achieve state-of-the-art performance in extreme weather prediction, while maintaining the overall forecast accuracy comparable to the top medium-range forecast models.
  arXiv  Detail & Related papers  (2024-02-02T10:34:13Z)
• DeepPhysiNet: Bridging Deep Learning and Atmospheric Physics for Accurate and Continuous Weather Modeling [24.848981502799244]
  There are two paradigms for weather forecasting: Numerical Weather Prediction (WP) and Deep Learning-based Prediction (DLP) WP utilizes atmospheric physics for weather modeling but suffers from poor data utilization and high computational costs. DLP can learn weather patterns from vast amounts of data directly but struggles to incorporate physical laws. We introduce the DeepPhysiNet framework, incorporating physical laws into deep learning models for accurate and continuous weather system modeling.
  arXiv  Detail & Related papers  (2024-01-04T05:05:16Z)
• 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)
• Physics-constrained deep learning postprocessing of temperature and humidity [0.0]
  We propose to achieve physical consistency in deep learning-based postprocessing models. We find that constraining a neural network to enforce thermodynamic state equations yields physically-consistent predictions.
  arXiv  Detail & Related papers  (2022-12-07T09:31:25Z)

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.