paper-with-me

Papers

SwinVRNN: A Data-Driven Ensemble Forecasting Model via Learned Distribution Perturbation

2022-05-26 · Yuan Hu, Lei Chen, Zhibin Wang, Hao Li

Data-driven approaches for medium-range weather forecasting are recently shown extraordinarily promising for ensemble forecasting for their fast inference speed compared to traditional numerical weather prediction (NWP) models, but their forecast accuracy can hardly match the state-of-the-art operational ECMWF Integrated Forecasting System (IFS) model. Previous data-driven attempts achieve ensemble forecast using some simple perturbation methods, like initial condition perturbation and Monte Carlo dropout. However, they mostly suffer unsatisfactory ensemble performance, which is arguably attributed to the sub-optimal ways of applying perturbation. We propose a Swin Transformer-based Variational Recurrent Neural Network (SwinVRNN), which is a stochastic weather forecasting model combining a SwinRNN predictor with a perturbation module. SwinRNN is designed as a Swin Transformer-based recurrent neural network, which predicts future states deterministically. Furthermore, to model the stochasticity in prediction, we design a perturbation module following the Variational Auto-Encoder paradigm to learn multivariate Gaussian distributions of a time-variant stochastic latent variable from data. Ensemble forecasting can be easily achieved by perturbing the model features leveraging noise sampled from the learned distribution. We also compare four categories of perturbation methods for ensemble forecasting, i.e. fixed distribution perturbation, learned distribution perturbation, MC dropout, and multi model ensemble. Comparisons on WeatherBench dataset show the learned distribution perturbation method using our SwinVRNN model achieves superior forecast accuracy and reasonable ensemble spread due to joint optimization of the two targets. More notably, SwinVRNN surpasses operational IFS on surface variables of 2-m temperature and 6-hourly total precipitation at all lead times up to five days.

📄 PDF Abstract BibTeX arXiv:2205.13158

Code (0)

등록된 구현이 없습니다.

Tasks

Weather Forecasting

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Uncertainty-Aware End-to-End AI Weather Forecasting: Disentangling Observation and Model Contributions

2026-08-31 · Rodrigo Almeida, Noelia Otero, Jost Arndt, Simon Baur 외 hf

End-to-end weather forecasting systems produce skillful global gridded and station forecasts directly from raw Earth observations, replacing the numerical weather prediction pipeline, including data assimilation, at a fr…

Weather Forecasting

An ensemble of data-driven weather prediction models for operational sub-seasonal forecasting

2024-03-22 · Jonathan A. Weyn, Divya Kumar, Jeremy Berman, Najeeb Kazmi 외

We present an operations-ready multi-model ensemble weather forecasting system which uses hybrid data-driven weather prediction models coupled with the European Centre for Medium-range Weather Forecasts (ECMWF) ocean mod…

Weather Forecasting

Attention-Based Ensemble Pooling for Time Series Forecasting

2023-10-24 · Dhruvit Patel, Alexander Wikner

A common technique to reduce model bias in time-series forecasting is to use an ensemble of predictive models and pool their output into an ensemble forecast. In cases where each predictive model has different biases, ho…

Time SeriesTime Series Forecastingvalid

Continuous Ensemble Weather Forecasting with Diffusion models

2024-10-07 · Martin Andrae, Tomas Landelius, Joel Oskarsson, Fredrik Lindsten

Weather forecasting has seen a shift in methods from numerical simulations to data-driven systems. While initial research in the area focused on deterministic forecasting, recent works have used diffusion models to produ…

Weather Forecasting

SimCast-S2S: An Efficient Generative Model for Subseasonal Precipitation Forecasting via Transfer Learning from Climate Simulations

2026-08-27 · Hiep V. Dang, Antonios Mamalakis arxiv

Subseasonal-to-seasonal (S2S) precipitation forecasting has substantial financial and societal impact, yet remains challenging because of weak predictive signals, high associated uncertainty, and the computational cost o…

Precipitation ForecastingTransfer Learning