High-Resolution Probabilistic Data-Driven Weather Modeling with a Stretched-Grid

TL;DR

This paper introduces a probabilistic, high-resolution weather model using a stretched grid and a stochastic encoder-decoder architecture, capable of generating spatially coherent ensemble forecasts for multiple variables.

Contribution

It presents a novel data-driven weather modeling approach with a stretched grid and spectral loss, improving spatial coherence and forecast accuracy over existing models.

Findings

Model produces spatially coherent high-resolution forecasts.

Competitive performance compared to operational numerical weather prediction.

Spectral loss component enhances spatial coherence in generated fields.

Abstract

We present a probabilistic data-driven weather model capable of providing an ensemble of high spatial resolution realizations of 87 variables at arbitrary forecast length and ensemble size. The model uses a stretched grid, dedicating 2.5 km resolution to a region of interest, and 31 km resolution elsewhere. Based on a stochastic encoder-decoder architecture, the model is trained using a loss function based on the Continuous Ranked Probability Score (CRPS) evaluated point-wise in real and spectral space. The spectral loss components is shown to be necessary to create fields that are spatially coherent. The model is compared to high-resolution operational numerical weather prediction forecasts from the MetCoOp Ensemble Prediction System (MEPS), showing competitive forecasts when evaluated against observations from surface weather stations. The model produced fields that are more spatially coherent than mean squared error based models and CRPS based models without the spectral component in the loss.