Towards replacing precipitation ensemble predictions systems using machine learning

TL;DR

This paper introduces a novel machine learning approach using generative adversarial networks to generate high-resolution precipitation ensemble predictions without needing high-resolution training data, aiming to improve forecast accuracy efficiently.

Contribution

The paper presents a GAN-based method to produce realistic precipitation ensembles at high resolutions using only control forecasts, bypassing the need for costly high-resolution simulations.

Findings

Generated ensembles closely match ECMWF IFS ensemble metrics

The approach produces diverse, realistic precipitation fields

Method reduces computational costs for high-resolution forecasting

Abstract

Precipitation forecasts are less accurate compared to other meteorological fields because several key processes affecting precipitation distribution and intensity occur below the resolved scale of global weather prediction models. This requires to use higher resolution simulations. To generate an uncertainty prediction associated with the forecast, ensembles of simulations are run simultaneously. However, the computational cost is a limiting factor here. Thus, instead of generating an ensemble system from simulations there is a trend of using neural networks. Unfortunately the data for high resolution ensemble runs is not available. We propose a new approach to generating ensemble weather predictions for high-resolution precipitation without requiring high-resolution training data. The method uses generative adversarial networks to learn the complex patterns of precipitation and produce diverse and realistic precipitation fields, allowing to generate realistic precipitation ensemble members using only the available control forecast. We demonstrate the feasibility of generating realistic precipitation ensemble members on unseen higher resolutions. We use evaluation metrics such as RMSE, CRPS, rank histogram and ROC curves to demonstrate that our generated ensemble is almost identical to the ECMWF IFS ensemble.