Identifying probabilistic weather regimes targeted to a local-scale impact variable

TL;DR

This paper introduces RMM-VAE, a novel probabilistic machine learning approach using variational autoencoders to identify weather regimes specifically linked to local impact variables, improving prediction and robustness.

Contribution

The paper presents a new method, RMM-VAE, that combines non-linear dimensionality reduction, prediction, and probabilistic clustering to target weather regimes relevant to local impact variables.

Findings

RMM-VAE outperforms linear methods in predicting the target variable.

It provides more robust and persistent regimes than existing machine learning approaches.

The method enhances input space reconstruction, benefiting climate applications.

Abstract

Weather regimes are recurrent and persistent large-scale atmospheric circulation patterns that modulate the occurrence of local impact variables such as extreme precipitation. In their capacity as mediators between long-range teleconnections and these local extremes, they have shown potential for improving sub-seasonal forecasting as well as long-term climate projections. However, existing methods for identifying weather regimes are not designed to capture the physical processes relevant to the impact variable in question while still representing the full atmospheric phase space. This paper introduces a novel probabilistic machine learning method, RMM-VAE, for identifying weather regimes targeted to a local-scale impact variable. Based on a variational autoencoder architecture, the method combines non-linear dimensionality reduction with a prediction task and probabilistic clustering in a coherent architecture. The new method is applied to identify circulation patterns over the Mediterranean region targeted to precipitation over Morocco and compared to three existing approaches, two established linear methods and another machine learning approach. The RMM-VAE method identifies regimes that are more predictive of the target variable compared to the two linear methods, and more robust and persistent compared to the alternative machine learning method, while also improving the reconstruction of the input space. The results demonstrate the potential benefit of the new method for use in various climate applications such as sub-seasonal forecasting, while also highlighting the trade-offs involved in targeted clustering.