This study introduces an original methodology combining ensemble boosting and conditional probability theory to estimate return periods of rare climate extremes without relying on long climate simulations. The method is rigorously developed, validated on a red-noise process, and applied to CESM2 simulations, including an analysis of the 2021 Pacific Northwest heatwave. Importantly, this framework enables linking probability estimates to specific climate storylines, allowing an assessment of the odds that an extreme event like the one examined will occur in the future.

The occurrence and predictability of extreme events is often modulated by regional dynamical drivers, but their identification is not straightforward. This paper by Fiona Spuler et al. presents an innovate approach to dimensionality reduction targeted on regionally occurring phenomena. Their approach is based on a machine-learning method demonstrating, in a broad sense, that these method can identify physically interpretable drivers of targeted phenomena. The authors discuss the tradeoff between regime informativeness of local precipitation extremes and predictability of the regimes at subseasonal lead times. The novel machine-learning-based approach may find useful application beyond atmospheric and climate science.

This study provides a unifying framework for extratropical low-pressure systems with tropical characteristics like nearly axisymmetric inner cores, eyes, and spiral bands. These characteristics can be found, e.g., in subtropical cyclones, polar lows, and medicanes. The authors propose to call these cyclones CYCLOPs, which refers to "cyclones from locally originating potential intensity". The paper presents several case studies to explain and illustrate the new concept, and therefore the paper is also of particular educational value.