Cloud and Aerosol Variability across Different Synoptic Regimes Identified with a Deep Learning-Based Unsupervised Clustering Model

The weather synoptic regimes are usually defined by multiple conditions. To define weather synoptic regimes and simultaneously constrain multiple large-scale conditions, we developed a Deep Spatiotemporal Clustering (DSC) model using deep learning-based unsupervised clustering algorithms. The DSC model utilizes an autoencoder integrating Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) layers to learn latent representations of the spatiotemporal data. DSC also includes a unique layer for cluster assignment on latent representations that uses the student’s t-distribution. Our experiments with ERA5 analysis data found the proposed approach outperforms both conventional and previous deep learning-based unsupervised clustering algorithms in terms of varied matrix.

To investigate aerosol and cloud variability across different synoptic regimes over the eastern North Atlantic (ENA) region, we utilized reanalysis data in the form of daily 2-D maps of multiple variables (500-hPa Geopotential height, Sea-level pressure, 10-m U, and 10-m V) from 2016 to 2021 as input data for the DSC model. This allowed us to classify the synoptic regimes that exhibited strong correlations with different cloud conditions. We characterized aerosol and cloud variability for different synoptic regimes using aerosol reanalysis data, satellite cloud retrievals and ground-based observations from the U.S. DOE Atmospheric Radiation Measurement (ARM) ENA atmospheric observatory. Our analyses suggest that the differences in cloud macro and micro properties among these regimes are more significant than the changes observed in most aerosol properties.

Acknowledgement: This work is supported by the DOE Office of Science Early Career Research Program. This work was performed under the auspices of the U.S. DOE by LLNL under contract DE-AC52-07NA27344. LLNL-ABS-853417