On the Prediction of Aerosol-Cloud Interactions Within a Data-Driven Framework

Abstract

Aerosol-cloud interactions (ACI) pose the largest uncertainty for climate projection. Among many challenges of understanding ACI, the question of whether ACI can be deterministically predicted has not been explicitly answered. Here we attempt to answer this question by predicting cloud droplet number concentration $N_c$ from aerosol number concentration $N_a$ and ambient conditions using a data-driven framework. We use aerosol properties, vertical velocity fluctuations, and meteorological states from the ACTIVATE field observations (2020–2022) as predictors to estimate $N_c$. We show that the campaign-wide $N_c$ can be successfully predicted using machine learning models despite the strongly nonlinear and multi-scale nature of ACI. However, the observation-trained machine learning model fails to predict $N_c$ in individual cases while it successfully predicts $N_c$ of randomly selected data points that cover a broad spatiotemporal scale. This suggests that, within a data-driven framework, the $N_c$ prediction is uncertain at fine spatiotemporal scales.