Year: 2024
Type: article
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 from aerosol number concentration 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 . We show that the campaign‐wide 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 in individual cases while it successfully predicts of randomly selected data points that cover a broad spatiotemporal scale. This suggests that, within a data‐driven framework, the prediction is uncertain at fine spatiotemporal scales.
Source: Geophysical Research Letters
DOI: 10.1029/2024gl110757
Language: English
Subfield: Global and Planetary Change
Field: Environmental Science
Domain: Physical Sciences
SDG: Climate action
Open Access status: gold
Estimated APC paid: $2,900
Awards: G135623947, G161867597, G1756126698, G1810277828, G2988778103, G3432315254, G4576246833, G5371981458, G538270251, G5726405315, Messung von Aerosol und Wolken und deren Wechselwirkung über dem sauberen Südlichen Ozean (AWWSO), Construction Of Novel CERTification methOds and means of compliance for disruptive technologies, G84288863, G8579532121
OpenAlex ID: W4405374542