On the Prediction of Aerosol-Cloud Interactions Within a Data-Driven Framework
[1];
[1];
[3];
[4];
[3];
- Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)
- Univ. of Arizona, Tucson, AZ (United States)
- NASA Langley Research Center, Hampton, VA (United States)
- German Aerospace Center (DLR), Oberpfaffenhofen (Germany); Johannes Gutenberg Univ., Mainz (Germany)
- Pacific Northwest National Laboratory (PNNL), Richland, WA (United States); Hanford High School, Richland, WA (United States)
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 Nc from aerosol number concentration Na 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 Nc. We show that the campaign-wide Nc 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 Nc in individual cases while it successfully predicts Nc of randomly selected data points that cover a broad spatiotemporal scale. This suggests that, within a data-driven framework, the Nc prediction is uncertain at fine spatiotemporal scales.
- Research Organization:
- Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)
- Sponsoring Organization:
- USDOE
- Grant/Contract Number:
- AC05-76RL01830
- OSTI ID:
- 2483610
- Report Number(s):
- PNNL-SA-196006
- Journal Information:
- Geophysical Research Letters, Journal Name: Geophysical Research Letters Journal Issue: 24 Vol. 51; ISSN 0094-8276
- Publisher:
- American Geophysical Union (AGU)Copyright Statement
- Country of Publication:
- United States
- Language:
- English
Similar Records
Interpretable ensemble learning unveils main aerosol optical properties in predicting cloud condensation nuclei number concentration
Aerosol and cloud microphysics covariability in the northeast Pacific boundary layer estimated with ship-based and satellite remote sensing observations