Monday, 13 January 2025
Hall C (New Orleans Ernest N. Morial Convention Center)
Aerosol-cloud interactions (ACI) are the source of the largest uncertainties for climate
simulations. Among many challenges of understanding ACI, the question of
whether ACI can be deterministically predicted has not been explicitly
formulated or asked. 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 to 2022) as
predictors to estimate Nc. We show that the climatological 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, for predictive purposes, ACI is essentially stochastic at fine spatiotemporal scales.
simulations. Among many challenges of understanding ACI, the question of
whether ACI can be deterministically predicted has not been explicitly
formulated or asked. 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 to 2022) as
predictors to estimate Nc. We show that the climatological 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, for predictive purposes, ACI is essentially stochastic at fine spatiotemporal scales.
- Indicates paper has been withdrawn from meeting
- Indicates an Award Winner