Improving Prediction of Marine Low Clouds Using Cloud Droplet Number Concentration in a Convolutional Neural Network

Marine low clouds play a crucial role in cooling the climate, but accurately predicting them remains challenging due to their highly non-linear response to various factors. Previous studies usually overlook the effects of cloud droplet number concentration (N_d) and the non-local information of the target grids. To address these challenges, we introduce a convolutional neural network model (CNN_Met-Nd) that uses both local and non-local information and includes N_d as a cloud-controlling factor to enhance the predictive ability of daily cloud cover, albedo, and cloud radiative effects (CRE) for global marine low clouds. CNN_Met-Nd demonstrates superior performance, explaining over 70% of the variance in these three cloud variables for scenes of 1° × 1°, a notable improvement over past efforts. CNN_Met-Nd also accurately replicates geographical patterns of trends in marine low clouds from 2003 to 2022. In contrast, a similar model without N_d (CNN_Met) struggles to predict long-term trends in cloud properties effectively. Permutation importance analysis further highlights the critical role of N_d in CNN_Met-N's predictive success. Further comparisons with an artificial neural network (ANN_Met-Nd) model, which uses the same inputs but without considering spatial dependence, show CNN_Met-Nd's superior performance with R² values for cloud cover, albedo, and CRE being 0.16, 0.12, and 0.18 higher, respectively. This highlights the importance of incorporating non-local information, at least on a daily scale, into low cloud predictions to enhance climate model parameterizations.