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 (Nd) and the non‐local information of the target grids. To address these challenges, we introduce a convolutional neural network model (CNNMet‐Nd) that uses both local and non‐local information and includes Nd 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. CNNMet‐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. CNNMet‐Nd also accurately replicates geographical patterns of trends in marine low clouds from 2003 to 2022. In contrast, a similar model without Nd (CNNMet) struggles to predict long‐term trends in cloud properties effectively. Permutation importance analysis further highlights the critical role of Nd in CNNMet‐N's predictive success. Further comparisons with an artificial neural network (ANNMet‐Nd) model, which uses the same inputs but without considering spatial dependence, show CNNMet‐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.
Understanding cloud phase changes over the Tibetan Plateau (TP) is crucial for regional and global climate research. Based on 17 years (2003–2019) of satellite and reanalysis data combined with a multivariate regression model, this study identifies a distinctive transition from supercooled to ice clouds over the TP, in contrast to most Asian regions where atmospheric warming favors a shift from cold to warm clouds. The transition is most pronounced in summer, with supercooled cloud fraction () decreasing by 3.5% per decade and ice increasing by 2.7% per decade. Enhanced cloud vertical development primarily drives this transition, accompanied by cloud‐top cooling of 6.0°C for supercooled and 10.2°C for ice clouds over the 17‐year period. Surface and atmospheric warming, changes in large‐scale circulation, and warmer glaciation temperatures contribute to the cooling. These findings underscore the unique cloud‐phase changes over the TP and highlight the need for further research on their climate implications.
16 November 2024 in Journal of Geophysical Research: Atmospheres
Marine low clouds significantly cool the climate, but predicting these clouds remains challenging: the response of these clouds to various factors is highly non-linear. Previous studies usually overlook the effects of cloud droplet number concentration (Nd) and the non-local information of the target grids. To address these challenges, we introduce a convolutional neural network model (CNNMet-Nd) that uses both local and non-local information and includes Nd as a cloud-controlling factor to enhance the predictive ability of cloud cover, albedo, and cloud radiative effects (CRE) for global marine low clouds. CNNMet-Nd demonstrates superior performance, explaining over 70% of the variance in these three cloud variables for instantaneous scenes of 1°×1°, a notable improvement over past efforts. CNNMet-Nd also accurately replicates geographical patterns of trends in marine low clouds from 2003 to 2022. In contrast, a similar convolutional neural network model without Nd input (CNNMet) fails to predict global mean cloud properties effectively, underscoring the critical role of Nd. Further comparisons with an artificial neural network (ANNMet-Nd) model, which uses the same inputs but without considering spatial dependence, show CNNMet-Nd’s superior performance with R2 values for cloud cover, albedo, and CRE being 0.16, 0.11, and 0.18 higher, respectively. This highlights the importance of incorporating non-local information into low cloud predictions to enhance climate model parameterizations.
13 December 2025 in Journal of Geophysical Research: Atmospheres