A convolutional neural network was used to detect occurrences of pockets of open cells (POCs). Trained on a small hand-logged dataset and applied to 13 years of satellite imagery the neural network is able to classify 8,491 POCs. This extensive database allows the first robust analysis of the spatial and temporal prevalence of these phenomena, as well as a detailed analysis of their micro-physical properties. We find a large (30%) increase in cloud effective radius inside POCs as compared to their surroundings and similarly large (20%) decrease in cloud fraction. This also allows their global radiative effect to be determined. Using simple radiative approximations we find that the instantaneous global mean top-of-atmosphere perturbation by all POCs is only 0.01Wm-2.

Clouds are one of the most critical yet uncertain aspects of weather and climate prediction. The complex nature of sub-grid scale cloud processes makes traceable simulation of clouds across scales difficult (or impossible). Often models and measurements are used to develop empirical relationships for large-scale models to be computationally efficient. Machine learning provides another potential tool to improve our empirical parameterizations of clouds. To explore these opportunities, we replace the warm rain formation process in a General Circulation Model (GCM) with a detailed treatment from a bin microphysical model that causes a 400\% slowdown in the GCM. We analyze the changes in climate that result from the use of the bin microphysical calculation and find improvements in the rain onset and frequency of light rain compared to detailed models and observations. We also find a resulting change in the cloud feedback response of the model to warming, which will significantly impact the climate sensitivity. We then emulate this process with an emulator consisting of multiple neural networks that predict whether specific tendencies will be nonzero and the magnitude of the nonzero tendencies. We describe the risks of over-fitting, extrapolation, and linearization of a non-linear problem by using perfect model experiments with and without the emulator and show we can recover the solutions with the emulators in almost all respects, and recover nearly all the speed to get simulations that perform as the detailed model, but with the computational cost of the control simulation.

Aerosols interact with radiation and clouds. Substantial progress made over the past 40 years in observing, understanding, and modeling these processes helped quantify the imbalance in the Earth’s radiation budget caused by anthropogenic aerosols, called aerosol radiative forcing, but uncertainties remain large. This poster presents the outcome of an international workshop and subsequent review paper, which quantify the likely range of aerosol radiative forcing over the industrial era based on multiple lines of evidence, including modelling approaches, theoretical considerations, and observations. Improved understanding of aerosol absorption and the causes of trends in surface radiative fluxes narrow the range of the forcing from aerosol-radiation interactions compared to the latest assessment by the Intergovernmental Panel on Climate Change (IPCC). A robust theoretical foundation and convincing evidence constrain the forcing caused by aerosol-driven increases in liquid cloud droplet number concentration. However, the influence of anthropogenic aerosols on cloud liquid water content and cloud fraction and on mixed-phase and ice clouds remains poorly constrained. Observed changes in surface temperature and radiative fluxes provide additional constraints. These multiple lines of evidence lead to total aerosol radiative forcing ranges that are of similar width to the last IPCC assessment but more clearly based on physical arguments.