Aerosol properties retrieval in partially cloud conditions using HDR All-Sky imagery

In the present study we focus our attention on determine aerosol properties from HDR All-Sky calibrated imagery. Even if this methodology is designed to be used regardless of the sky conditions, we especially explore the sensitivity to partially cloud scenarios, which is the main novelty of this work. Our methodology is based on using a small sector of the image that contains the principal plane of the Sun. The RGB principal plane radiances are associated to the Aerosol Optical Depth (AOD) and Ångström exponent (AE) AERONET observations through a Gaussian Process Regression (GPR) machine learning (ML) model. The cloudy points in our working sector are previously identified and then the correspondent free-sky radiances simulated with the aid of the Perez model. Therefore, the entire principal plane signal as if no clouds are present is synthetized and used as the ML model input. As the outputs of the ML model are the AOD and AE, the ML find a hidden relationship between these quantities and provide a useful prediction method. Finally, 2 years dataset has been used to test the method considering different atmospheric conditions related to the presence of clouds and aerosols, according to their amount and type. Since we used a GPR as ML model, we took advantage of the statistically propagated uncertainty the model relates to the outputs to give a proxy of an error of measurement to the predicted quantities. We also used these uncertainties to develop a method that evaluate the quality of predictions themselves. This quality assurance method may be fine-tuned according to the desired accuracy based on the application for which it is intended. Our AOD and AE predictions show an excellent overall agreement with AERONET measurements that substantially improves when our quality assurance method is applied. In that case, we obtain a high degree of correlation (R² >0.97) and an overall MAE lower than the nominal uncertainty of AERONET measurements (0.006 and 0.05 for AOD and AE, respectively). Moreover, more than 83% and 77% of the predictions fall within the nominal uncertainty associated with AERONET measurements for AOD and AE, respectively. A comprehensive sensitivity analysis of the factors affecting the performance of the proposed methodology confirms that our method is stable and not very sensitive to external and methodological factors, especially when we apply quality assurance criteria. All this supports that our methodology is a reliable alternative to retrieve the optical properties of aerosols independently of the cloud conditions. Our results may contribute to the operational use of all-sky cameras, which may be an interesting complement regarding the study of aerosol-cloud interactions in partially cloud scenarios.