Comment on amt-2023-26

Abstract

<strong class="journal-contentHeaderColor">Abstract.</strong> This work introduces the novel short-term nowcasting model MACIN, which predicts direct normal irradiance (DNI) for solar energy applications based on hemispheric sky images from two all-sky imagers (ASI). With a synthetic setup based on simulated cloud scenes, the model and its components were validated in depth. We trained a convolutional neural network to identify clouds in ASI images and derive their height and motion using sparse matching. In contrast to other studies, all derived cloud information from both ASIs and multiple timesteps are combined into an optimal model state using techniques from data assimilation. This state is advected to predict future cloud positions and compute DNI for lead times up to 20 minutes. For the cloudmasks derived from the ASI images we found a pixel accuracy of 94.66 % compared to the references available in the synthetic setup. The relative error of derived cloud base heights is 4 % and cloud motion error is in the range of 0.1 ms^&minus;1. For the DNI nowcasts, we found an improvement over persistence for lead times larger than one minute. Using the synthetic setup, we computed a DNI reference for a point and also an area of 500m &times; 500 m. Errors for area nowcasts as required, e.g., for photovoltaics plants, are smaller compared to errors for point nowcasts. Overall, the novel ASI nowcasting model and its components proved to work within the synthetic setup.