A neural network to retrieve cloud cover from all-sky cameras: A case of study over Antarctica

• Published in: Quarterly Journal of the Royal Meteorological Society
• Main Authors: González-Fernández, Daniel, Román, Roberto, Antuña-Sánchez, Juan Carlos, Cachorro, Victoria E., Copes, Gustavo, Herrero-Anta, Sara, Herrero del Barrio, Celia, Barreto Velasco, África, González, Ramiro, Ramos López, Ramón, Toledano, Carlos, Calle, Abel, Frutos Baraja, Ángel Máximo de
• Format: Article in Journal/Newspaper
• Language: English
• Published: Wiley 2024
• Subjects: AI; All-sky camera; Antarctic; Convolutional neural network; Cloud cover; Image identification; Antarc*; Antarctica
• Online Access: https://hdl.handle.net/20.500.11765/16119

We present a new model based on a convolutional neural network (CNN) to predict daytime cloud cover (CC) from sky images captured by all-sky cameras, which is called CNN-CC. A total of 49,016 daytime sky images, recorded at different Spanish locations (Valladolid, La Palma, and Izaña) from two different all-sky camera types, are manually classified into different CC (oktas) values by trained researchers. Subsequently, the images are randomly split into a training set and a test set to validate the model. The CC values predicted by the CNN-CC model are compared with the observations made by trained people on the test set, which serve as reference. The research has been supported by the Ministeriode Ciencia e Innovación (MICINN), with Grant no.PID2021-127588OB-I00, and the Junta of Castilla y León (JCyL) with Grant no. VA227P20. This work ispart of the project TED2021-131211B-I00 funded byMCIN/AEI/10.13039/501100011033 and the EuropeanUnion, “NextGenerationEU”/PRTR.