Cloud Cover Nowcasting with Deep Learning

TL;DR

This paper explores deep learning techniques, specifically convolutional neural networks, for short-term cloud cover nowcasting using satellite imagery, outperforming traditional physical models and persistence methods.

Contribution

It introduces deep learning architectures tailored for cloud cover nowcasting, demonstrating superior performance over existing physical and persistence models.

Findings

Deep learning models outperform persistence methods.

U-Net surpasses traditional physical models like AROME.

Significant improvements in meteorological and machine learning metrics.

Abstract

Nowcasting is a field of meteorology which aims at forecasting weather on a short term of up to a few hours. In the meteorology landscape, this field is rather specific as it requires particular techniques, such as data extrapolation, where conventional meteorology is generally based on physical modeling. In this paper, we focus on cloud cover nowcasting, which has various application areas such as satellite shots optimisation and photovoltaic energy production forecast. Following recent deep learning successes on multiple imagery tasks, we applied deep convolutionnal neural networks on Meteosat satellite images for cloud cover nowcasting. We present the results of several architectures specialized in image segmentation and time series prediction. We selected the best models according to machine learning metrics as well as meteorological metrics. All selected architectures showed significant improvements over persistence and the well-known U-Net surpasses AROME physical model.