Extended-Range Forecast of Regional Persistent Extreme Cold Events Based on Deep Learning

• Published in: Atmosphere Vol. 14; no. 10; p. 1572
• Main Authors: Wu, Weichen, Wang, Yaqiang, Wei, Fengying, Liu, Boqi, You, Xiaoxiong
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.10.2023
• Subjects: Artificial neural networks; Cold weather; Decomposition; Deep learning; Disasters; Empirical analysis; Extended forecasting; Extreme cold; Extreme low temperatures; Extreme weather; Low temperature; low-frequency oscillation; Neural networks; Orthogonal functions; Oscillations; Precipitation; regional persistent extreme cold events; Temperature; Temperature effects; Wavelet transforms; Weather forecasting; China; Yangtze River
• ISSN: 2073-4433; 2073-4433
• DOI: 10.3390/atmos14101572

Regional persistent extreme cold events are meteorological disasters that cause serious harm to people’s lives and production; however, they are very difficult to predict. Low-temperature weather systems and their effects have a significant low-frequency oscillation period (10–20 d and 30–60 d). This paper uses deep learning to analyze the extended-range time scale and predict regional persistent extreme cold events. The dominant low-frequency oscillation components of cold events are obtained via wavelet transform and Butterworth filtering. The low-frequency oscillation component is decomposed via empirical orthogonal function decomposition to extract the main spatial mode and time coefficient. A convolutional neural network is used to establish the correlation between large-scale circulations and the time coefficient of the low-frequency oscillation component of the lowest temperature. The proposed deep learning model exhibits good prediction accuracy for regional persistent extreme cold events with low-frequency oscillations.