Temperature forecasting by deep learning methods

• Published in: Geoscientific Model Development Vol. 15; no. 23; pp. 8931 - 8956
• Main Authors: Gong, Bing, Langguth, Michael, Ji, Yan, Mozaffari, Amirpasha, Stadtler, Scarlet, Mache, Karim, Schultz, Martin G
• Format: Journal Article
• Language: English
• Published: Katlenburg-Lindau Copernicus GmbH 13.12.2022; Copernicus Publications
• Subjects: Analysis; Artificial neural networks; Atmospheric models; Cloud cover; Computer vision; Correlation coefficient; Correlation coefficients; Datasets; Deep learning; Differential equations; Generative adversarial networks; Machine learning; Machine vision; Measurement techniques; Methods; Modelling; Neural networks; Nowcasting; Numerical methods; Numerical prediction; Numerical weather forecasting; Partial differential equations; Prediction models; Recurrent neural networks; Sensitivity analysis; Spatial variability; Spatial variations; Stochasticity; Temperature; Temperature effects; Temperature forecasting; Training; Weather; Weather forecasting
• ISSN: 1991-9603; 1991-959X; 1991-962X; 1991-9603; 1991-962X
• DOI: 10.5194/gmd-15-8931-2022

Numerical weather prediction (NWP) models solve a system of partial differential equations based on physical laws to forecast the future state of the atmosphere. These models are deployed operationally, but they are computationally very expensive. Recently, the potential of deep neural networks to generate bespoke weather forecasts has been explored in a couple of scientific studies inspired by the success of video frame prediction models in computer vision. In this study, a simple recurrent neural network with convolutional filters, called ConvLSTM, and an advanced generative network, the Stochastic Adversarial Video Prediction (SAVP) model, are applied to create hourly forecasts of the 2 m temperature for the next 12 h over Europe. We make use of 13 years of data from the ERA5 reanalysis, of which 11 years are utilized for training and 1 year each is used for validating and testing. We choose the 2 m temperature, total cloud cover, and the 850 hPa temperature as predictors and show that both models attain predictive skill by outperforming persistence forecasts. SAVP is superior to ConvLSTM in terms of several evaluation metrics, confirming previous results from computer vision that larger, more complex networks are better suited to learn complex features and to generate better predictions. The 12 h forecasts of SAVP attain a mean squared error (MSE) of about 2.3 K2, an anomaly correlation coefficient (ACC) larger than 0.85, a structural similarity index (SSIM) of around 0.72, and a gradient ratio (rG) of about 0.82. The ConvLSTM yields a higher MSE (3.6 K2), a smaller ACC (0.80) and SSIM (0.65), and a slightly larger rG (0.84). The superior performance of SAVP in terms of MSE, ACC, and SSIM can be largely attributed to the generator. A sensitivity study shows that a larger weight of the generative adversarial network (GAN) component in the SAVP loss leads to even better preservation of spatial variability at the cost of a somewhat increased MSE (2.5 K2). Including the 850 hPa temperature as an additional predictor enhances the forecast quality, and the model also benefits from a larger spatial domain. By contrast, adding the total cloud cover as predictor or reducing the amount of training data to 8 years has only small effects. Although the temperature forecasts obtained in this way are still less powerful than contemporary NWP models, this study demonstrates that sophisticated deep neural networks may achieve considerable forecast quality beyond the nowcasting range in a purely data-driven way.