Volume XLII-3/W9
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-3/W9, 89–94, 2019
https://doi.org/10.5194/isprs-archives-XLII-3-W9-89-2019
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-3/W9, 89–94, 2019
https://doi.org/10.5194/isprs-archives-XLII-3-W9-89-2019
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.

  25 Oct 2019

25 Oct 2019

AENN: A GENERATIVE ADVERSARIAL NEURAL NETWORK FOR WEATHER RADAR ECHO EXTRAPOLATION

J. R. Jing, Q. Li, X. Y. Ding, N. L. Sun, R. Tang, and Y. L. Cai J. R. Jing et al.
  • College of Meteorology and Oceanography, National University of Defense Technology, 60 Shuanglong Road, Nanjing, China

Keywords: Weather Radar, Radar Echo Extrapolation, Deep Learning, Recurrent Neural Network, Generative Adversarial Network, Adversarial Training, Short-term Weather Forecasting

Abstract. Weather radar echo is one of the fundamental data for meteorological workers to weather systems identification and classification. Through the technique of weather radar echo extrapolation, the future short-term weather conditions can be predicted and severe convection storms can be warned. However, traditional extrapolation methods cannot offer accurate enough extrapolation results since their modeling capacity is limited, the recent deep learning based methods make some progress but still remains a problem of blurry prediction when making deeper extrapolation, which may due to they choose the mean square error as their loss function and that will lead to losing echo details. To address this problem and make a more realistic and accurate extrapolation, we propose a deep learning model called Adversarial Extrapolation Neural Network (AENN), which is a Generative Adversarial Network (GAN) structure and consist of a conditional generator and two discriminators, echo-frame discriminator and echo-sequence discriminator. The generator and discriminators are trained alternately in an adversarial way to make the final extrapolation results be realistic and accurate. To evaluate the model, we conduct experiments on extrapolating 0.5h, 1h, and 1.5h imminent future echoes, the results show that our proposed AENN can achieve the expected effect and outperforms other models significantly, which has a powerful potential application value for short-term weather forecasting.