Prediction of Typhoon Track and Intensity Using a Generative Adversarial Network With Observational and Meteorological Data

Abstract

To save lives and reduce damage from the destructive impacts of a typhoon, an accurate and fast forecast method is highly demanded. Particularly, predictions for short lead times, known as nowcasting, rely on fast forecasts allowing immediate emergency plannings in the affected areas. In this paper, we propose a generative adversarial network that operates on a single graphics processing unit, to predict both the track and intensity of typhoons for short lead times within fractions of a second. To investigate the effects of meteorological variables on typhoon forecasts, we conducted a parameter study for 6-h track predictions. The results of the study indicate that learning velocity, temperature, pressure, and humidity along with satellite images have positive effects on prediction accuracy. To address the limited access to observational data and facilitate predictions for 12-h intervals, we replaced satellite images with reanalysis data of the total cloud cover and vorticity fields. This replacement led to an increase in data from 76 to 757 typhoons, and it reduced the error of the 6-h track forecasts by 23.5%. The best combination of the parameter study yields track predictions in intervals of 6 and 12 h with the corresponding averaged absolute errors of 44.5 and 68.7 km. Typhoon intensities are predicted by extracting information from generated velocity fields with averaged hit rates of 87.3% and 83.2% for 6-and 12-h interval forecasts, respectively. For typhoons after 1994, tracks and intensities for 12-h intervals are compared to forecasts from the Joint Typhoon Warning Center and Regional Specialized Meteorological Center Tokyo.INDEX TERMS Typhoon track prediction, typhoon intensity prediction, deep learning, nowcasting I. INTRODUCTION

Could artificial intelligence win the next Weather Photographer of the Year competition?

“…GANs and diffusion models are not limited to producing images and have many potential applications in other fields, including meteorology and climate science. Such applications include downscaling climate model output (Cheng et al ., 2021), ensemble weather prediction (Bihlo, 2021), nowcasting (Rüttgers et al ., 2022) and even storm surge models (Lütjens et al ., 2020). Generative models can also now produce convincing text output.…”

Object Tracking Based on Satellite Videos: A Literature Review

“…Similarly, Ref. [111] designed a GAN based approach to predict both the track and intensity of typhoons for short lead times within fractions of a second. The experimental results indicated that learning velocity, temperature, pressure, and humidity along with satellite images have positive effects on trajectory prediction accuracy.…”

“…In addition, Figure 4 shows a comparison of algorithm structure between two categories. [110] 2021 GAN with deep multi-scale frame prediction method [111] 2022 GAN to predict both the track and intensity of typhoons RNN-based [112] 2017 A convolutional sequence-to-sequence autoencoder [113] 2018 MNNs for typhoon tracking [114] 2018 A CLSTM based model [115] 2021 A CLSTM layer with FCLs [116] 2022 A CLSTM with 3D CNN based on multimodal data [117] 2022 An echo state network-based tracking Fire Traditional [118] 2017 Identify possible fire hotspots from two bands of AHI [119] 2018 A threshold algorithm with visual interpretation [120] 2019 A multi-temporal method of temperature estimation [121] 2020 Temperature dynamics by data assimilation [122] 2022 Wildfire tracking via visible and infrared image series DL-based [123] 2019 3D CNN to capture spatial and spectral patterns [124] 2019 Inception-v3 model with transfer learning [125] 2021 Near-real-time fire smoking prediction [126] 2022 Combine the residual convolution and separable convolution to detect fire [127] 2022 Multiple Kernel learning for various size fire detections…”

How Regional Wind Characteristics Affect Cnn-Based Wind Predictions: Insights from Spatiotemporal Correlation Analysis

“…Recently, neural networks have shown promising results in addressing atmospheric flow problems, such as typhoon prediction [5,6]. Neural-networkbased wind predictions have also been investigated by various researchers [7,8,9].…”