Tracks of typhoons are predicted using a generative adversarial network (GAN) with satellite images as inputs. Time series of satellite images of typhoons which occurred in the Korea Peninsula in the past are used to train the neural network. The trained GAN is employed to produce a 6-hour-advance track of a typhoon for which the GAN was not trained. The predicted track image of a typhoon favorably identifies the future location of the typhoon center as well as the deformed cloud structures. Errors between predicted and real typhoon centers are measured quantitatively in kilometers. An averaged error of 95.6 km is achieved for tested 10 typhoons. Predicting sudden changes of the track in westward or northward directions is identified as a challenging task, while the prediction is significantly improved, when velocity fields are employed along with satellite images.

No 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

Tracks of typhoons are predicted using satellite images as input for a Generative Adversarial Network (GAN). The satellite images have time gaps of 6 hours and are marked with a red square at the location of the typhoon center. The GAN uses images from the past to generate an image one time step ahead. The generated image shows the future location of the typhoon center, as well as the future cloud structures. The errors between predicted and real typhoon centers are measured quantitatively in kilometers. 42.4% of all typhoon center predictions have absolute errors of less than 80 km, 32.1% lie within a range of 80 -120 km and the remaining 25.5% have accuracies above 120 km. The relative error sets the above mentioned absolute error in relation to the distance that has been traveled by a typhoon over the past 6 hours. High relative errors are found in three types of situations, when a typhoon moves on the open sea far away from land, when a typhoon changes its course suddenly and when a typhoon is about to hit the mainland. The cloud structure prediction is evaluated qualitatively. It is shown that the GAN is able to predict trends in cloud motion. In order to improve both, the typhoon center and cloud motion prediction, the present study suggests to add information about the sea surface temperature, surface pressure and velocity fields to the input data.

Using traditional computational fluid dynamics and aeroacoustics methods, the accurate simulation of aeroacoustic sources requires high compute resources to resolve all necessary physical phenomena. In contrast, once trained, artificial neural networks such as deep encoder-decoder convolutional networks allow to predict aeroacoustics at lower cost and, depending on the quality of the employed network, also at high accuracy. The architecture for such a neural network is developed to predict the sound pressure level in a 2D square domain. It is trained by numerical results from up to 20,000 GPU-based lattice-Boltzmann simulations that include randomly distributed rectangular and circular objects, and monopole sources. Types of boundary conditions, the monopole locations, and cell distances for objects and monopoles serve as input to the network. Parameters are studied to tune the predictions and to increase their accuracy. The complexity of the setup is successively increased along three cases and the impact of the number of feature maps, the type of loss function, and the number of training data on the prediction accuracy is investigated. An optimal choice of the parameters leads to network-predicted results that are in good agreement with the simulated findings. This is corroborated by negligible differences of the sound pressure level between the simulated and the network-predicted results along characteristic lines and by small mean errors.