Classification and Prediction of Typhoon Levels by Satellite Cloud Pictures through GC-LSTM Deep Learning Model.

Jianyin Zhou,Sixun Huang,Jie Xiang

doi:10.3390/s20185132

Jianyin Zhou, Sixun Huang + Show 1 more

Open Access

https://doi.org/10.3390/s20185132

Copy DOI

Abstract

Typhoons are some of the most serious natural disasters, and the key to disaster prevention and mitigation is typhoon level classification. How to better use data of satellite cloud pictures to achieve accurate classification of typhoon levels has become one of classification the hot issues in current studies. A new framework of deep learning neural network, Graph Convolutional–Long Short-Term Memory Network (GC–LSTM), is proposed, which is based on the data of satellite cloud pictures of the Himawari-8 satellite in 2010–2019. The Graph Convolutional Network (GCN) is used to process the irregular spatial structure of satellite cloud pictures effectively, and the Long Short-Term Memory (LSTM) network is utilized to learn the characteristics of satellite cloud pictures over time. Moreover, to verify the effectiveness and accuracy of the model, the prediction effect and model stability are compared with other models. The results show that: the algorithm performance of this model is better than other prediction models; the prediction accuracy rate of typhoon level classification reaches 92.35%, and the prediction accuracy of typhoons and super typhoons reaches 95.12%. The model can accurately identify typhoon eye and spiral cloud belt, and the prediction results are always kept in the minimum range compared with the actual results, which proves that the GC–LSTM model has stronger stability. The model can accurately identify the levels of different typhoons according to the satellite cloud pictures. In summary, the results can provide a theoretical basis for the related research of typhoon level classification.

Highlights

Typhoons have the widest damage range among all the natural disasters, which is the most invading disaster of coastal areas
Through the analysis of the original typhoon prediction model, problems such as poor prediction accuracy, low recognition rate, and complex feature extraction are found in the traditional typhoon prediction models
Based on the deep learning neural network framework, the advantages of Graph Convolutional Network (GCN) and Long Short-Term Memory (LSTM) are utilized to build the typhoon Graph Convolutional–Long Short-Term Memory Network (GC–LSTM) model to effectively process the problems in the construction of satellite cloud picture models

Summary

Introduction

Typhoons have the widest damage range among all the natural disasters, which is the most invading disaster of coastal areas. Storms caused by typhoons have caused huge losses to coastal ships and the marine industry [1]. The prediction of typhoons has always been a scientific issue in this field [3]. With the improvement of the satellite remote sensing technology, meteorological satellite cloud pictures can more accurately and stably monitor the weather changes in real-time in all weathers, becoming the main means of observing and predicting typhoons [5]. Research on using satellite cloud pictures has achieved a series of results in the process of typhoon generation and development [6,7]

Methods

Results

Conclusion