A Novel Data-Driven Tropical Cyclone Track Prediction Model Based on CNN and GRU With Multi-Dimensional Feature Selection

• Published in: IEEE access Vol. 8; pp. 97114 - 97128
• Main Authors: Lian, Jie, Dong, Pingping, Zhang, Yuping, Pan, Jianguo, Liu, Kehao
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Cyclones; Datasets; Deep learning; Feature selection; Forecasting techniques; Mathematical models; Meteorological data; Model accuracy; Numerical weather forecasting; Prediction models; Teaching methods; Tropical cyclones tracks prediction; typhoon; Weather forecasting
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2020.2992083

Strong tropical cyclones have made a drastic effect on human life and natural environment. As large amounts of meteorological data and monitoring data continue to accumulate, traditional methods for predicting tropical cyclone tracks face numerous challenges regarding their prediction efficiency and accuracy. Deep learning methods recently have been proven to be able to learn both spatial and temporal features from a large amount of dataset and be extremely efficient and accurate for forecasting data in complex structures. In this paper, we propose a novel data-driven deep learning model to predict tropical cyclone tracks using the spatial locations and multiple meteorological factors. This model comprises a multi-dimensional feature selection layer, a CNN layer and a GRU layer. The proposed model was trained using a dataset of real-world tropical cyclones from the years 1945 to 2017. Through the comparison experiments, the results verify that the proposed model outperforms the traditional forecasting methods, including a climatologically aware forecasting technique, the Sanders Barotropic technique and a numerical weather prediction (NWP) model. In addition, the proposed model has better accuracy than some deep learning methods, including RNN, GRU, CNN, AE-RNN, CNN-RNN, and CNN-GRU without the proposed feature selection layer.