Enhancing tropical cyclone intensity forecasting with explainable deep learning integrating satellite observations and numerical model outputs

Juhyun Lee; Jungho Im; Yeji Shin

doi:10.1016/j.isci.2024.109905

Enhancing tropical cyclone intensity forecasting with explainable deep learning integrating satellite observations and numerical model outputs

iScience. 2024 May 3;27(6):109905. doi: 10.1016/j.isci.2024.109905. eCollection 2024 Jun 21.

Authors

Juhyun Lee¹, Jungho Im^{1

2

3}, Yeji Shin^{1

4}

Affiliations

¹ Department of Civil, Urban, Earth, and Environmental Engineering, Ulsan National Institute of Science and Technology, Ulsan, Republic of Korea.
² Graduate School of Carbon Neutrality, Ulsan National Institute of Science and Technology, Ulsan, Republic of Korea.
³ Artificial Intelligence Graduate School, Ulsan National Institute of Science and Technology, Ulsan, Republic of Korea.
⁴ Market Intelligence Team, Purchasing Strategy Unit, CJ CheilJedang Corporation, Seoul, South Korea.

Abstract

Tropical cyclone (TC) intensity change forecasting remains challenging due to the lack of understanding of the interactions between TC changes and environmental parameters, and the high uncertainties resulting from climate change. This study proposed hybrid convolutional neural networks (hybrid-CNN), which effectively combined satellite-based spatial characteristics and numerical prediction model outputs, to forecast TC intensity with lead times of 24, 48, and 72 h. The models were validated against best track data by TC category and phase and compared with the Korea Meteorological Administrator (KMA)-based TC forecasts. The hybrid-CNN-based forecasts outperformed KMA-based forecasts, exhibiting up to 22%, 110%, and 7% improvement in skill scores for the 24-, 48-, and 72-h forecasts, respectively. For rapid intensification cases, the models exhibited improvements of 62%, 87%, and 50% over KMA-based forecasts for the three lead times. Moreover, explainable deep learning demonstrated hybrid-CNN's potential in predicting TC intensity and contributing to the TC forecasting field.

Keywords: Applied computing in earth sciences; Atmospheric science; Earth sciences; Machine learning; Meteorology.