Lee Juhyun, Im Jungho, Shin Yeji
Department of Civil, Urban, Earth, and Environmental Engineering, Ulsan National Institute of Science and Technology, Ulsan, Republic of Korea.
Graduate School of Carbon Neutrality, Ulsan National Institute of Science and Technology, Ulsan, Republic of Korea.
iScience. 2024 May 3;27(6):109905. doi: 10.1016/j.isci.2024.109905. eCollection 2024 Jun 21.
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.
由于对热带气旋（TC）变化与环境参数之间的相互作用缺乏了解，以及气候变化带来的高度不确定性，热带气旋强度变化预测仍然具有挑战性。本研究提出了混合卷积神经网络（hybrid-CNN），它有效地结合了基于卫星的空间特征和数值预测模型输出，以预测提前24、48和72小时的热带气旋强度。通过TC类别和阶段，根据最佳路径数据对模型进行了验证，并与韩国气象厅（KMA）的TC预报进行了比较。基于hybrid-CNN的预报优于基于KMA的预报，在24小时、48小时和72小时预报的技能分数上分别提高了22%、110%和7%。对于快速增强的情况，在三个提前时间上，模型相对于基于KMA的预报分别有62%、87%和50%的改进。此外，可解释的深度学习证明了hybrid-CNN在预测TC强度以及对TC预报领域做出贡献方面的潜力。
