China's National Meteorological Center has deployed a machine learning ensemble model developed by the Shenzhen Institutes of Advanced Technology for typhoon rapid intensification forecasts.
The model, named Machine Learning Ensemble Model for Tropical Cyclone Rapid Intensification Forecast, was developed by a team led by Li Qinglan. It integrates four machine-learning algorithms and issues a rapid intensification forecast when more than half of the sub-models predict it.
The model introduces two quantitative indices, the sea-land ratio and the symmetric ratio, to reveal physical links between inner-core symmetry and rapid intensification. Tests showed it achieved a higher probability of detection and lower false alarm rate than the U.S. National Hurricane Center system when simulating tropical cyclones from 2016 to 2020.
National Meteorological Center senior engineer Lyu Xinyan said the 24-hour rapid intensification forecast technology now provides an important reference for China's typhoon intensity forecasting. Typhoons such as Rammasun in 2014, Hato in 2017 and Yagi in 2024 all underwent rapid intensification before landfall.
