Chinese scientists develop new AI method to forecast cyclone intensity

Chinese scientists have developed a new artificial intelligence (AI) method to forecast dramatic increases in the intensification of tropical cyclones over a short period, state media reported on Tuesday.

Developed by researchers from the Institute of Oceanology at the Chinese Academy of Sciences, the latest method sheds new light on improving global disaster preparedness, according to Beijing-based Xinhua News.

The rapid intensification of a tropical cyclone has long remained one of the most challenging weather phenomena to forecast due to its unpredictable and destructive nature.

Addressing this issue, the new AI model combines satellite, atmospheric, and oceanic data.

The new method achieved an accuracy of 92.3% and reduced false alarms to 8.9% when tested on data from the tropical cyclone periods in the Northwest Pacific between 2020 and 2021.

It improved accuracy by around 12% compared to existing techniques and boasted a threefold reduction in false alarms, representing a significant advancement in forecasting.

"This study addresses the challenges of low accuracy and high false alarm rates in rapid intensification forecasting," Li Xiaofeng, the study's corresponding author, was quoted as saying by Xinhua News.