参考消息
Chinese scientists develop new AI model for cyclone forecast
Chinese scientists have developed a new artificial intelligence (AI) method to forecast the rapid intensification of a tropical cyclone, shedding new light on improving global disaster preparedness.
Recently, researchers from the
Institute of Oceanology at the Chinese Academy of Sciences published this study in the journal, Proceedings of the National Academy of Sciences.
The rapid intensification of a tropical cyclone, which refers to a dramatic increase in the intensity of a tropical storm over a short period, remains one of the most challenging weather phenomena to forecast because of its unpredictable and destructive nature.
According to the study, traditional forecasting methods, such as numerical weather prediction and statistical approaches, often fail to consider the complex environmental and structural factors driving rapid intensification. While AI has been explored to improve rapid intensification prediction, most AI techniques have struggled with high false alarm rates and limited reliability.
To address this issue, the researchers have developed a new AI model that combines satellite, atmospheric and oceanic data. When tested on data from the tropical cyclone periods in the Northwest Pacific between 2020 and 2021, the new method achieved an accuracy of 92.3 percent and reduced false alarms to 8.9 percent.
The new method improved accuracy by nearly 12 percent compared to existing techniques and boasted a 3-times reduction in false alarms, representing a significant advancement in forecasting, said the study.
"This study addresses the challenges of low accuracy and high false alarm rates in rapid intensification forecasting," said Li Xiaofeng, the study's corresponding author.
"Our method enhances understanding of these extreme events and supports better defenses against their devastating impacts," Li added.
