The application of Artificial Intelligence (AI) in scientific research is transforming the traditional scientific research paradigm, and AI weather models have already been deployed in operational applications. Despite significant progress in typhoon track forecasting, AI weather models still exhibit limitations in capturing complex physical processes within typhoons and predicting changes in typhoon intensity, especially the Rapid Intensification (RI) of typhoons and the evolution of typhoon internal structures. This is mainly because AI weather models lack sufficient resolution support for determining typhoon intensity and fine structure. The use of AI weather model-driven regional model technology can overcome this bottleneck, enabling more accurate forecast of typhoon intensity and structural evolution. To this end, the Chinese Academy of Meteorological Sciences and the National Meteorological Centre have jointly developed the AI-driven Typhoon Rapid Analysis and Forecasting System (AI-TRANS) based on the technical route mentioned above. The forecast results of AI-TRANS are compared with forecasts of six other operational models using typhoon forecast data from 2024. The results show that the performance of AI-TRANS is basically the same as that of the existing operational models in typhoon track forecasting. The prediction of typhoon intensity and structure shows obvious advantages. The system integrates the advantages of the AI weather model and numerical models, and significantly improves the accuracy of typhoon landfall forecast by improving the track forecast stability of the AI weather model. At the same time, the AI weather model-driven regional model technology has effectively improved the forecasting effect of key indicators such as typhoon RI, lifetime maximum intensity and fine structure. Taking the severe typhoons Gaemi and Yagi in 2024 as examples, the AI-TRANS system successfully predicted the track rotation, RI process and concentric eyewalls structure of Gaemi in the east side of Taiwan Island, and accurately captured the RI, concentric eyewalls formation and eye wall replacement process after Typhoon Yagi entered the South China Sea. This is the first time that a model can successfully predict the concentric eyewalls structure and the eyewall replacement process in real-time typhoon forecasting, which demonstrates the critical supporting role of the AI-TRANS system in improving the accuracy of typhoon intensity forecast and enhancing the capability of disaster mitigation.

Using the interim reanalysis data of European Centre for Medium-Range Weather Forecasts (ERA-Interim), the tropical cyclone best track data from Shanghai Typhoon Institute of China Meteorological Administration, the NOAA daily optimum sea surface temperature (OISST), Himawari-8 satellite data, and observations collected at automatic weather stations (AWS) in China, the difficulties of the intensity forecasting of typhoon Mekkhala in the southern Taiwan Strait are analyzed. The environmental factors and the asymmetric distribution of the convective burst during the rapid intensification of Mekkhala in the southern Taiwan Strait are further studied. Results are as follows: (1) The rapid intensification of typhoon Mekkhala in the southern Taiwan Strait under the strong 200—850 hPa vertical wind shear and its landing in Fujian province at peak intensity are very rare, which resulted in a short warning time and great difficulties in intensity prediction. (2) The favorable ocean heat condition and large-scale environmental conditions such as the abnormal warm sea surface temperature in the northern South China Sea, the strong upper-level outflow caused by the easterly jet to the south of the South Asian High, and the abundant and stable southwesterly monsoon water vapor transport all play an important role in the rapid intensification of typhoon Mekkhala in the southern Taiwan Strait. (3) The traditional environmental vertical wind shear (200—850 hPa) is very strong, but the vertical distribution of the environmental wind shows that the environmental vertical wind shear is mainly concentrated in the middle and upper levels, while the shear in the middle and lower levels is relatively weak. However, the vertical wind shear in upper and middle levels has relatively little inhibition on the typhoon intensification. (4) During the rapid intensification of typhoon Mekkhala, the distribution of deep convection presented obvious asymmetric distribution characteristics. The convection was mainly concentrated in the down shear side and the left side of the environmental vertical wind shear (200—850 hPa), accompanied by cyclonic propagation of convective burst from the down shear side to the up shear side, and the tilt of typhoon significantly reduced. Further studies on the impact mechanism of environmental vertical wind shear at different levels on typhoon intensity change and characteristics of asymmetric convective bust during typhoon intensification under strong environmental vertical wind shear will be conducted in the future based on more cases.

Compared with the forecast of typhoon track, numerical models lack the ability to forecast typhoon intensity. To further reduce errors in typhoon intensity forecast and improve the mitigation ability of typhoon, an equation of the typhoon intensity in the Northwest Pacific that consists of typhoon initial intensity, initial field error term, change of ensemble mean term and dispersion term has been established using the ECMWF ensemble forecast data from 2018 to 2019. Partial correlation analysis and collinearity test are applied. The 2020 data are used to compare and test the forecast effects. Conclusions are as follows. The prediction error of typhoon intensity calculated by the prediction equation is always less than that of various statistics in the ensemble prediction in each prediction time. Among them, the RMSR of 24 hour prediction is lower than the maximum, the ensemble mean prediction and the deterministic model forecast by 34.36%, 14.58% and 20.38%, respectively. Also, the RMSE of 72 hour prediction is lower than the maximum, the ensemble mean prediction and the deterministic model forecast by 25.68%, 12.91% and 11.13%, respectively. In the comparative case analysis of typhoon, the prediction effect of the revised forecast is also better than the ECMWF ensemble forecast and deterministic model forecast, which is the closest to the reality, and can perform better in the forecast of rapidly enhancing typhoon. The prediction equation of typhoon intensity based on ensemble forecast can quantitatively extract key information from ensemble forecast and generate more accurate prediction, which provides a reference for typhoon forecast in the Northwest Pacific.

After landfall, tropical cyclone (TC) remnants may maintain or even rejuvenate and incur catastrophic disasters. What leads to the revival of TC remnants over land remains elusive. In this study, the revival mechanism of Typhoon Doksuri (2023) remnants is extensively explored. Doksuri brought severe damage to the Chinese mainland after its landfall. The remnants vortex of Doksuri sustained an inland trajectory for 3 days and underwent a total maintenance of 60 h, with a revival of 18 h. Based on multi-source observations and ERA5 reanalysis data, by calculation of moist potential vorticity and analysis of slantwise vorticity development (SVD), this study unveils that while maintaining a significant warm-core structure over the course of maintenance and revival, the Doksuri remnants transported sufficient moisture in the mid–lower troposphere, which intensified the north–south temperature and humidity gradients, causing tilting of the isentropic surfaces remarkably. According to the SVD theory, the tilting gave rise to vorticity development and forced upward air motion on the northern side of the remnant vortex. Moreover, numerical sensitivity experiments based on the WRF model reveal that the topography of Taihang Mountains and the diabatic heating associated with surface and convective latent heat fluxes also played important roles in the revival of the Doksuri remnants. The dynamic and thermodynamic mechanisms derived by this study will help improve understanding and prediction of the disasters induced by TC remnants.