Search

Attributing sources of tropical cyclogenesis (TCG) bias to large‐scale circulation in global circulation models is challenging. Here, we propose the use of empirical orthogonal functions as an approach to understand model bias of TCG. Two leading modes of large‐scale wind circulations in the West Pacific can explain the TCG frequency and location in both climate reanalysis and the MetUM model. In the reanalysis, the two modes distinguish the summer monsoon trough position and the strength of the north Pacific subtropical high. However, in the model, the wind circulations are biased toward the positive phase of simulated modes thus overestimating TCG in the entire Main Development Region. This bias is further related to the north‐eastward shifted monsoon trough and a weakened subtropical high, and overly strong tropics‐subtropics connections. This approach could be deployed more widely to other basins and models to diagnose the causes of TCG bias. Plain Language Summary: General Circulation Models (GCMs) have bias in tropical cyclogenesis (TCG). This bias largely reduces the credibility of GCMs. In this study, we suggest an empirical orthogonal function‐based approach to trace the sources of TCG bias in the western North Pacific more rigorously back to large‐scale wind circulation patterns. We find that TCG bias in both basin‐wide and regional scales is a combination of the two biased circulation patterns, associated with too strong tropics‐subtropics connections. The two biased circulation patterns are also featured with a north‐eastward shifted monsoon trough and a weakened subtropical high. We choose the Met Office climate models to demonstrate the approach. But, it can be applied to other GCMs and basins to better understand TCG bias and inform further model development. Key Points: Multivariate empirical orthogonal functions are used to diagnose model bias of tropical cyclogenesis (TCG) in the West PacificTwo leading modes of large‐scale wind circulations can explain most of TCG variability in both ECMWF fifth generation climate reanalysis and MetUMIn MetUM, positive TCG bias is related to large‐scale wind circulations biased toward the positive phase of the simulated modes [ABSTRACT FROM AUTHOR]

Tropical cyclones (TCs) seriously threaten the safety of human life and property especially when approaching a coast or making landfall. Robust, long-lead predictions are valuable for managing policy responses. However, despite decades of efforts, seasonal prediction of TCs remains a challenge. Here, we introduce a deep-learning prediction model to make skillful seasonal prediction of TC track density in the Western North Pacific (WNP) during the typhoon season, with a lead time of up to four months. To overcome the limited availability of observational data, we use TC tracks from CMIP5 and CMIP6 climate models as the training data, followed by a transfer-learning method to train a fully convolutional neural network named SeaUnet. Through the deep-learning process (i.e., heat map analysis), SeaUnet identifies physically based precursors. We show that SeaUnet has a good performance for typhoon distribution, outperforming state-of-the-art dynamic systems. The success of SeaUnet indicates its potential for operational use. [ABSTRACT FROM AUTHOR]