Zhejiang Province in China is one of the most typhoon-prone regions globally, making typhoon and storm surge hazard analysis critically important for disaster mitigation. This study integrates the Tropical Cyclone Risk Model (TCRM) with a machine learning-based storm surge forecasting model to analyze typhoon hazards and storm surge risks at four representative coastal sites in Zhejiang Province: Haimen, Ruian, Wenzhou, and Zhapu. Firstly, the input database of the TCRM has been updated and subsequently used to generate a 1000-year synthetic typhoon event catalog for the Northwest Pacific region. Secondly, four machine learning models—Long Short-Term Memory (LSTM), Back Propagation (BP), Support Vector Regression (SVR), and Random Forest (RF)—were developed to forecast storm surge component at the four sites, with sensitivity analysis conducted on the input parameters. Among the four models, RF consistently outperformed the others across all four sites. Thirdly, by integrating the storm surge forecasting model with the Yan Meng (YM) typhoon wind field model, extreme wind speed sequences and extreme surge component sequences were derived for the four coastal sites. Finally, four extreme value distribution models—empirical distribution, Weibull, Gumbel, and Generalized Pareto Distribution (GPD)—were applied to fit the extreme wind and surge sequences. Goodness-of-fit tests indicated that the GPD best captured extreme wind speeds at all four sites and extreme surge levels at Haimen, Ruian, and Wenzhou. Using the optimal distributions, return periods (10-, 50-, 100-, and 200-year) for extreme wind speeds and surge components were calculated, providing actionable references for disaster risk management authorities.

Storm-surge residuals represent one of the most destructive marine-coastal hazards, and reliable short-term surge residual prediction is critical for coastal disaster preparedness. Conventional empirical forecasting approaches suffer from limited cross-regional generalization, while high-fidelity physics-based hydrodynamic models such as ADCIRC-SWAN can reproduce complete storm-surge physical processes but demand substantial computational resources. In this study, a three-layer back-propagation neural network (BPNN) for storm-surge residual forecasting is constructed, which is driven by output datasets from the validated ADCIRC-SWAN coupled hydrodynamic model. Wind speed, significant wave height, sea-surface atmospheric pressure, and the simulated current-time storm-surge residual are selected as input predictors. Simulation-derived samples are pre-processed via data cleaning and Min-Max normalization, and two different dataset partitioning strategies (random mesh-point-based partition and time-sequential partition) are implemented for comparative experiments. After hyperparameter sensitivity tests, the optimal network configuration with 30 hidden-layer neurons is determined. Model predictive performance is quantitatively evaluated via multi-station time-series comparison and universal statistical metrics including R, NSE, and RMSE. The results show that the BPNN achieves satisfactory performance under random mesh-point-oriented partitioning, yet obvious performance degradation occurs under time-sequential temporal extrapolation, with prominent underestimation of surge peaks. On the basis of BPNN-predicted spatial surge residual fields, storm-surge intensity grading is carried out following the Chinese national standard GB/T 39418-2020. Statistical comparisons between the full computational domain and the Pearl River Estuary sub-region reveal strong spatial aggregation of high-intensity storm-surge grids within the estuary driven by funnel-shaped topographic amplification. This work demonstrates the feasibility of using a BPNN as a surrogate emulator for hydrodynamic outputs under a given typhoon condition; however, limitations in temporal extrapolation performance still need to be addressed before this approach can be practically used in operational early-warning applications.

In this study, we employ seven well-established machine learning algorithms for the stochastic simulation of tropical cyclones in the Northwest Pacific, namely Support Vector Machine (SVM), Random Forest (RF), Bayesian Network (BN), Backpropagation Neural Network (BPNN), Wavelet Neural Network (WNN), Recurrent Neural Network (RNN), and Long Short-Term Memory (LSTM) network. First, based on the CMA (China Meteorological Administration) Tropical Cyclone Best-Track Dataset, we statistically analyze key typhoon parameters within each 5° × 5° grid over the Northwest Pacific. Second, the Random Forest method is applied to rank the importance of feature factors for predicting typhoon translation speed, storm heading, and central pressure in each grid. Third, each algorithm is used to develop prediction models, with hyperparameters optimized via a time-series cross-validation scheme. Fourth, the prediction models are compared to identify the best-performing model for predicting translation speed, storm heading, and central pressure, respectively. The optimal models are then evaluated in terms of computational efficiency and overfitting/underfitting, and validated both against traditional statistical methods and through multi-lead-time (1–72 h) predictions for four independent typhoons: Lekima 2019, Doksuri 2023, Ragasa 2025, and Yagi 2024. The results show that the optimal machine learning models outperform traditional statistical benchmarks, achieve a direct position error of <7 km and R² ≥ 0.979 at 1 h lead time, with track prediction remaining useful up to 48–72 h, while effective intensity prediction does not exceed 24 h. This study provides a robust data-driven framework for short-term typhoon forecasting within stochastic simulation, with future work aiming to extend to long-term predictions.