Search Results (255)

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. Full article

Island terrain poses a significant challenge in tropical cyclone (TC) track prediction, particularly during the early development of TCs. Using the Weather Research and Forecasting (WRF) model, China Meteorological Administration (CMA) best-track data, and ERA5 reanalysis, we conducted control (CTRL), terrain-removal (Te0P), terrain-enhancement (Te2P), and no-land-sensible-heat (HFX0) experiments for Typhoon Yagi (2024) near Luzon during 1–3 September. CTRL showed a pronounced northward track bias. Te0P shifted westward and closer to observations, whereas Te2P further amplified the northward bias; HFX0 remained close to CTRL. Terrain-height changes substantially modified the surrounding mid-tropospheric environmental flow and asymmetric horizontal-advection potential-vorticity tendency (PVT_h). Although Te0P produced the closest track, its PVT_h orientation deviated most from ERA5, suggesting that the track improvement partly reflects a compensating reduction in the excessive northward response in CTRL rather than a uniformly more realistic dynamical structure. Land sensible heating mainly affected the boundary layer and nearby circulation, with weaker effects on the broader mid-tropospheric flow and track. These results show that terrain dynamics dominate the simulated track response, while land sensible heat provides secondary modulation, and highlights the need to evaluate track, environmental flow, and PVT_h jointly near complex islands. Full article

Accurate prediction of near-surface meteorological variables is important for weather services and coastal risk management. However, the station-level performance of global artificial intelligence (AI) weather models remains insufficiently characterized in complex coastal environments. This study evaluated Pangu-Weather, FengWu, FuXi, and the Global Forecast System (GFS) against observations from 210 stations in eastern coastal China from July to December 2022. The assessment focused specifically on 2 m temperature, surface pressure, 10 m wind speed, and wind direction across forecast lead times, stations, and routine and typhoon conditions. FuXi had the lowest temperature RMSE (1.70 °C), whereas FengWu had the lowest pressure and wind-speed RMSE values (0.89 hPa and 1.17 m/s, respectively). The models showed distinct spatial error patterns, and wind-speed errors were concentrated at several northern coastal and transition-zone stations. During Typhoon Muifa, errors increased for all models, with the largest deterioration occurring for wind speed. FengWu retained the lowest typhoon-period wind-speed RMSE (1.87 m/s), whereas GFS had the largest value (3.03 m/s). Wind-direction distributions remained difficult for all models to reproduce. These results support variable-specific model selection, but they should not be interpreted as a general ranking of atmospheric forecast systems because the validation is limited to near-surface station data and a six-month period. Full article

Storm surge current-time estimations are strongly influenced by recent water-level conditions, while the temporal dependence among samples from the same typhoon event can complicate the assessment of model generalization to unseen events. This study evaluated storm surge estimation at the Lianyungang tide gauge using 2168 samples from 28 typhoon events during 2002–2024. A 41-feature extreme gradient boosting (XGBoost) model integrating historical surge and physics-motivated information was evaluated using fully nested event-grouped cross-validation, with complete outer-test typhoon events excluded from hyperparameter optimization, early stopping, and model fitting. The 41-feature XGBoost model achieved a mean absolute error (MAE) of 0.083 m, a root mean square error (RMSE) of 0.128 m, and a coefficient of determination (R²) of 0.794. On the common valid sample subset, its RMSE was 9.15% lower than that of Persistence, and it achieved a lower event-level RMSE in 18 of the 28 independently held-out typhoon events. Controlled information-source experiments showed that historical surge information accounted for most of the aggregate predictive skill, whereas adding core storm-state variables and the complete set of physics-motivated descriptors produced only limited changes in overall performance. The relative improvement over Persistence was larger for samples in which the shortest available historical surge lag was 3–6 h than for those with a 1 h lag, but this advantage did not extend consistently to the highest-surge conditions, where systematic underestimation remained evident. These results demonstrate the importance of event-independent validation for assessing machine-learning storm surge estimation and show that the model skill depends strongly on both information availability and the surge magnitude. The framework should be interpreted as a retrospective, single-station current-time estimation approach rather than an operational forecasting or extreme-surge warning system. Full article

This paper evaluates the sensitivity and calibration of the third-generation shallow-water wave model SWAN for Typhoon Doksuri (No. 202305) along the Fujian coast. Sensitivity analyses were conducted for model initialization, wind forcing, and key physical parameters. The results show that a 1-day spin-up period is sufficient to largely reduce the initial error caused by a cold start. A locally refined unstructured triangular grid was adopted, and ERA5 reanalysis winds were blended with the Holland empirical typhoon wind field to better represent extreme winds near the typhoon core. Further tests indicate that the combination of the Janssen wind input scheme, cds1 = 3.5, LTA triad wave interaction scheme, JONSWAP bottom friction scheme, and a wave-breaking parameter of 0.73 can effectively reproduce the typhoon wave process along the Fujian coast. The optimized simulations agree well with buoy observations and provide a reference for typhoon wave forecasting and coastal disaster risk assessment. Full article

To address the insufficient flexibility in power systems caused by renewable energy output uncertainty during extreme weather events, a coordinated source–network–load–storage (SNLS) dispatch method that combines a flexibility supply–demand balance approach with a partitioned grid framework is proposed to achieve the effective enhancement of operational resilience. Firstly, a convolution method is employed to aggregate net load forecast error distributions, and expected flexibility demand metrics are introduced to construct a probabilistic model of compound weather impacts, thereby improving flexibility requirement quantification. Secondly, uncertainties arising from extreme meteorological conditions are considered, and an integrated economic dispatch model for the partitioned grid is established based on chance-constrained reserves and regulation capability envelopes, in order to co-optimize generation costs, demand response, and expected flexibility insufficiency penalties. Then, inter-zone power exchange and spatiotemporal unit commitment dynamics are introduced to optimally redistribute spatial generation surpluses and load deficits, so that a system-wide flexibility supply–demand balance is enabled. Finally, simulations are conducted on the real-world Guangdong 500 kV transmission network under typhoon, heatwave, and rainstorm scenarios, and the results demonstrate the effectiveness of the proposed method in eliminating flexibility deficits, reducing total dispatch costs, and capturing distinct weather-adaptive operational patterns. Full article

Specific humidity profile retrievals from the Geostationary Interferometric Infrared Sounder (GIIRS) onboard Fengyun-4B (FY-4B) are often degraded by cloud contamination, while strict quality control flags further limit data usability. To address these issues, an optimization framework for FY-4B GIIRS specific humidity profiles was developed using ERA5 reanalysis data spanning January 2023 to January 2024. Guangxi and the Beibu Gulf were selected as the study domain. Independent ERA5 datasets, not involved in model construction, were used as a benchmark to evaluate performance. The results indicate that the original FY-4B GIIRS specific humidity profiles tend to underestimate moisture relative to ERA5. For profiles with quality flags of 0 and 1, the Bias, Root Mean Square Error (RMSE), and Mean Relative Error (MRE) range of −3~0 g/kg, 0~4 g/kg, and 17~53%, respectively. After optimization, the bias is effectively reduced to 0 g/kg. RMSE shows an average reduction of 15% within the 700~300 hPa layer, while the most notable improvement in MRE occurs between 1000 and 920 hPa. For lower-quality data (Flags 2–3), the bias, RMSE, and MRE span −12~0 g/kg, 0~13 g/kg, and 48~140%, respectively. Following optimization, the bias range narrows to −6~0 g/kg. RMSE decreases by 20~40% from the near-surface layer up to 400 hPa, and MRE is reduced by 40% below 300 hPa. A case study of Typhoon “Peipah” further demonstrates the model’s effectiveness. At stations experiencing intense rainfall, the optimized specific humidity profiles show markedly improved accuracy, and the Mean Absolute Errors (MAEs) of derived forecast-related physical variables are substantially reduced. Overall, the proposed optimization model significantly enhances both the accuracy and practical usability of FY-4B GIIRS specific humidity profiles, providing more reliable data support for monitoring severe weather events such as typhoons and heavy rainfall. Full article

Short-term coastal surface-current forecasts at forecast lead times ($\tau$ = 1–12 h) are critical for search and rescue (SAR), pollution response, and vessel routing. From a 2015–2019 archive of hourly CODAR high-frequency radar (HFR) observations off Southwestern Taiwan, we developed grid-point long short-term memory (LSTM) models using historical observations alone, without atmospheric forcing or data assimilation (training 2015–2017, validation 2018, test 2019). Because harmonic tides account for ~19% of the surface-current variance, we tested harmonic detiding under a matched architecture and tuning protocol, comparing a raw-input LSTM with a detided variant (LSTM-HA) that forecasts the detided residual and reconstructs the total current. In the out-of-sample 2019 test year ($\tau$ = 12 h), LSTM-HA ranked highest ($R$ = 0.768/0.729 for $u$/$v$) and reduced $RMSE$ by ~34% relative to Persistence; both LSTM configurations far exceeded HA-Persistence and tide-free HYCOM, and the LSTM-HA advantage was statistically significant and spatially pervasive. An independent single-drifter Lagrangian proof-of-concept (December 2020) gave 12 h mean separations of 8.52/9.20 km for LSTM/LSTM-HA, comparable to the HFR observations (9.26 km) and below HYCOM. For this tide-influenced focus area, the benefit of LSTM-HA emerges from approximately $\tau$ = 3 h and becomes most relevant over $\tau$ = 6–12 h. At $\tau$ = 1–3 h, the raw-input LSTM performs nearly equivalently while forecasting the total current directly. Broader seasonal validation, including monsoon and typhoon forcing, remains a priority. Full article

Coastal typhoon deformation plays a critical role in determining typhoon tracks, intensity changes, precipitation and related flooding, storm surges, and typhoon waves, and thus is highly associated with coastal disaster patterns. This study proposes a three-level framework for typhoon wind field modeling through the integration of geometric characterization with physical-informed reconstruction. At its core, an elliptical fitting method is developed based on second-order moments to quantify the structural asymmetries. This geometric fitting method is incorporated into the reconstruction method of Holland–Miyazaki, creating a physically consistent model capable of simulating typhoon deformation processes during landfall. Validation through high-resolution Weather Research and Forecasting (WRF) simulations of Typhoon Chan-hom (2015) demonstrates the framework’s effectiveness, capturing elliptical eyewall deformation with aspect ratios exceeding 1.5, primarily driven by coastal topography and surface friction interactions. The method is further validated through Typhoon Mitag (2019), with mean wind component errors below 1 m/s, the average correlation coefficients surpassing 0.9, and wind direction mean absolute errors largely below 10°. This research provides a practical framework for quantifying and characterizing the wind field deformation during typhoon landfall in coastal regions, thereby supporting ther operational forecasting and disaster reduction in vulnerable coastal regions. Full article

This study investigates tide–surge nonlinear interactions along the southeastern coast of China (SCC) using Typhoon Winnie as a case study. A coupled tide–surge model is established based on the Finite-Volume Community Ocean Model (FVCOM), incorporating realistic bathymetry, tidal constituents, wind fields, and atmospheric pressure. The results show that tide–surge interactions contribute up to 1.8 m to the total water level, with the most pronounced effects occurring in shallow, high-friction coastal regions such as Hangzhou Bay, the Yangtze River Estuary, and the Jiangsu coast. Sensitivity experiments reveal that the quadratic bottom friction term is the dominant mechanism driving the nonlinear interaction, while the advection term plays a secondary role. The interaction intensity is highly sensitive to water depth and topographic slope; reducing water depth generally intensifies the interaction, though the response is non-monotonic in regions with complex bathymetry such as the radial sand ridge field. The phase and period of astronomical tides also exert significant control. Notably, semi-diurnal constituents (e.g., M₂, S₂) dominate the interaction, accounting for up to 80% of the nonlinear effect, whereas diurnal constituents contribute negligibly (less than 0.1 m). Tide–surge coupling significantly affects both the magnitude and timing of extreme water levels, with enhanced interaction occurring during astronomical low tide at some stations (e.g., Dinghai). These findings underscore the necessity of incorporating tide–surge interactions, particularly with accurate bottom friction and semi-diurnal tidal forcing, into storm surge models for improved forecasting and disaster risk assessment along China’s southeastern coast. Full article

Landfalling typhoons are the dominant trigger of short-duration extreme rainfall along the Zhejiang coast. It is necessary to estimate the recurrence of future typhoon rainfall at the city scale under the global-warming scenarios. Using Super Typhoon Lekima (2019) as a representative high-impact event, this study develops an event-based assessment framework for Taizhou city by combining the Weather Research and Forecast (WRF) model simulation, pseudo-global-warming (PGW) perturbation experiments, and generalized extreme value analysis. The historical simulation is first evaluated against the China Meteorological Administration best track, storm intensity evolution, and station rainfall observations. Future counterparts of the same event are then generated using CMIP6-derived thermodynamic perturbations under SSP1-2.6, SSP2-4.5, SSP3-7.0, and SSP5-8.5. Finally, scenario-dependent rainfall totals are projected onto a historical GEV curve to identify equivalent historical rainfall return periods. Results show that the WRF setup reproduces the main track, intensity tendency, and rainfall timing of Lekima with reasonable fidelity. The ensemble-mean cumulative rainfall over the Taizhou area increases from 204.75 mm in the historical simulation to 335.85, 366.72, 400.79, and 464.08 mm under the four SSPs, respectively. These increases translate into equivalent historical rainfall return periods of 47.40, 84.61, 164.28, and 604.05 years, compared with 5.24 years for the historical case. The results indicate that the moderate thermodynamic rainfall amplification produces a highly nonlinear escalation of event rarity based on historical frequency statistics. This implies that future typhoon rainfall should be interpreted using scenario-aware benchmarks within the historical reference framework. Full article

Accurate simulation of landfalling typhoons is essential for urban resilience in the densely populated Pearl River Delta. Using Super Typhoon Mangkhut (2018) as a case study, this paper evaluates the Weather Research and Forecasting (WRF) model through a contribution analysis designed to disentangle the roles of surface layer, planetary boundary layer (PBL), urban canopy model (UCM), and eddy-coefficient/diffusion closure parameterizations in wind-hazard prediction. Model results are validated against observations at the Hong Kong Observatory headquarters (HKO) and King’s Park (KP) stations, demonstrating that the hierarchy of physical controls is strongly metric-dependent. Substantial and structured spread is found among the tested configurations. Controlled comparisons show that PBL selection is the primary driver of variability in peak timing and high-wind persistence, whereas surface-layer formulation and diffusion closure exert secondary but systematic influences by shifting distributional centers and reshaping variability and upper tails. Urban canopy effects are comparatively weaker in aggregate but become more apparent during the impact and recovery phases. Overall, the results confirm that no single parameterization is consistently optimal across all metrics and motivate a multi-objective physics-selection strategy, in which multi-physics ensembles are used to better represent uncertainty in wind-event duration and associated loading risks in complex urban environments. Full article

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. Full article

Accurate forecasting of typhoon evolution from satellite cloud imagery is critical for disaster preparedness and mitigation, yet remains challenging due to the complex spatiotemporal dynamics of typhoon systems. While deep learning models have shown promise in spatiotemporal sequence prediction, existing approaches often struggle to balance the modeling of large-scale structural evolution with fine-grained local dynamics. In this paper, we propose FusionTyphoonPredictor, a novel dual-branch encoder–decoder framework designed for typhoon cloud image prediction. The model integrates a Global Fusion Module to capture multi-scale spatial interactions using large-kernel attention and multi-scale convolution, and an ST Recurrent Refiner to enhance temporal consistency and local detail through recurrent processing with ConvGRU and residual blocks. Extensive experiments on the Digital Typhoon dataset demonstrate that our approach achieves improved performance compared to existing methods (including PredFormer and PhyDNet) across most metrics and forecasting horizons. Specifically, FusionTyphoonPredictor shows consistent advantages in SSIM, MAE, and MSE, with particular strength in short-term forecasting. Comprehensive ablation studies validate the complementary design of the two branches and confirm the effectiveness of each proposed component. Our work advances typhoon forecasting and has potential for real-time operational deployment. Full article

The accuracy of numerical weather prediction largely depends on the quality of the initial conditions. Global Navigation Satellite System radio occultation (GNSS-RO) observations, with their high vertical resolution, play an important role in reducing initial condition errors. In this study, multiple simulations with different initialization times were conducted during the development of Typhoon BEBINCA using the WRF-GSI assimilation system to evaluate the impact of YunYao GNSS-RO observations on improving extreme weather simulation performance and to investigate the sensitivity of refractivity assimilation to different cloud microphysics parameterization schemes. The results show that assimilating YunYao GNSS-RO data significantly improves the consistency between the model initial fields and observations and enhances the analysis quality in the middle and upper troposphere. Compared with ERA5 reanalysis data, the assimilation experiments better reproduce the spatial and temporal evolution of key atmospheric variables, and the improvements persist from 36 h to 120 h forecast lead time. Statistical results from multiple initializations show that the maximum RMSE reductions exceed 0.2 K for temperature, 0.1 m s⁻¹ for wind speed, and geopotential height shows consistent improvements throughout the entire atmosphere. In addition, the assimilation experiments improve the simulation of Typhoon BEBINCA’s track and intensity. Statistical results from multiple initializations indicate that the 84 h track error is reduced by approximately 30 km on average, and the minimum central pressure bias is also reduced. Sensitivity experiments further show that the WSM6 microphysics scheme performs better in track forecasting, while the Thompson scheme is more suitable for intensity forecasting. Overall, YunYao GNSS-RO assimilation effectively improves typhoon forecast accuracy and demonstrates strong potential for operational applications. Full article