To explore the effects of air‐sea interaction on the eyewall replacement cycle (ERC) of tropical cyclones (TCs), an ERC of Typhoon Sinlaku (2008) was reproduced using the high‐resolution coupled ocean‐atmosphere‐wave‐sediment transport (COAWST) model. The numerical simulations were evaluated with a wide range of observational datasets. Moreover, the importance of the ocean to ERC is discussed by comparing six sensitive experiments, that is, three uncoupled experiments with different time‐invariant sea surface temperatures, an ocean‐atmosphere coupled experiment, an ocean‐wave coupled experiment, and an ocean‐atmosphere‐wave fully coupled experiment. The results show that Sinlaku simulated by the fully coupled experiment was highly consistent with the observations, and the evolution of ERC varies from those only simulated by the atmospheric models in previous studies. When the ocean and waves were both considered, the lifetime of the ERC was significantly prolonged, even though the simulated Sinlaku was weakened by the cooling of the sea; the asymmetric distribution of the concentric eyewalls (CEs) which caused by the non‐uniform energy exchanges was also prominent. By contrast, without ocean coupling, the simulated secondary eyewall, composed of axisymmetric convections, exhibited false enhancement and fake inward contraction, and the duration of the ERC was also shorter than that actually observed. In conclusion, the results highlight the significance of ocean coupling for the numerical simulation of the ERC of a TC, including survival time and asymmetric structure.

Clouds critically influence Earth’s radiation balance and climate, making accurate cloud detection essential for improving climate models. This study develops the TSAR model to improve the cloud detection accuracy of the FY-4A CLM product by incorporating physical features. The input features include FY-4A brightness temperature (BT) data from channels 8–14, geometric parameters (satellite zenith angle (SAZ), satellite azimuth angle (SAA), solar zenith angle (SOZ), solar azimuth angle (SOA), and latitude), and four ERA5 meteorological factors (2 m air temperature (T2m), skin temperature (SKT), air temperature profiles (ATP), and relative humidity profiles (RH)). Using the CALIPSO cloud detection product as labels, the model outputs cloud/clear-sky classification results. Additionally, four machine learning (ML) algorithms—RF, LightGBM, XGBoost, and MLP—achieved overall accuracies of 91.5%, 92.2%, 92.5%, and 92.8%, respectively, considerably outperforming the FY-4A L2 CLM product (83.1%). The results demonstrate that incorporating physical factors significantly improves cloud detection performance regardless of the algorithm employed. Incorporating meteorological factors notably improved nighttime and water–cloud detection, narrowing day–night accuracy gaps. Shapley additive explanation (SHAP) analysis indicated feature contributions of 15.8%, 50.8%, and 33.3% from geometric, BT, and meteorological variables, respectively, with stronger meteorological effects at mid- to high-latitudes. These findings demonstrate that integrating meteorological factors significantly improves FY-4A cloud detection accuracy and consistency, highlighting the MLP-TSAR model’s effectiveness for reliable all-day operational applications.

Short-duration heavy rainfall occurring simultaneously across multiple subregions is more likely to trigger severe flooding than events confined to a single local area, yet long-term changes in hourly precipitation synchrony remain poorly quantified. We analyse hourly rain-gauge observations over South China during the 1981–2020 pre-summer rainy season and ERA5 environmental diagnostics. Using a simplified station-based definition, we find a significant increase in synchronized heavy-rain hours of 0.24 percentage points decade ⁻¹ , equivalent to about +16.7% of the 40-year mean per decade. This increase is expressed mainly as more frequent multi-cluster and multi-regional coactivity, rather than expansion of a single coherent rain area. Synchronized-event days occur within circulation and thermodynamic windows characterized by broader convective instability, stronger low-level moisture transport and convergence, more frequent low-level jets, and a favorable western North Pacific subtropical high configuration. The increasing recurrence of these event-like windows is consistent with the observed rise in synchronized heavy-rain hours. These results identify rainfall synchrony as a spatial connectedness dimension of short-duration extremes and highlight its relevance for compound flood-hazard assessment in humid monsoon regions.