Shallow-water depth information is essential for ship navigation and fishery farming. However, the accurate acquisition of shallow-water depth has been a challenge for marine mapping. Combining Ice, Cloud, and Land Elevation Satellite-2 (ICESat-2) bathymetry data with multispectral data, satellite-derived bathymetry is a promising solution through which to obtain bathymetric information quickly and accurately. This study proposes a photon refraction correction method considering sea-surface undulations to address errors in the underwater photons obtained by the ICESat-2. First, the instantaneous sea surface and beam emission angle are integrated to determine the sea-surface incidence angle. Next, the distance of photon propagation in water is determined using sea-surface undulation and Snell’s law. Finally, position correction is performed through geometric relationships. The corrected photons were combined with the multispectral data for bathymetric inversion, and a bathymetric map of the Yongle Atoll area was obtained. A bathymetric chart was created using the corrected photons and the multispectral data in the Yongle Atoll. Comparing the results of different refraction correction methods with the data measured shows that the refraction correction method proposed in this paper can effectively correct bathymetry errors: the root mean square error is 1.48 m and the R2 is 0.86.

Significant Wave Height (SWH) is a crucial parameter in ocean wave dynamics, impacting coastal safety, maritime transportation, and meteorological research. Building upon the TimesNet neural network, a recent advancement in the realm of time series prediction in deep learning, this study proposes an integrated approach combining Empirical Mode Decomposition (EMD) with TimesNet, introducing the EMD-TimesNet model for SWH forecasting. The TimesNet model’s multidimensional spatial mapping guarantees effective historical information extraction, while the EMD approach makes it easier to decompose subsequence characteristics inside the original SWH data. The predicted Root Mean Square Error (RMSE) and Correlation Coefficient (CC) values of the EMD-TimesNet model are 0.0494 m and 0.9936; 0.0982 m and 0.9747; and 0.1573 m and 0.9352 at 1 h, 3 h, and 6 h, respectively. The results indicate that the EMD-TimesNet model outperforms existing models, including the TimesNet, Autoformer, Transformer, and CNN-BiLSTM-Attention models, both in terms of overall evaluation metrics and prediction performance for diverse sea states. This integrated model represents a promising advancement in enhancing the accuracy of SWH predictions.

Shallowwater depth plays an important role in marine development, navigation safety, and environmental protection. It is an efficient and economical way to obtain water depth by remote sensing technology. At present, most empirical models based on multispectral image usually obtain water depth by the relationship between the sea surface reflectance (SSR) (a single pixel) and in situ water depth, it is a one-to-one correspondence between the reflectance and depth. However, seafloor substrate and inherent optical properties (IOP) will also have contribution to the SSR. In this article, we propose an adjacent pixels multilayer perceptron model (APMLP) model using adjacent pixels to weaken the influence of seafloor substrate and IOP.Datasets on Oahu Island (Sentinel-2B, LIDAR in situ data) and Saint Thomas Island (Sentinel-2A, LIDAR in situ data) are used to establish and verify the model. The APMLP model are also compared with the multilayer perceptron model (MLP) model, BP neural network model, and Log-ratio model. The overall root-mean-square error (RMSE) of APMLP model on Oahu Island is 0.72 m, which is much better than the other three models (MLP 1.07 m, BP 1.05 m, Log-ratio 1.52 m). Similar results are obtained from the Saint Thomas Island dataset, RMSE of APMLP model is 1.56 m, better than the other three (MLP 1.91 m, BP 1.89 m, Log-ratio 2.39 m). The study confirms that considering adjacent pixels in an artificial neural network model can effectively improve the performance of water depth retrieval.

Shore zone information is essential for coastal habitat assessment, environmental hazard monitoring, and resource conservation. However, traditional coastal zone classification mainly relies on in situ measurements and expert knowledge interpretation, which are costly and inefficient. This study classifies a shore zone area using satellite remote sensing data only and investigates the effect of the statistical indicators from Ice, Cloud, and Land Elevation Satellite-2 (ICESat-2) information with the Sentinel-2 data-derived spectral variables on the prediction results. Google Earth Engine was used to synthesize long time-series Sentinel-2 images, and different features were calculated for this synthetic image. Then, statistical indicators reflecting the characteristics of the shore zone profile were extracted from ICESat-2. Finally, a random forest algorithm was used to develop characteristics and shore zone classification. Comparing the results with the data measured shows that the proposed method can effectively classify the shore zone; it has an accuracy of 83.61% and a kappa coefficient of 0.81.

The log-ratio model (LRM) with three model parameters ( ${\boldsymbol{n}}$ , ${{\boldsymbol{m}}_1},$ and ${{\boldsymbol{m}}_0}$ ) has been widely used in shallow water bathymetry of multispectral images. At present, obtaining LRM model parameters by optimization algorithms depends on the setting of initial values [ ${\boldsymbol{n}}(0)$ , ${{\boldsymbol{m}}_1}(0),$ and ${{\boldsymbol{m}}_0}(0)$ ] or initial value ranges. However, how to set the initial value can obtain model parameters more effectively and credibly, and the significance of each initial value in the optimization process is very important for LRM bathymetric retrieval method. In this article, remote sensing images and bathymetric data were used to determine the initial value ranges of credible model parameters, and then the sensitivity of each parameter was analyzed in the algorithm optimization process from the partial differential perspective, and the bathymetry was retrieved in the sea area near Ganquan Island. The results show that according to the partial differential analysis of model parameters, ${\boldsymbol{n}}$ , with the smallest change rate in three LRM parameters and the rate of ${{\boldsymbol{m}}_1}$ and ${{\boldsymbol{m}}_0}$ is at least five times of it. So ${\boldsymbol{n}}(0)$ needs more iterations to achieve the optimal. Therefore, the initial value ${\boldsymbol{n}}(0)$ determines whether the optimization method can obtain credible LRM model parameters and the algorithm convergence speed. And when ${\boldsymbol{n}}(0) \in ({1/{{\boldsymbol{R}}_{{{\bf min}}}},\ 1000} ]$ ( ${{\boldsymbol{R}}_{{{\bf min}}}}$ is the minimum reflectance in blue and green bands), there must be a credible model parameter solution. The bathymetric retrieval results of the sea area with coral and sand substrates show the applicability of our initial value ranges in different substrate area.

Typhoon-induced ocean responses are not only a key mechanism for regulating global heat transport and maintaining the energy balance of the climate system, but also the core physical processes underlying the intense exchange of matter and energy at the air-sea interface under extreme dynamic forcing. However, traditional passive sampling methods are limited by their discontinuous and sparse spatiotemporal coverage, making it difficult to capture the complete three-dimensional structure and rapid evolution of upper-ocean responses during the critical window of typhoon passage. Autonomous Underwater Vehicles (AUVs) and Underwater Gliders (UGs), with their active tracking and sampling capabilities, can effectively resolve the spatiotemporal evolution of these highly dynamic processes. This paper presents a high-resolution temperature-salinity dataset covering the passage of seven typhoons in the South China Sea during 2024. Constructed from collaborative observations by 62 UGs and 2 AUVs, the dataset achieves an average spatial resolution of 2.4–3.8 km and an average temporal resolution of 3.5–4.3 h (99.7% of the samples had resolutions within 8.4 km and 6.7 h, respectively ). The dataset successfully captures the complex upper-ocean temperature and salinity responses under typhoon forcing, including cooling and salinity increase due to pumping, cooling and salinity decrease triggered by freshwater caps formed by precipitation, cooling and salinity decrease caused by background warm eddies, and significant near inertial oscillations in temperature and salinity. This dataset holds significant potential for in-depth investigation of typhoon-ocean coupling mechanisms and for improving the accuracy of numerical model forecasts.