Satellite remote sensing plays a fundamental role in observing oceanic processes by providing large-scale, long-term, and continuous measurements. With the increasing availability of multisource satellite data, challenges such as data gaps, complex environmental conditions, and the limitations of conventional retrieval methods have become more evident. In recent years, artificial intelligence (AI) has emerged as a practical and effective approach to address these issues. This article reviews the development of AI techniques in satellite ocean remote sensing, focusing on three main application areas: parameter retrieval, data reconstruction, and image-based ocean phenomenon detection. For geophysical variable retrieval, AI models such as convolutional neural networks (CNNs) and Transformer architectures have improved the accuracy of ocean waves, sea surface, salinity, wind, and ocean color estimates, especially under extreme or noisy conditions. In the field of data reconstruction, AI methods enable the completion of missing data in both surface and subsurface ocean layers, offering finer spatial–temporal resolution and better consistency than traditional interpolation approaches. For image interpretation, deep learning (DL) models have been applied to detect and segment dynamic ocean features such as mesoscale eddies, internal waves, sea ice, and tropical cyclones (TCs), achieving high efficiency and precision. This article also highlights the integration of AI with physical knowledge, the use of multisource fusion, and the trend toward near real-time (NRT) applications. These developments indicate that AI will play an increasingly important role in future satellite-based ocean observation and environmental monitoring.

Synthetic Aperture Radar (SAR) has unique advantages in sea surface wind field retrieval due to its all-weather observation capability and high spatial resolution. However, the effectiveness of wind measurement is vulnerable to limitations such as saturation of backscattering signals from the sea surface and attenuation of heavy rainfall under extreme weather conditions. Considering that the response of physical factors (e.g., radar backscattering coefficient at different polarizations) to wind varies in different wind speed ranges, in this study, based on 36 scenes of dual-polarized Sentinel-1 SAR images of hurricanes from 2016 to 2023, and using wind speed observations from the airborne Stepped-Frequency Microwave Radiometer (SFMR) as ground truth values, we proposed a partition and fusion residual transfer network (PFRTNet) model. In the training process, two separate residual neural networks were pretrained under low-to-medium wind speeds (< 30 m/s) and high winds (≥ 30 m/s), and combined with the idea of transfer learning. An attention mechanism was then introduced to achieve adaptive feature fusion. The optimal model inputs were determined by feature importance analysis and sensitivity experiments, which consists of 14 features including SAR measured physical parameters, image texture features, hurricane morphological information, as well as environmental and geographic factors. The PFRTNet model can effectively alleviate the underestimation of high wind speed caused by sample imbalance, and significantly improve the accuracy of hurricane wind retrieval. Independent evaluation results based on an additional 9 SAR images demonstrate that the algorithm achieves a root mean square error (RMSE) of 2.81 m/s under high wind conditions. Compared with other machine learning methods and traditional empirical algorithms, PFRTNet has significant performance advantages, with a RMSE reduction of approximately 2.0 m/s or more, confirming its robustness in retrieving hurricane wind speeds and finer-scale structural features.

Single-beam synthetic aperture radar (SAR) Doppler frequency observations have been widely used for retrieving ocean surface radial current velocities. However, the Doppler frequency contains multiple components, among which the systematic shift caused by electronic pointing error (EPE) is difficult to accurately model and remove. This issue is particularly prominent in open-ocean regions without land echo references, where it can significantly affect the accuracy of current retrieval. To address this problem, this study proposes a Bayesian framework–based method for radial current velocity retrieval, which innovatively incorporates the systematic Doppler shiftbcaused by EPE as a key parameter into the state vector, enabling its joint estimation with the ocean surface radial current velocity. Empirical analysis of 1,800 SAR sub-swath images demonstrates high consistency between the estimated Doppler shiftband land-derived true values, with a standard deviation (STD) of 6.45 Hz and a correlation coefficient (R) exceeding 93%. This validates the method’s capability for accurate EPE estimation in remote ocean regions. Performance comparisons against HF radar observations and drifting buoy measurements confirm that the proposed Bayesian retrieval method significantly outperforms conventional direct approaches: it reduces radial current velocity STD by 0.23 m/s and improves R by 35.60%. Additionally, it effectively corrects systematic biases in the ocean model background field, lowering the STD of the retrieved radial velocity relative to the model by 13.33%. Even in complicated dynamic contexts, the approach retains great accuracy and physical consistency, as demonstrated by case studies in unique regions. In conclusion, the suggested Bayesian retrieval method significantly improves the precision, resilience, and usefulness of radial current velocity retrieval while successfully resolving the technical difficulty of EPE correction in SAR data over open oceans.

Synthetic Aperture Radar (SAR), with its ability to function under any weather conditions and at any time of day, along with multi-polarization and frequent revisit capabilities, plays a crucial role in flood monitoring. However, SAR images face challenges such as coherent speckle noise, feature mixing, terrain undulation, and adverse weather, making flood monitoring difficult. To address these challenges, this paper proposes a high-precision flood mapping method from Sentinel-1 dual-polarization SAR data. We begin by generating false-color images through polarization combination and apply them to a multiscale segmentation approach, overcoming the limitations of single-polarization scattering and effectively reducing speckle noise. Digital elevation model and reference water datasets are integrated into the segmentation process to mask terrain shadowing and permanent water. To reduce feature mixing effects, the optimal SAR image with minimal feature mixing is selected for flood mapping using the Gaussian Mixture Model. In the subsequent two-step classification process, fuzzy sets of texture features are incorporated to assist in categorizing uncertain regions, further reducing interference from feature mixing and enhancing flood recognition accuracy. Additionally, integrating pixel-level and object-level analyses minimizes errors caused by improper segmentation. The proposed method is compared with several well-established algorithms, and the results demonstrate that our method outperforms the others in flood mapping accuracy. Analysis of years of flooding on the Leizhou Peninsula shows that Sentinel-1 SAR has the potential to effectively monitor the occurrence and development of floods.

Sea surface temperature (SST) measurements are crucial in the context of climate change. Microwave SST measurements are currently provided by radiometers operating in the C- and X-bands. In-orbit K- and Ka-band payloads lack the commonly used C- and X-bands for SST retrieval. We present the K-KaSSTNet, a residual neural network (NN) that, for the first time, uses the K and Ka microwave bands with much weaker SST response than C- and X-bands for SST retrieval. Despite training on a limited dataset from 2020 to 2021, K-KaSSTNet consistently achieves reasonable accuracy SST retrievals for data spanning 2017–2022. Moreover, by using deep learning (DL) interpretability methods, we have unveiled the underlying mechanisms driving K-KaSSTNet. When extended to the Special Sensor Microwave Imager/Sounder (SSMIS) and Calibration Microwave Radiometers (CMRs)—payloads typically not used for SST retrieval—the K-KaSSTNet model maintains SST retrievals with reasonable accuracy compared with Advanced Microwave Scanning Radiometer-2 (AMSR-2). This extension broadens the spatiotemporal coverage of microwave SST products and enhances the temporal sampling frequency and continuity of microwave SST measurements.

The incomplete eye structure during the generation and weakening stages of tropical cyclones (TCs) makes it difficult to accurately locate low-intensity TCs in satellite infrared (IR) images. Here, we develop a physics-enhanced deep convolutional neural network (CNN) to determine centers of tropical depressions (TDs) and tropical storms (TSs) with maximum sustained wind speed (MSW) below 63 kt. This is accomplished by integrating consecutive IR images from the Himawari-8 geostationary satellite and historical information of TCs including center position, MSW, and the minimum pressure. Multi-channel images of 196 TCs over the Northwest Pacific from 2015 to 2021 are randomly divided into a 3:1:1 ratio for model training, validation, and testing. Sensitivity experiments are designed to investigate the influence of different inputs on model performance. The best results are achieved by combining 18 hours of images at three IR channels and historical TC information at 3-h intervals as model inputs. The mean distance between the model identified center and that recorded in the Best Track dataset for TD and TS levels are 20.1 km and 19.1 km, respectively. This indicates an accuracy improvement of 63.0% and 54.6%, respectively, over the model which only considers images at the current moment. Compared with some other state-of-the-art models, the center positions of TDs and TSs determined by our model agree better with the Best Track records. The CNN model also performs quite well in determining the center of stronger TCs, with an average error of 14.1 km, indicating it is robust for all-level TCs.

Microwave radiometers are widely used in Earth observation and ocean monitoring for their strong penetration ability. Nevertheless, their utilization is somewhat constrained by their intrinsic low-resolution capability, particularly in complex applications such as coastal zone monitoring and analysis of typhoons. To overcome this limitation, resolution enhancements are necessary. Here, we present a novel resolution enhancement technique, the alternating proximal gradient (APG) method, applied to Haiyang-2B (HY-2B) Scanning Microwave Radiometer (SMR) data. This method is based on the decorrelation approach and incorporates total variation constraint. The APG method, along with the Backus-Gilbert (BG) method, are both applied to the 6.925GHz data of HY-2B SMR. Both simulated and real HY-2B SMR data from two representative regions, including land-sea transition zones and cyclonic storms, are analyzed. Results show that both the BG method and the APG method can significantly enhance details obscured in the original SMR data. Furthermore, the enhanced brightness temperatures are compared to the AMSR-2 25 km product, revealing that the APG method provides more consistent results and contains more reliable information than the BG method in terms of resolution enhancement.

Retrieving temperature structure of the interior ocean based on surface parameters is important for the study of complex dynamic processes in the ocean. This study introduces an artificial intelligence (AI) approach called Attention U-net to reconstruct the subsurface temperature (ST) field in the South China Sea (SCS) from sea surface parameters. The 5-day average temperature profiles with 0.5° spatial resolution from Simple Ocean Data Assimilation (SODA) product were used for training the network and evaluating the accuracy of estimated results. The Attention U-net model showed a good performance on the ST reconstruction in the upper 100 m of the SCS. The root mean square error (RMSE) between the reconstructed temperature and SODA reanalysis data ranges from 0.39 to 1.42°C, and the average value is 1.08°C. The correlation coefficient (R) is significant in the upper 60 m and becomes weaker as depth increases. The overall R is 0.95. This study provides an effective technique for the ST reconstruction with relatively high spatial and temporal resolution in the SCS.

In this study, a set of deep convolutional neural networks (CNNs) was designed for estimating the intensity of tropical cyclones (TCs) over the Northwest Pacific Ocean from the brightness temperature data observed by the Advanced Himawari Imager onboard the Himawari-8 geostationary satellite. We used 97 TC cases from 2015 to 2018 to train the CNN models. Several models with different inputs and parameters are designed. A comparative study showed that the selection of different infrared (IR) channels has a significant impact on the performance of the TC intensity estimate from the CNN models. Compared with the ground truth Best Track data of the maximum sustained wind speed, with a combination of four channels of data as input, the best multicategory CNN classification model has generated a fairly good accuracy (84.8%) and low root mean square error (RMSE, 5.24 m/s) and mean bias (−2.15 m/s) in TC intensity estimation. Adding attention layers after the input layer in the CNN helps to improve the model accuracy. The model is quite stable even with the influence of image noise. To reduce the side-effect of the very unbalanced distribution of TC category samples, we introduced a focal_loss function into the CNN model. After we transformed the multiclassification problem into a binary classification problem, the accuracy increased to 88.9%, and the RMSE and the mean bias are significantly reduced to 4.62 and −0.76 m/s, respectively. The results show that our CNN models are robust in estimating TC intensity from geostationary satellite images.

In this study, an Attention U-net network was proposed to reconstruct the subsurface temperature (ST) field with high temporal and spatial resolution in the South China Sea (SCS) from sea surface parameters observed by satellites. In addition to sea surface temperature, sea level anomaly and sea surface wind field, the wind stress curl, which influences three-dimensional structure of temperature through the induced Ekman pumping and transport, was also input into the model. The 5-day average vertical temperature profiles with spatial resolution of 0.5° from Simple Ocean Data Assimilation (SODA) reanalysis were used for training and evaluating the network. The results show that the Attention U-net model performs quite well in ST reconstruction in the upper 100 m layers of the SCS. The additional input of wind stress curl helps to improve the model accuracy. The average root mean square error (RMSE)/bias of ST decreases from 1.08°C/-0.21°C to 1.01°C/-0.05°C. Particularly, the RMSE near the thermocline is reduced significantly by up to 10.9%. The estimation error of the Attention U-net model is much smaller than that of some linear and tree models in the SCS, especially in shallow waters and regions with complex dynamic processes. The case study also shows that our model is capable of capturing the evolution of mesoscale processes in the SCS. The combination of satellite observations with high-precision ST reconstruction model will help us comprehensively understand the fine structure and variation of temperature and circulation in the marginal seas and open oceans.

Satellite observations and in situ BGC-Argo profiles are used to explore the impacts of two sequential tropical cyclones (TCs) Man-yi and Pabuk in 2013 on the distribution of chlorophyll-a (CHL) and dissolved oxygen (DO) concentration. After the passages of TCs, apparent CHL enhancement is observed mainly resulting from TC-induced vertical mixing and upwelling as well as the favorable conditions of the near-shore area. CHL blooming patches correspond to the pre-existing cyclonic eddies (CEs) owing to their relatively unstable thermodynamic structures. While in anti-cyclonic eddies (AEs), CHL concentration is likely to maintain at a lower value because of weaker stratification inside AEs. A significant increase of near-surface DO concentration is detected, which is caused by TC-induced vertical mixing and photosynthesis of increased CHL. Conversely, subsurface DO decreases, accompanied by a drop of maximum DO and oxycline depth, mainly due to the strong upwelling induced by TCs and the CE.

In this study, a deep convolutional neural network (CNN) was developed to forecast the movement direction of tropical cyclones (or typhoons) over the Northwestern Pacific basin from Himawari-8 (H-8) satellite images. 2250 infrared images which captured 97 typhoon cases between 2015 and 2018 were used to train the CNN model. By using images from Channels 13 and 15 as input into the CNN model, the mean error of the typhoon movement angle reaches up to 27.8°, which shows the great potential of deep learning in tropical cyclone track prediction.

In this study, we proposed an automatic internal wave (IW) signature extraction method based on the deep convolutional neural networks (DCNN). Our objective is to provide a rapid and simple to use method that can tackle the IW signature extraction in images from different satellite sensors without re-training or manual interference. We proved the generalization ability of our method across multiple optical satellite sensors. The statistical results show this DCNN-based method has appreciable transferability and is promising for efficient extraction of internal wave signature in different satellite images with varying spatial resolution even under complex imaging conditions.

In this work, the cyclostationary empirical orthogonal function analysis and the empirical mode decomposition (EMD) method is used to compute the low frequency parts (T >~5 years) in tide gauge, satellite altimetry and reconstructed sea level data. High spatio-temporal correlations are observed between tide gauge measurements North of Cape Hatteras (NCH) and other datasets in the subpolar and tropical regions in the North Atlantic Ocean. The altimeter and tide gauge data show significant different spatial pattern of correlation over north with that South of CH. In the last two decades, the weakening of Atlantic Meridional Overturning Circulation (AMOC) might be related to the phase reversal of the correlations in the NCH as well as the strengthening of positive correlations in the tropical regions. Moreover, higher correlations observed near the tide gauges on the coasts of the NCH are presented by comparing the correlations in the time span of 2003-2012 with that in 1993-2002. Both the North Atlantic Oscillation, Atlantic Multidecadal Oscillation and ocean heat content variations, which could affect AMOC and Gulf Stream variations, are linked to the variations of the correlations.

In this study, a deep convolutional neural network was designed to estimate the intensity of tropical cyclones over the Northwestern Pacific Ocean from high-frequency Himawari-8 satellite images. Our model achieved good results by using the brightness temperature derived from one single infrared band data. The accuracy of the top (top-1) and the second best (top-2) tropical cyclone intensity classification reaches 81.4% and 93.3%, respectively.

In this study, we exhibit the temporal variability of Sea State Bias (SSB) correction in TOPEX (sides A and B), Jason-1, Jason-2 and Jason-3 missions over 1993-2017 time span. Although the trend in long-term global mean 2D nonparametric SSB correction is not significant from zero (- 0.03±0.03 mm/yr, e.g., accounts for 1% of current global mean sea level rate) during 1993-2016, it contributes - 1.27±0.21 mm/yr and -0.26±0.13 mm/yr in TOPEX-A and Jason-2 missions, respectively. Also, the SSB trend in TOPEX-A may be partly related to the recently reported sea level trend drift during 1993-1998. On zonal average, SSB correction causes about 1% uncertainty in mean sea level trend. In regions with high significant wave height (SWH), the uncertainties grow to 2% and 4% at near 50°N and 60°S, respectively.

In this study, four daily sea surface temperature (SST) products combined with satellite infrared or microwave sensor derived SST data with different spatial resolution and in situ measurements, are used to investigate the SST response to super typhoon Soudelor in 2015 over the Northwestern Pacific Ocean. Before typhoon Soudelor passes by the studied area, the magnitude and spatial distribution of SST from different products are consistent with each other, and all products show the existence of the cyclonic eddies. However, during the passage of typhoon Soudelor, the four SST products show significant difference in the extent and intensity of typhoon-induced SST cooling, especially in the mesoscale eddy regions. OISST dataset based on the infrared sensor shows the weakest and smallest surface cooling area. Much more intense decrease in SST is found in MW OISST and MW-IROISST datasets, which integrate a variety of microwave-derived SST. With a higher resolution up to 1 km, MURSST may reveal more detailed features in SST variation.

The upper ocean nutrients concentration is found to be enhanced in the peripheries of two anti-cyclonic mesoscale eddies in the Western North Pacific (WNP) through using AVISO Sea Level Anomaly (SLA), a Bio-Geo-Chemical Argo (BGC-Argo) float, and merged, multi-sensor Sea Surface Temperature (SST) data. In the first eddy, which is near the coast, nutrients concentration in the upper layer is low at the core but high along the periphery. In the second eddy, which is near the extension of Kuroshio, nutrients concentration along the periphery is higher than the surrounding areas. The enhancement of nutrients concentration along the peripheries is perhaps mainly due to strong vertical mixing. The distributions of dissolved oxygen, temperature, and salinity show similar patterns as the nutrients. In the peripheries, dissolved oxygen concentration is low, indicating high production induced by the high concentration of nutrients.

A preliminary study is conducted on generating the topographic map of the Subei Bank tidal flats from three Sentinel-1A SAR images acquired at different tidal levels, i.e., low, middle and high tidal levels. The derived elevations using the waterline method agree well with the in-situ measured topographic data, implying that the waterline method based on successive SAR images has the potential to monitor the topography of large-scale tidal flats.

Three RADARSAT-2 synthetic aperture radar (SAR) images in dual-polarization mode were acquired successively over Typhoon Soudelor in early August, 2015. In this work, the center locations of the typhoon were determined from SAR images using an automatic eye detection method. The derived typhoon centers are very close to that from the tropical cyclone Best Track dataset, which allows the study of the typhoon eye evolution during its movement. The change of the sea surface wind structure was also investigated based on the sea surface wind speed retrieved from the cross-polarized SAR images with a Cross-Polarization Ocean (C-2PO) model.

In this study, the radar backscatter features of the shallow water topography of Subei bank in the Southern Yellow Sea are investigated using ENVISAT (Environmental Satellite) ASAR (advanced synthetic aperture radar) images. Different bathymetric features are found on SAR imagery, which correspond to sea surface imprints of tidal channels or sand ridges, respectively. Preliminary analysis demonstrates that the ocean current and surface wind, as well as the wave breaking, play a significant role in the SAR imaging of shallow water topography in this region.

Extensive validation of altimetry measurements is of fundamental importance prior to their scientific or commercial applications. In the present study, new CryoSat-2, HY-2A, SARAL/AltiKa, Jason-2 measured Sea Surface Height (SSH) obtained from RADS (Radar Altimeter Database System) and DUACS (Data Unification and Altimeter Combination System) are cross-validated and compared with tide gauge data in China Seas. The CryoSat-2 SAR (Synthetic Aperture Radar) and LRM (Low Repetition Mode) modes are available in the Bohai Sea/Yellow Sea and East China Sea, respectively, which enables the initial evaluation of the performance of the new satellite altimetry over the regions. The results demonstrate high consistency between the new altimetry missions with a root mean square difference of 3-5 cm in SSH. Coherent SSH time series are observed from the new satellite altimetry measurements and tide gauge data. The findings are important for continuous mapping the sea level variations based on 23 years of altimetry measurements in China Seas.

Ocean surface wind retrieval from Sentinel-1SAR data is scientific and technically matured at NOAA. The SAR wind has a fairly good accuracy with a standard deviation of less than 2 m/s.

In this work, an automatic method is proposed to determine the center of tropical cyclones (TCs) from a series of RADARSAT-1 synthetic aperture radar (SAR) images, which captured TCs over the Atlantic, the Pacific and the Indian Ocean during the years from 2001 to 2007. The TC centers determined by the method are compared to the TC best track (BT) datasets provided by National Hurricane Center (NHC) of National Oceanic and Atmospheric Administration (NOAA) and Shanghai Typhoon Institute (STI) of the China Meteorological Administration (CMA). The results show a good agreement between the SAR-estimated TC center positions and the BT data, indicating that satellite SAR is a powerful tool for the study of tropical cyclone morphology and dynamics.

Several groups of atmospheric gravity waves (AGWs) were observed on a Sentinel-1A synthetic aperture radar (SAR) image acquired near the Kuril Islands in the Northwest Pacific Ocean on June 1, 2015 during the passage of an extratropical cyclone (ETC). These waves occurred on the lee side of the mountains located on the islands. Both diverging and transverse waves with wavelengths ranging between 20 and 30 km are shown as alternating bright-dark patterns in the SAR image. For the diverging waves, there exists a prominent asymmetry in the wave motions of the two arms. The Moderate Resolution Imaging Spectroradiometer and Landsat 7 Enhanced Thematic Mapper Plus images acquired 5-7 h prior to the Sentinel-1A pass also contain the same groups of AGWs. The mesoscale Weather Research and Forecasting model simulation confirms that the AGWs are lee waves triggered by the airflow over the islands. AGWs are aligned perpendicular to the wind direction and locked on the lee side of the islands. The life span of the waves is about two days, consistent with that of the ETC over the region. The numerical model also successfully reproduces the main characteristics of the lee waves. Simulation results demonstrate that the variation in the wave parameters (i.e., wavelength, amplitude, orientation, wedge angle of the diverging wave, and vertical propagation characteristic) and the wave asymmetry of the diverging wave are mainly caused by the wind and stratification changes. The smaller amplitude of the diverging wave seems to be associated with a smaller Froude number.

The assessment of altimetric data is crucial for investigating the regional sea level variability. Few works has been performed to validate the altimetric data [1, 2] in the Baltic Sea. The exploring of multi-mission altimetric data in the Baltic Sea has yet to be published. The number of available altimetric measurements increases of 96% by replacing the radiometer wet troposphere correction with model based correction. The results indicate the high quality of the along-track altimetry measurements in the semi-closed sea, which shows good agreement with tide gauge data except in the shallow waters and ice-covered regions, such as Danish Straits and the Gulf of Bothnian.

In this paper, the Ulva prolifera bloom event in the Yellow Sea in summer 2010 is investigated by MODIS (Moderate Resolution Imaging Spectroradiometer) images. We use the FAI (Floating Algae Index) method to detect the distribution of the floating macroalgae from the images. Then we apply the GNOME (General NOAA Operational Modeling Environment) model to simulate the trajectories of the Ulva prolifera in the Yellow Sea. The model results agree well with satellite observations, indicating that the occurrence and movement of the floating macroalgae can be investigated with the combination of GNOME model and satellite data.

Hurricane tangential wind profiles are routinely observed by aircraft reconnaissance in order to estimate the surface winds. However, these wind profile estimates are occasionally biased because along-track aircraft observations might not determine the nonaxisymmetric hurricane structure characteristics. In this paper, we resolve this problem by calculating the mean wind speed in all radial directions using cross-polarization SAR wide-swath images. Moreover, we propose a one-half modified Rankine vortex (OHMRV) model to describe the hurricane wind profile, particularly for those wind profiles with a wind speed maximum and an inflection point possibly associated with the degeneration of the inner wind maximum in the hurricane reintensification phase. OHMRV characterizes the hurricane wind profile and represents a model that complements the previously established single-modified Rankine vortex model and the double-modified Rankine vortex model. Moreover, the OHMRV-derived wind profiles are used to estimate hurricane intensity and structure parameters, such as the maximum wind speed and the radius of maximum wind. For validation of the method, the estimated ISPs are compared with measurements by the stepped-frequency microwave radiometer on board the National Oceanic and Atmospheric Administration aircraft. These parameters contribute to a description of hurricane inner-core intensity and structure associated with eyewall replacement cycles.

A group of submerged ocean bottom sand ridges in the Bohai Sea, China, are shown in RADARSAT-1 and ENVISAT synthetic aperture radar (SAR) images. The sand ridges appear as fingerlike quasi-linear features in the SAR images. Examining the detailed local bathymetry chart, we find that these features coincide with the satellite images. The heights of the sand ridges are less than 10 m, and the water depth is between 10 and 30 m. The spacing of the sand ridges is about 10 km, and the length of the sand ridges is about 20 km. The same sand ridges are also visible on a Moderate Resolution Imaging Spectroradiometer (MODIS) true-color image. The semidiurnal and diurnal tidal currents in this area are almost parallel to the major axis of these sand ridges. These observations cannot be explained using the existing 1-D SAR imaging model, which is not applicable to sand ridges parallel to the tidal current. In this paper, we consider the shallow-water current bathymetry in a 2-D space. An analytical ocean model was applied to demonstrate the temporal variations of the current divergence and convergence that are induced by the along-sand-ridge-direction current and ridge interaction. A radar simulation model is used to simulate the variation of normalized radar cross section (NRCS) induced by the ocean surface current. The simulated NRCS variation is similar to that extracted from the calibrated SAR image. Simulation results also show that the NRCS variation becomes negligible when the ocean current is set to about half of the maximum tidal current.