With the development of deep learning techniques, convolutional neural networks (CNN) are increasingly being used in image recognition for marine surveys and underwater object classification. Automatic recognition of targets on side-scan sonar (SSS) images using CNN can improve recognition accuracy and efficiency. However, the vast selection of CNN models makes it challenging to select models for target recognition in SSS images. Therefore, this paper aims to compare different CNN models’ prediction accuracy and computational performance comprehensively. First, four traditional CNN models were applied to train and predict the same submarine SSS dataset using both the original model and models with transfer learning methods. Then, we examined and studied the prediction accuracy and computation performance of four CNN models. Results showed that transfer learning enhances the accuracy of all CNN models, with lesser improvements for AlexNet and VGG-16 and greater improvements for GoogleNet and ResNet101. GoogleNet has the highest prediction of accuracy (100% in the train dataset and 94.27% in the test dataset) and good computational difficulty. The findings of this work are useful for future model selection in target recognition in SSS images.

The satellite altimetry missions could measure high-accuracy sea surface heights (SSHs) that can be used to recover the marine gravity field. Traditional methods for estimating the marine gravity field from SSHs all rely on approximate physical correlations between SSHs and gravity, which may neglect nature’s complex nonlinearity. This work presents a new deep network-based method to recover the gravity anomaly. This new method uses a multi-channel convolutional neural network (MCCNN) architecture to capture the nolinear features between ship-borne gravity and a group of input parameters including deflections of the vertical (DOVs), submarine topography and the geo-locations. To validate the gravity, ship-borne gravity anomalies on the two independent cruises were not used in the deep learning process. For comparison, we also estimated the gravity using the traditional inverse Vening Meinesz (IVM) method. Our results indicate that the MCCNN method can derive high-quality marine gravity anomalies. The assessments using 1 mGal-accuracy ship-borne gravity anomalies show that the average accuracy for gravity from MCCNN method is higher than 3 mGal and this method achieves 0.05-0.50 mGal improvement over benchmark methods IVM. Assessed by marine gravity anomaly models with the accuracy of 1-2 mGal, the MCCNN method has shown to improve the accuracy of gravity by at least 4%. Comparisons with the IVM results show that improvements of the MCCNN method were mainly in wavelengths between 8 km and 100 km due to the using of bathymetry. The results show that our deep learning method maintains good performance and is promising for gravity recovering.

Scientometric reviews, facilitated by computational and visual analytical approaches, allow researchers to gain a thorough understanding of research trends and areas of concentration from a large number of publications. With the fast development of satellite altimetry, which has been effectively applied to a wide range of research topics, it is timely to summarize the scientific achievements of the previous 50 years and identify future trends in this field. A comprehensive overview of satellite altimetry was presented using a total of 8541 publications from the Web of Science Core Collection covering the years from 1970 to 2021. We begin by presenting the fundamental statistical results of the publications, such as the annual number of papers, study categories, countries/regions, afflictions, journals, authors, and keywords, in order to provide a comprehensive picture of satellite altimetry research. We discuss the co-occurrence of the authors in order to reveal the global collaboration network of satellite altimetry research. Finally, we utilised co-citation networks to detect the development trend and associated crucial publications for various specific topics. The findings show that satellite altimetry research has been changed immensely during the last half-century. The United States, France, China, England, and Germany made the most significant contributions in the field of satellite altimetry. The analysis reveals a clear link between technology advancements and the trend in satellite altimetry research. As a result, wide swath altimetry, GNSS-reflectometry, laser altimetry, terrestrial hydrology, and deep learning are among the most frontier study subjects. The findings of this work could guide a thorough understanding of satellite altimetry’s overall development and research front.

The topography of the seafloor is highly correlated with the local gravity through intrinsically nonlinear relationships across a particular wavelength band. The purpose of this study is to compare a fully connected deep neural network (FC-DNN) and a convolutional neural network (CNN) with the gravity-geologic method (GGM) to determine whether deep learning can provide superior predictions of bathymetry. We include the short-wavelength gravity and geological models as training parameters, and assess the performance of different models and parameter combinations using various inputs. Compared with the CNN method, the FC-DNN with the short-wavelength gravity as an input reduces the standard deviation of bathymetry differences from 118.6 m to about 73.5 m. The FC-DNN with short-wavelength gravity reduces the standard deviation of bathymetry differences by up to 13.3% compared with the conventional GGM. Furthermore, we demonstrate that the addition of geological information alongside the short-wavelength gravity does not significantly enhance the accuracy. Power spectral density analysis suggests that the FC-DNN is superior for predicting wavelengths shorter than 6 km.

Based on the nonlinear relationship between multi-source marine geodetic data and seafloor topography, the multilayer perceptron (MLP) neural network is introduced into bathymetry prediction to improve the accuracy of bathymetry model. This method not only integrates multi-source marine geodetic data, but also takes into consideration the nonlinear relationships between these data and seafloor topography. Firstly, we utilize terrain information and the multi-source marine geodetic data (vertical deflection, gravity anomaly, vertical gravity gradient, mean dynamic topography) around the shipborne sounding control points within a 6’×6’ grid as input data, while using the actual bathymetry at control points as output data to train the MLP neural network model. Subsequently, inputting the input data from the central point of a 1’×1’ grid within the study area into the MLP model to predict the bathymetry at the grid’s center. Then, based on the predicted bathymetry, a bathymetry model is established of this research area. Utilizing this methodology, this paper establishes the Gulf of Mexico Bathymetric Chart of the Oceans (MBCO1) model. Due to the influence of complex seafloor topography and the distribution of shipborne bathymetry points, there are differences in training and prediction among different regions. To address this, this study divides the research area into five sub-regions (A, B, C, D, and E) and establishes bathymetry model (MBCO2 models) through each sub-region. Finally, we evaluated the accuracy and effectiveness of this method by comparing it with existing bathymetry models, as well as shipboard depths.

Calibration/Validation (Cal/Val) of satellite altimeters is fundamental for monitoring onboard sensor performance and ensuring long-term data quality. As altimeter technology has been evolving rapidly from profile to wide swath and interferometric altimetry, different requirements regarding Cal/Val have emerged. Most current Cal/Val technology has been developed for conventional profile altimeters, whereby satellite observations are compared against measurements at one point along orbit lines. However, the application of this type of Cal/Val technique to swath interferometric altimeters with two-dimensional measurements is difficult. Here, we propose a new strategy for the evaluation of interferometric altimeters based on comparison of wave-induced sea surface elevation (WSSE) spectra from one- and two-dimensional measurements. This method assumes that the WSSE variance of an equilibrium wave field is uniform and can be measured equivalently in the space or time domains. The method was first tested with simulated data and then used to evaluate the performance of an airborne interferometric radar altimeter system (AIRAS) using Global Navigation Satellite System (GNSS) buoy measurements. The differences between the WSSE variances from the AIRAS and two GNSS buoys were below 8 cm², corresponding to a standard deviation of 2.8 cm, which could serve as a reference for the WSSE error over the scale range of waves. The correlation coefficient between the AIRAS and GNSS buoys was approximately 0.90, indicating that the error was small relative to the WSSE signals. In addition, the sea surface height (SSH) difference measured by the AIRAS was compared with that derived from the GNSS buoys at two sites. The results indicated that the error of the SSH difference was 3 cm. This approach represents a possible technique for the Cal/Val of future spaceborne/airborne interferometric altimeters; however, additional experiments and applications are needed to verify the feasibility of this method.