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.

This study introduces a novel approach to the critical task of submarine pipeline or cable (POC) detection by employing GoogleNet for the automatic recognition of side-scan sonar (SSS) images. The traditional interpretation methods, heavily reliant on human interpretation, are replaced with a more reliable deep-learning-based methodology. We explored the enhancement of model accuracy via transfer learning and scrutinized the influence of three distinct pre-training datasets on the model’s performance. The results indicate that GoogleNet facilitated effective identification, with accuracy and precision rates exceeding 90%. Furthermore, pre-training with the ImageNet dataset increased prediction accuracy by about 10% compared to the model without pre-training. The model’s prediction ability was best promoted by pre-training datasets in the following order: Marine-PULSE ≥ ImageNet > SeabedObjects-KLSG. Our study shows that pre-training dataset categories, dataset volume, and data consistency with predicted data are crucial factors affecting pre-training outcomes. These findings set the stage for future research on automatic pipeline detection using deep learning techniques and emphasize the significance of suitable pre-training dataset selection for CNN models.

Side-scan sonar (SSS) image classification is crucial for underwater applications, but the trade-off between the accuracy afforded by high-resolution images and the associated computational cost challenges deployment, particularly on resource-constrained platforms like AUVs. This study systematically investigates and quantifies this accuracy–efficiency trade-off in SSS image classification by varying input resolution. Using two distinct SSS datasets and a resolution-adaptive deep learning strategy employing MobileNetV2 and ResNet variants across six resolutions, we evaluated classification accuracy and computational metrics. Results demonstrate a clear inverse relationship: decreasing resolution significantly reduces computational load and processing times but lowers classification accuracy, with the degradation being more pronounced for the more complex four-class dataset. Notably, model test accuracy did not necessarily increase monotonically with resolution. Importantly, acceptable accuracy levels above 90% or 80% could be maintained at significantly lower resolutions, offering substantial efficiency gains. In conclusion, strategically reducing SSS image resolution based on application-specific accuracy requirements is a viable approach for optimizing computational resources. This work provides a quantitative framework for navigating this trade-off and underscores the need for developing SSS-specific architectures for future advancements.

Side-scan sonar (SSS) is a critical tool in marine geophysical exploration, enabling the detection of seabed structures and geological phenomena. However, the manual interpretation of SSS images is time-consuming and relies heavily on expertise, limiting its efficiency and scalability. This study addresses these challenges by employing deep learning techniques for the automatic recognition of SSS images and introducing Marine-PULSE, a specialized dataset focusing on underwater engineering structures. The dataset refines previous classifications by distinguishing four categories of objects: pipeline or cable, underwater residual mound, seabed surface, and engineering platform. A convolutional neural network (CNN) model based on GoogleNet architecture, combined with transfer learning, was applied to assess classification accuracy and the impact of data expansion. The results demonstrate a test accuracy exceeding 92%, with data expansion improving small-sample model performance by over 7%. Notably, mutual influence effects were observed between categories, with similar features enhancing classification accuracy and distinct features causing inhibitory effects. These findings highlight the importance of balanced datasets and effective data expansion strategies in overcoming data scarcity. This work establishes a robust framework for SSS image recognition, advancing applications in marine geophysical exploration and underwater object detection.

A submarine landslide is a well-known geohazard that can cause significant damage to offshore engineering facilities. Most standard predicting and mapping methods require expert knowledge, supervision, and fieldwork. In this research, the main objective was to analyze the potential of unsupervised machine learning methods and compare the performance of three different unsupervised machine learning models (k-means, spectral clustering, and hierarchical clustering) in modeling the susceptibility of the submarine landslide. Nine groups of geological factors were selected as the input parameters, which were obtained through field surveys. To estimate submarine landslide susceptibility, all input factors were separated into three or four groups based on data features and environmental variables. Finally, the goodness-of-fit and accuracy of models were validated with both internal metrics (Calinski–Harabasz index, silhouette index, and Davies–Bouldin index) and external metrics (existing landslide distribution, hydrodynamic distribution, and liquefication distribution). The findings of k-means, spectral clustering, and hierarchical clustering performed commendably and accurately in forecasting the submarine landslide susceptibility. Spectral clustering has the greatest congruence with environmental geology parameters. Therefore, the unsupervised machine learning model can be used in submarine-landslide-predicting studies, and the spectral clustering method performed best. Furthermore, machine learning can improve submarine landslide mapping in the future with the development of models and the extension of geological data related to submarine landslides.