Deep neural networks (DNNs) are advantageous for representing complex nonlinear relationships. This paper applies DNNs to source localization in a shallow water environment. Two methods are proposed to estimate the range and depth of a broadband source through different neural network architectures. The first adopts the classical two-stage scheme, in which feature extraction and DNN analysis are independent steps. The eigenvectors associated with the modal signal space are extracted as the input feature. Then, the time delay neural network is exploited to model the long term feature representation and constructs the regression model. The second concerns a convolutional neural network−feed-forward neural network (CNN–FNN) architecture, which trains the network directly by taking the raw multi-channel waveforms as input. The CNNs are expected to perform spatial filtering for multi-channel signals, in an operation analogous to time domain filters. The outputs of CNNs are summed as the input to FNN. Several experiments are conducted on the simulated and experimental data to evaluate the performance of the proposed methods. The results demonstrate that DNNs are effective for source localization in complex and varied water environments, especially when there is little precise environmental information.

Deep learning based methods have achieved state-of-the-art results on the task of ship type classification. However, most existing ship type classification algorithms take time–frequency (TF) features as input, the underlying discriminative information of these features has not been explored thoroughly. This paper proposes a novel feature optimization method which is designed to minimize an objective function aimed at increasing inter-class and reducing intra-class feature distance for ship type classification. The objective function we design is able to learn a center for each class and make samples from the same class closer to the corresponding center. This ensures that the features maximize underlying discriminative information involved in the data, particularly for some targets that usually confused by the conventional manual designed feature. Results on the dataset from a real environment show that the proposed feature optimization approach outperforms traditional TF features.

Deep learning is widely used for target detection and direction-of-arrival (DOA) estimation due to its powerful data fitting capability. However, limited by different environments and number of sound sources, it is difficult to be applied to complex underwater environments. We propose a two-stage approach called Beam-Network for underwater acoustic DOA estimation. In the first stage, local beam patterns with different data augmentation methods, carrying the essential information required for target detection, are used as the input feature to our model. In the second stage, an adaptive convolutional neural network (CNN) is proposed to construct a classification model. Only single-source data are required for model training and data from multi sources can be tested. What’s more, the model is suitable for arrays with different numbers of hydrophones in different geometrical arrangements. The performance of the proposed method is evaluated by comparing with mainstream DOA estimation algorithms such as CBF, MUSIC, MVDR, and SBL. In three simulation scenarios and two sets of recorded data from different marine environments, the proposed method has higher directivity and lower angular root-mean-squared error (RMSE).

Underwater acoustic target recognition has emerged as a prominent research area within the field of underwater acoustics. However, the current availability of authentic underwater acoustic signal recordings remains limited, which hinders data-driven acoustic recognition models from learning robust patterns of targets from a limited set of intricate underwater signals, thereby compromising their stability in practical applications. To overcome these limitations, this study proposes a recognition framework called M3 (multitask, multi-gate, multi-expert) to enhance the model's ability to capture robust patterns by making it aware of the inherent properties of targets. In this framework, an auxiliary task that focuses on target properties, such as estimating target size, is designed. The auxiliary task then shares parameters with the recognition task to realize multitask learning. This paradigm allows the model to concentrate on shared information across tasks and identify robust patterns of targets in a regularized manner, thus, enhancing the model's generalization ability. Moreover, M3 incorporates multi-expert and multi-gate mechanisms, allowing for the allocation of distinct parameter spaces to various underwater signals. This enables the model to process intricate signal patterns in a fine-grained and differentiated manner. To evaluate the effectiveness of M3, extensive experiments were implemented on the ShipsEar underwater ship-radiated noise dataset. The results substantiate that M3 has the ability to outperform the most advanced single-task recognition models, thereby achieving the state-of-the-art performance.

Underwater acoustic target recognition based on passive sonar faces numerous challenges in practical maritime applications. One of the main challenges lies in the susceptibility of signal characteristics to diverse environmental conditions and data acquisition configurations, which can lead to instability in recognition systems. While significant efforts have been dedicated to addressing these influential factors in other domains of underwater acoustics, they are often neglected in the field of underwater acoustic target recognition. To overcome this limitation, this study designs auxiliary tasks that model influential factors (e.g., source range, water column depth, or wind speed) based on available annotations and adopts a multi-task framework to connect these factors to the recognition task. Furthermore, we integrate an adversarial learning mechanism into the multi-task framework to prompt the model to extract representations that are robust against influential factors. Through extensive experiments and analyses on the ShipsEar dataset, our proposed adversarial multi-task model demonstrates its capacity to effectively model the influential factors and achieve state-of-the-art performance on the 12-class recognition task.