In this paper, the acoustic field excited by multipole sources in a fluid-filled borehole surrounded by a transversely isotropic elastic solid is systematically analyzed and numerically simulated. Not only have the mode waves been analyzed thoroughly, but the propagation mechanism of the critical refracted P and S waves corresponding to the multipole branch cut integration for the transversely isotropic formation has also been investigated for the first time. In the presence of a fast or a slow transversely isotropic elastic solid formation, the component waves excited by a monopole, a dipole, and a quadrupole source have been studied in the time and frequency domains. It is found that the critical refracted arrival of the S wave is a dominant factor, while the mode wave is not in the low-frequency multipole direct shear wave logging. When the formation is changed from isotropic to transversely isotropic, the amplitudes of the component waves vary significantly, but the variation of the cutoff frequencies of the mode waves and the resonant frequencies of the P and S waves is less pronounced.

Underwater source localization is an important task, especially for real-time operation. Recently, machine learning methods have been combined with supervised learning schemes. This opens new possibilities for underwater source localization. However, in many real scenarios, the number of labeled datasets is insufficient for purely supervised learning, and the training time of a deep neural network can be huge. To mitigate the problem related to the low number of labeled datasets available, we propose a two-step framework for underwater source localization based on the semi-supervised learning scheme. The first step utilizes a convolutional autoencoder to extract the latent features from the whole available dataset. The second step performs source localization via an encoder multi-layer perceptron trained on a limited labeled portion of the dataset. To reduce the training time, an interpretable feature selection (FS) method based on principal component regression is proposed, which can extract important features for underwater source localization by only introducing the source location without other prior information. The proposed approach is validated on the public dataset SWellEx-96 Event S5. The results show that the framework has appealing accuracy and robustness on the unseen data, especially when the number of data used to train gradually decreases. After FS, not only the training stage has a 95% acceleration but the performance of the framework becomes more robust on the receiver-depth selection and more accurate when the number of labeled data used to train is extremely limited.

We propose a time-frequency fused underwater acoustic source localization method based on self-supervised learning with contrastive predictive coding. Firstly, two feature extractors are trained to solve the pretext task (predicting the future) based on the unlabeled acoustic signals in the time and frequency domains, respectively. Next, encoders with frozen parameters are taken from the trained feature extractors for extracting the high-level features in the time and frequency domains. During the training stage of the source localizer, features extracted by two encoders are concatenated together as a time-frequency fused feature vector and fed into a 3-layer multi-layer perceptron for solving the downstream task (source localization) based on a tiny labeled dataset. This method is assessed on the SWellEx-96 Experiment and compared with several alternative methods. The performance analysis confirms the promising performance of our proposed method.

No abstract

No abstract