When a feed-forward neural network (FNN) is trained for acoustic source ranging in an ocean waveguide, it is difficult evaluating the FNN ranging accuracy of unlabeled test data. The label is the distance between source and receiver array. A fitting-based early stopping (FEAST) method is introduced to evaluate the FNN ranging error on test data where the distance to the source is unknown. Based on FEAST, when the evaluated ranging error is minimum on test data, training is stopped. This will improve the FNN ranging accuracy on the test data. The FEAST is demonstrated on simulated and experimental data.

A U-Net is trained to recover acoustic interference striations (AISs) from distorted ones. A random mode-coupling matrix model is introduced to generate a large number of training data quickly, which are used to train the U-Net. The performance of AIS recovery of the U-Net is tested in range-dependent waveguides with nonlinear internal waves (NLIWs). Although the random mode-coupling matrix model is not an accurate physical model, the test results show that the U-Net successfully recovers AISs under different signal-to-noise ratios and different amplitudes and widths of NLIWs for different shapes.

The received low frequency signals in the long range shallow water will suffer severe attenuation and modal dispersion effect, which will distort the signal and deteriorate the communication performance. In this letter, a modal dispersion compensation receiver is proposed, which exploits the de-dispersion transform to compensate intra-mode dispersion and the rake combination to combine the multi-mode components. With the proposed receiver, the waveform expansion of high order modes is compensated, and thus more modes can be distinguished from the noise and the rake combination gain is improved, which leads to high communication accuracy. Simulation results show that the proposed receiver can achieve about 3 dB gain for the 40 km range and signal with a center frequency 400 Hz.

The backscattered travel-time structure is obtained by cross-correlating air-acoustic ocean surf noise recorded on microphone pairs (separation ∼2 m) on the beach. The scatterer is a 20 cm radius Polyvinyl chloride pipe 2.5 m landside of the microphone array. Arrivals corresponding to the time-difference (travel-time difference between two scatterer-receiver paths) and scattered (travel time for receiver-scatterer-receiver path) waves emerge in the cross-correlation functions in a backscattering configuration. Theoretically, only a microphone pair is needed to locate the scatterer using the time-difference and scattered travel times. Localization of the scatterer is demonstrated with the microphone array on the beach.

In the shallow-water waveguide environment, the tonal signals radiated by moving targets carry modal interference and Doppler shift information. The modal interference can be used to obtain the time of the closest point of approach ($t_{CPA}$) and the ratio of the range at the closest point of approach to the velocity of the source ($r_{CPA}/v$). However, parameters $r_{CPA}$ and v cannot be solved separately. When $t_{CPA}$ is known, the $r_{CPA}$ and the v of the target can be obtained theoretically by using the Doppler information. However, when the Doppler frequency shift is small or at a low signal-to-noise ratio, there will be a strong parametric coupling between $r_{CPA}$ and v. In order to solve the above parameter coupling problem, a target motion parameter estimation method from tonal signals with a single hydrophone is proposed in this paper. The method uses the Doppler and modal interference information carried by the tonal signals to obtain two different parametric coupling curves. Then, the parametric coupling curves can be used to estimate the two motion parameters. Simulation experiments verified the rationality of this method. The proposed method was applied to the SWellEx-96 and speedboat experiments, and the estimation errors of the motion parameters were within 10%, which shows the method is effective in its practical applications.

When there appears the relative motion between the sound source and the receiver, the received tonal signal will produce Doppler shift, and the Doppler information is relevant to the motion parameters of the target. According to the acoustic Doppler shift frequency, we propose the Doppler-warping transformation. The phase linearization of the Doppler signal can be realized by using the transformation. Then, we deduce the warping operator and propose an algorithm for estimating the target motion parameters by using the proposed transformation. Firstly, the Doppler-warping operator under different motion parameters is constructed. Secondly, the time resampling of the received time-domain signal is performed by using the operator. Then, the spectral function of the transformed signal is calculated. Finally, the spectral function entropy is minimized to estimate the objective parameter. The simulation results show the effectiveness of the proposed method. For a low signal-to-noise ratio of sea trial data, where the real speed of a fishing boat is 4.5 m/s, the result from the traditional minimum mean square error (MMSE) velocity estimation method is 5.2 m/s, and the estimation error is 15.56%. The proposed Doppler-warping transform method can estimate the target velocity more accurately, specifically, it is 4.7 m/s and its corresponding estimation error is 4.44%.