Due to the high cost of sea trials and the variability of sea states, the duration of experiments is usually too short to fully verify underwater acoustic communication (UAC) performance in a real-ocean environment. Moreover, traditional UAC channel simulators also face issues of inaccurate environmental parameters or mismatched statistical models. To tackle these challenges, we propose UACC-GAN, a data-driven stochastic channel simulator for UAC, offering an innovative solution for channel data augmentation. UACC-GAN uses the generative adversarial network model to learn the latent space of the measured channel data set and then maps the random sampling points in this space into a new time-varying impulse response (TVIR). Our simulator is validated using the small-scale WATERMARK data set collected at sea. The results indicate that the generated TVIR has a realistic delay–Doppler spread and can reproduce time-varying delay path characteristics. The cumulative distribution of multiple 0-D properties also proves the realism of the entire distribution of the generated channel data set. In addition, by relying on the continuity of the latent space, UACC-GAN generates channel characteristics with random fluctuations, such as Doppler spectrum shape, delay energy distribution, and tap covariance, which contributes to more diverse communication testing conditions. Finally, we pass frequency-hopping spread spectrum and orthogonal frequency-division multiplexing communication signals through the generated and measured channels. The comparable results of simulated bit error rate (BER) and actual BER underline the value of the UACC-GAN simulator for communication system design and testing.

The underwater acoustic (UWA) communication system faces challenges due to environmental factors, extensive multipath spread, and rapidly changing propagation conditions. Deep learning based solutions, especially for orthogonal frequency division multiplexing (OFDM) receivers, have been shown to improve performance. However, the UWA channel characteristics are highly dynamic and depend on the specific underwater conditions. Therefore, these models suffer from model mismatch when deployed in environments different from those used for training, leading to performance degradation and requiring costly, time-consuming retraining. To address these issues, we propose a transfer learning (TL)-based pre-trained model for OFDM based UWA communication. Rather than training separate models for each underwater channel, we aggregate received signals from five distinct WATERMARK channels, across varying signal to noise ratios (SNRs), into a unified dataset. This diverse training set enables the model to generalize across various underwater conditions, ensuring robust performance without extensive retraining. We evaluate the pre-trained model using real-world data from Qingdao Lake in Hangzhou, China, which serves as the target environment. Our experiments show that the model adapts well to these challenging environment, overcoming model mismatch and minimizing computational costs. The proposed TL-based OFDM receiver outperforms traditional methods in terms of bit error rate (BER) and other evaluation metrics. It demonstrates strong adaptability to varying channel conditions. This includes scenarios where training and testing occur on the same channel, under channel mismatch, and with or without fine-tuning on target data. At 10 dB SNR, it achieves an approximately 80% improvement in BER compared to other methods.

Traditional Underwater Acoustic Communication (UAC) typically assumes static or slowly varying channels over short observation periods and models multipath amplitude fluctuations with single-state statistical distributions. However, field measurements in shallow-water high-speed mobile scenarios reveal that the combined effects of rapid platform motion and dynamic environments induce multi-scale time-varying amplitude characteristics. These include distance-dependent attenuation, fluctuations in average energy, and rapid random variations. This observation directly challenges traditional single-state models and wide-sense stationary assumptions. To address this, we propose a multi-scale time-varying multipath amplitude model. Using singular spectrum analysis, we decompose amplitude sequences into hierarchical components: large-scale components modeled via acoustic propagation physics; medium-scale components characterized by Hidden Markov Models; and small-scale components described by zero-mean Gaussian distributions. Building on this model, we further develop a time-varying impulse response simulation framework validated with experimental data. The results demonstrate superior performance over conventional single-state distribution and autoregressive models in statistical distribution matching, temporal dynamics representation, and communication performance testing. The model effectively characterizes non-stationary time-varying channels, supporting high-precision modeling and simulation for mobile UAC systems.

Due to the influence of underwater acoustic multipath channel and lack of prior information, the likelihood-based MPSK modulation identification method is facing great challenges. Therefore, we proposed an identification method combining the orthogonal matching pursuit (OMP) and expectation maximization (EM) in single input and multiple output (SIMO) underwater acoustic channel. First, the blind channel is estimated and equalized by the OMP. Then, the EM is used to compensate the recovered constellation. Finally, the likelihood-based method is applied to identify the MPSK modulation. Numerical results show the proposed method can achieve more than 95% identification rate while the SNR is higher than 7 dB.

Underwater acoustical communication (UAC) systems typically presume limited platform mobility, with insufficient attention to challenging high-speed mobile (HSM) scenarios. However, its importance is expected to increase with the rapid development of highly maneuverable autonomousunderwater vehicles. Knowledge of HSM-UAC channels is a prerequisite for ensuring reliable communication links. This study conducts two shallow-water channel measurements with speeds up to 15 knots, involving both variable-speed and constant-speed horizontal motion. Measured time-varying impulse responses clearly reveal time-varying, multiscale, multilag (TV-MSML) phenomena. Based on these findings, we propose a TV-MSML channel model and use geometric acoustics theory and BELLHOP simulation to explain the observed phenomena and validate the model. We further analyze the time-varying behavior of multipath parameters, such as path delay, residual Doppler factor, and amplitude, and evaluate the applicability of conventional statistical distribution models in HSM scenarios. The nonstationary behavior of HSM-UAC channels is examined through frequency-selective fading, multipath birth–death processes, and spatiotemporal correlation. We designed a local stationarity distance metric using the temporal power correlation coefficient and compared various property parameters with static environments. This work alleviates the lack of measured data and characteristic studies on HSM-UAC channels, highlights the TV-MSML phenomena and high dynamism in HSM scenarios, and offers valuable insights for designing and optimizing mobile UAC systems.