Diffusion-based Surrogate Model for Time-varying Underwater Acoustic Channels

TL;DR

This paper introduces StableUASim, a diffusion-based surrogate model that accurately and efficiently simulates time-varying underwater acoustic channels, overcoming limitations of traditional models by providing diverse, realistic, and adaptable channel representations.

Contribution

The paper presents a novel pre-trained latent diffusion model for underwater acoustic channels that enables fast adaptation, realistic simulation, and efficient analysis, advancing the state-of-the-art in channel modeling.

Findings

StableUASim accurately reproduces key channel characteristics.

The model supports conditional generation from measurement samples.

It enables rapid adaptation with minimal additional data.

Abstract

Accurate modeling of time-varying underwater acoustic channels is essential for the design, evaluation, and deployment of reliable underwater communication systems. Conventional physics models require detailed environmental knowledge, while stochastic replay methods are constrained by the limited diversity of measured channels and often fail to generalize to unseen scenarios, reducing their practical applicability. To address these challenges, we propose StableUASim, a pre-trained conditional latent diffusion surrogate model that captures the stochastic dynamics of underwater acoustic communication channels. Leveraging generative modeling, StableUASim produces diverse and statistically realistic channel realizations, while supporting conditional generation from specific measurement samples. Pre-training enables rapid adaptation to new environments using minimal additional data, and the autoencoder latent representation facilitates efficient channel analysis and compression. Experimental results demonstrate that StableUASim accurately reproduces key channel characteristics and communication performance, providing a scalable, data-efficient, and physically consistent surrogate model for both system design and machine learning-driven underwater applications.