Duan Jie, Zhao Hangfang, Song Jinbao
College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, Zhejiang 310027, China.
Interdisciplinary Student Training Platform for Marine Areas, Zhejiang University, Zhoushan, Zhejiang 316021, China.
J Acoust Soc Am. 2024 May 1;155(5):3306-3321. doi: 10.1121/10.0026025.
Practical acoustic propagation modeling is significantly affected by ocean dynamics, and then can be exploited in numerous oceanic applications, where "practical" refers to modeling acoustic propagation in simulations that mimic real-world ocean environments. Physics-based numerical models provide approximate solutions of wave equation and rely on accurate prior environmental knowledge while the environment of practical scenarios is largely unknown. In contrast, data-driven machine learning offers a promising avenue to estimate practical acoustic propagation by learning from dataset. However, collecting such a high-quality, noise-free, and dense dataset remains challenging. Under the practical hurdle posed by the above approaches, the emergence of physics-informed neural network (PINN) presents an alternative to integrate physics and data but with limited representation capacity. In this work, a framework, termed spatial domain decomposition-based physics-informed neural networks (SPINNs), is proposed to enhance the representation capacity in spatially dependent oceanic scenarios and effectively learn from incomplete and biased prior physics and noisy dataset. Experiments demonstrate SPINNs' advantages over PINN in practical acoustic propagation estimation. The learning capacity of SPINNs toward physics and dataset during training is further analyzed. This work holds promise for practical applications and future expansion.
实际声学传播建模受到海洋动力学的显著影响，进而可应用于众多海洋领域，其中“实际”是指在模拟真实海洋环境的仿真中对声学传播进行建模。基于物理的数值模型提供波动方程的近似解，并依赖准确的先验环境知识，而实际场景中的环境很大程度上是未知的。相比之下，数据驱动的机器学习通过从数据集中学习，为估计实际声学传播提供了一条有前景的途径。然而，收集这样一个高质量、无噪声且密集的数据集仍然具有挑战性。在上述方法带来的实际障碍下，物理信息神经网络（PINN）的出现提供了一种整合物理和数据的替代方法，但表示能力有限。在这项工作中，提出了一种名为基于空间域分解的物理信息神经网络（SPINNs）的框架，以增强在空间相关海洋场景中的表示能力，并有效地从不完整和有偏差的先验物理以及有噪声的数据集中学习。实验证明了SPINNs在实际声学传播估计方面优于PINN。进一步分析了SPINNs在训练过程中对物理和数据集的学习能力。这项工作在实际应用和未来扩展方面具有前景。
