Continuous forecasting of range-dependent ocean sound speed field: Diffusion model meets multi-output Gaussian process
- 1 May 2026
- journal article
- Published by Acoustical Society of America (ASA) in The Journal of the Acoustical Society of America
- Vol. 159 (5) , 4204-4222
Abstract
Environment-aware underwater acoustic detection and communication require precise forecasting of the range-dependent sound speed field (SSF) at any given time. Recently, methods such as Gaussian process regression (GPR) and conditional diffusion models have shown advanced performance in SSF forecasting. However, limitations remain: standard GPR fails to capture the range-depth spatial correlations, and conditional diffusion models struggle with continuous forecasting. To address these issues, we integrate multi-output GPR and conditional diffusion models to enable continuous forecasting of range-dependent SSFs, employing careful designs for diffusion noise, neural architecture, and training strategies. Our experiments, conducted on HYCOM hindcast datasets from the South China Sea, demonstrate that our proposed model outperforms state-of-the-art baselines in forecasting range-dependent SSFs at any given time and the associated underwater transmission losses.Keywords
Funding Information
- Zhejiang Provincial Natural Science Foundation of China (LR26F010004)
- National Natural Science Foundation of China (62371418)
- Fundamental Research Funds for the Central Universities (226-2025-00168)
This publication has 12 references indexed in Scilit:
- Bayesian optimization with Gaussian process surrogate model for source localizationThe Journal of the Acoustical Society of America, 2023
- Inversion in an uncertain ocean using Gaussian processesThe Journal of the Acoustical Society of America, 2023
- Seabed classification and source localization with Gaussian processes and machine learningJASA Express Letters, 2022
- Matched field source localization with Gaussian processesJASA Express Letters, 2021
- Remarks on multi-output Gaussian process regressionKnowledge-Based Systems, 2018
- A Two-Stage Approach for the Estimation of Doubly Spread Acoustic ChannelsIEEE Journal of Oceanic Engineering, 2014
- Tracking of time-evolving sound speed profiles in shallow water using an ensemble Kalman-particle filterThe Journal of the Acoustical Society of America, 2013
- Inversion for Time-Evolving Sound-Speed Field in a Shallow Ocean by Ensemble Kalman FilteringIEEE Journal of Oceanic Engineering, 2009
- The ubiquitous Kronecker productJournal of Computational and Applied Mathematics, 2000
- Bidirectional recurrent neural networksIEEE Transactions on Signal Processing, 1997