Physics-Constrained Deep Neural Networks for Short-Term 3-D Flow Field Prediction Using Coastal Acoustic Tomography
- 29 April 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 64 (01962892) , 4206513
Abstract
Accurate prediction of three-dimensional (3-D) ocean flow fields is essential for understanding small-scale dynamic processes, improving environmental monitoring, and enhancing the performance of underwater observation and operation sys-tems. However, predictive modeling using coastal acoustic to-mography (CAT) data remains relatively unexplored. This study proposes a novel physics-constrained deep learning framework, termed PC-LSTM-MLP, to achieve the short-term prediction of 3-D ocean flow fields from CAT observations. The framework consists of three integrated components: a long short-term memory (LSTM) network for capturing temporal dependencies in range-averaged currents (RACs), a multilayer perceptron (MLP) for nonlinear mapping to spatial Fourier coefficients, and a physics-constrained (PC) module that imposes a horizontal incompressibility constraint to enhance the accuracy of the predicted 3-D flow fields. Experimental results on real CAT data demonstrate that the proposed PC-LSTM-MLP framework effec-tively captures complex spatiotemporal dynamics and provides accurate predictions up to 25 minutes ahead. The model achieves an average mean absolute error (MAE) of 0.0241 m/s and an average root mean square error (RMSE) of 0.0269 m/s in 3-D flow field prediction. This research shifts CAT analysis from traditional inversion methods to intelligent, prediction-oriented modeling, underscoring the significant potential of deep learning in ocean flow field prediction.Keywords
Funding Information
- National Natural Science Foundation of China (52071293)
- Qiushi Eagle Program of Zhejiang University
- Citrus Research and Development Foundation (RDF-24-02-085)
This publication has 29 references indexed in Scilit:
- Accurate tidal prediction based on empirical mode decomposition-enhanced multilayer perceptronOcean Engineering, 2025
- Multi-layer flow field mapping in a small-scale shallow water reservoir by coastal acoustic tomographyJournal of Hydrology, 2022
- Mapping of tidal current and associated nonlinear currents in the Xiangshan Bay by coastal acoustic tomographyOcean Dynamics, 2021
- A reciprocal acoustic transmission experiment for precise observations of tidal currents in a shallow seaOcean Engineering, 2021
- Revisiting a coastal acoustic tomography experiment in Hiroshima Bay: Temporal variations in path-averaged currents and its relation to windApplied Ocean Research, 2020
- Inversion on a Vertical Slice2020
- Inversion on a Horizontal Slice2020
- Observing Internal Solitary Waves in the Lombok Strait by Coastal Acoustic TomographyGeophysical Research Letters, 2019
- Long-term measurement of stream flow and salinity in a tidal river by the use of the fluvial acoustic tomography systemJournal of Hydrology, 2010
- Computer Simulation of Coastal Acoustic Tomography by a Two-Dimensional Vortex ModelJournal of Oceanography, 2001