DBF-KAN: A Double Basis Function Kolmogorov–Arnold Network for Predicting Underwater Sound Speed With the Presence of Internal Waves
- 20 October 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 22 (1545598X) , 1-5
Abstract
The distribution of underwater sound speed is crucial for determining the propagation mode of underwater acoustic signals. In traditional works for predicting sound speed profiles (SSPs), attention is seldom paid to the situation under the influence of internal waves, due to the scarcity of data. However, the sound velocity under the influence of internal waves exhibits distribution characteristics at different time scales, making it difficult to be predicted by existing models, such as the long short-term memory neural network (LSTM). To address these issues, we propose a double basis function Kolmogorov–Arnold network (DBF-KAN) model for predicting sound speed distribution with the presence of internal waves in this paper. Different basis functions are used to capture features of time series at different scales. Real data experiments show that the DBF-KAN network can capture the changing characteristics of complex sound velocity fluctuations and obtain good accuracy performance.Keywords
Funding Information
- National Key Research and Development Program of China (2024YFB3909701)
- National Natural Science Foundation of China (42404001, 62271459, 42304011)
- Stable Supporting Fund of the Acoustic Science and Technology Laboratory (JCKYS2025SSJS008)
- Natural Science Foundation of Shandong Province (ZR2023QF128, ZR2023QD163)
This publication has 16 references indexed in Scilit:
- An Attention Assisted LSTM Model for Underwater Sound Speed Profile Prediction2024
- Real-time estimation of underwater sound speed profiles with a data fusion convolutional neural network modelApplied Ocean Research, 2024
- Development of High Accuracy CTD Sensor: 5EL-CTD2024
- Dynamic Prediction of Full-Ocean Depth SSP by a Hierarchical LSTM: An Experimental ResultIEEE Geoscience and Remote Sensing Letters, 2024
- Localization Algorithm for Underwater Sensor Network: A ReviewIEEE Internet of Things Journal, 2021
- Collaborating Ray Tracing and AI Model for AUV-Assisted 3-D Underwater Sound-Speed InversionIEEE Journal of Oceanic Engineering, 2021
- Dictionary learning of sound speed profilesThe Journal of the Acoustical Society of America, 2017
- Merging Multiple-Partial-Depth Data Time Series Using Objective Empirical Orthogonal Function FittingIEEE Journal of Oceanic Engineering, 2010
- Acoustic tomography via matched field processingThe Journal of the Acoustical Society of America, 1991
- Simple equations for the speed of sound in Neptunian watersThe Journal of the Acoustical Society of America, 1981