Underwater Sound Speed Field Forecasting Based on the Least Square Support Vector Machine
Abstract
:1. Introduction
2. Matching Extension Method Based on EOF
- (1)
- Let measured SSPs, TPs, and SPs with full ocean depth set , , and . Each SSP, TP, and SP sample could be expressed asIf the maximum depth of the target SSP (TP, SP) to be extended is , all SSPs, TPs, and SPs in , , and are partially intercepted by depth and form a dataset of reference SSPs—, TPs and SPs , with a maximum depth that equals , where , , and can be expressed as
- (2)
- To maintain the original principal component of any target SSP (TP, SP) to be extended, the feature vectors of reference SSPs (TPs, SPs) and the target SSP are obtained through EOF. These are calculated by
- (3)
- Through the matching process, the coefficients , , and could be solved by
- (4)
- When combining , , and with , , and , the target SSP, TP, and SP with full ocean depth will be constructed:
3. Methodology for Constructing the Forecasting Model of Sound Speed Fields
3.1. Forecasting of SSFs Based on Polynomial Fitting
- (1)
- After the matching extension of SSP, the dataset of reference SSPs for SSF forecasting can be obtained as
- (2)
- The nonlinear relationship between the sound speed and the observation time at depth is constructed as
- (3)
- R-th SSPs are used to construct the SSF; the linearization matrix form of Equation (11) can be expressed as:Based on Equation (12), the error equation is constructed byAccording to the least squares,
- (4)
- When the observation time of the forecasting SSP is , the SSP at depth is calculated by
- (5)
- Repeating step (1) to step (4), the forecasting SSP of full depth can be obtained.
3.2. Forecasting of SSFs Based on BPNN
3.3. Forecasting of SSFs Based on the LSSVM
4. Results
4.1. Measured Data
4.1.1. Matching Extension of SSPs, TPs, and SPs
4.1.2. Evaluation of the Inversion Accuracy of SSF
4.2. Public Data Sources
5. Conclusions
- (1)
- The matching extension method uses EOF decomposition to perform principal component analysis for profile information, thereby achieving the profile extension in the full ocean depth. The extended profile exhibits a similar trend to the reference profile, which provides crucial reference data for constructing the SSF forecasting model for the entire ocean depth.
- (2)
- For the measured data, when the forecasting SSPs and the reference SSPs have significant consistency, the polynomial fitting algorithm has higher accuracy. However, when the forecasting SSPs and the reference SSPs have significant differences, the accuracy of the polynomial fitting algorithm is greatly reduced. When there are significant changes in the marine environment, the BPNN algorithm is better than the PF algorithm, and its forecasting accuracy is affected by the number of training samples. The RMS of the full ocean depth for the proposed LSSVM algorithm based on the observation time is 0.51 m/s, with an improvement of 37.7% and 33.2% compared to the 0.82 m/s of PF and the 0.76 m/s of BPNN. By using an improved strategy of the multi-parameter model, the improved LSSVM can further improve the accuracy of sound speed field prediction. The mean of the RMS of the full ocean depth for the improved LSSVM algorithm based on the multi-parameter model is 0.45 m/s, with an improvement of 44.6% and 40.6% compared to the 0.82 m/s of PF and the 0.76 m/s of BPNN. The above results indicate that the LSSVM considering the multi-parameter model has the highest forecasting accuracy. The reason is that the algorithm is more suitable for the training of small samples and considers multiple parameters in order to better express the sound speed.
- (3)
- For the public data, using the ability of linear least squares in high dimensional space, the LSSVM algorithm can improve the forecasting accuracy of sound speed fields by combining measured temperature, salinity, and pressure data. The mean of the RMS for LSSVM-1 is 1.35 m/s, with an improvement of 48.8% and 23.7% compared to the 2.63 m/s of PF and the 1.77 m/s of BPNN. The mean of the RMS for LSSVM-2 is 0.636 m/s, with an improvement of 75.8% and 63.9% compared to the 2.63 m/s of PF and the 1.77 m/s of BPNN. Consequently, this LSSVM considering multiple parameters can construct a high-precision sound speed field with hourly resolution, which offers sound speed corrections for underwater acoustic positioning and navigation.
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
Abbreviations
SSF | Sound Speed Field |
LSSVM | Least Square Support Vector Machine |
EOF | Empirical Orthogonal Function |
SSPs | Sound Speed Profiles |
TPs | Temperature Profiles |
SPs | Salinity Profiles |
RBF | Radial Basis Function |
CTD | Conductivity–Temperature–Depth |
XCTD | Expendable Conductivity–Temperature–Depth |
RMS | Root Mean Square |
PNTC | Positioning, navigation, timing, and communication |
SSP | Sound speed profiler |
SVD | Singular value decomposition |
PSO | Particle swarm optimization |
SA | Simulated annealing |
GA | Genetic algorithm |
References
- Yang, Y. Concept of comprehensive PNT and related key technologies. Acta Geod. Cartogr. Sin. 2016, 45, 205–510. [Google Scholar]
- Yang, Y. Resilient PNT Concept Frame. Acta Geod. Cartogr. Sin. 2018, 47, 893–898. [Google Scholar]
- Yang, Y.; Yang, C.; Ren, X. PNT intelligent services. Acta Geod. Cartogr. Sin. 2021, 50, 1006–1012. [Google Scholar]
- Xue, S.; Li, B.; Xiao, Z.; Sun, Y.; Li, J. Centimeter-level-precision seafloor geodetic positioning model with self-structured empiricasound speed profile. Satell. Navig. 2023, 4, 30. [Google Scholar] [CrossRef]
- Huang, Y.; Guo, W.S. Spatial correlation of the acoustic vector field of the surface noise in three-dimensional ocean environments. J. Acoust. Soc. Am. 2014, 135, 2397. [Google Scholar] [CrossRef]
- Worcester, P.F.; Munk, W.H. Ocean acoustic tomography: Fortieth anniversary, 1976–2016. J. Acoust. Soc. Am. 2016, 140, 2976. [Google Scholar] [CrossRef]
- Zhang, L.; Ye, S.; Zhou, S.; Liu, F.; Han, Y. Review of Measurement Techniques for Temperature, Salinity and Depth Profile of Sea Water. Mar. Sci. Bull. 2017, 36, 481–489. [Google Scholar]
- Munk, W.; Wunsch, C. Ocean acoustic tomography: A scheme for large scale monitoring. Deep-Sea Res. (Oceanogr. Res. Pap.) 1979, 26, 123–161. [Google Scholar] [CrossRef]
- Michael, B.; Peter, G. Dictionary Learning of Sound Speed Profiles. J. Acoust. Soc. Am. 2017, 141, 1749–1758. [Google Scholar]
- Tolstoy, A. Linearization of the matched-field processing approach to acoustic tomography. J. Acoust. Soc. Am. 1992, 91, 781–787. [Google Scholar] [CrossRef]
- Zhang, Z.; Ma, Y.; Yang, K.; Yan, S. Inversion for sound speed profile in shallow water using matched-beam processing. Acta Acust. 2005, 30, 103–107. (In Chinese) [Google Scholar]
- Tang, J.F.; Yang, S.E. Sound speed profile in ocean inverted by using travel time. J. Harbin Eng. Univ. 2006, 27, 734–756. (In Chinese) [Google Scholar]
- Davis, R.E. Predictability of Sea Surface Temperature and Sea Level Pressure Anomalies over the North Pacific Ocean. J. Phys. Ocean. 1976, 6, 249–266. [Google Scholar] [CrossRef]
- Bianco, M.J.; Gerstoft, P.; Traer, J.; Ozanich, E.; Roch, M.A.; Gannot, S.; Deledalle, C.A. Machine Learning in Acoustics: Theory and Applications. J. Acoust. Soc. Am. 2019, 146, 3590–3628. [Google Scholar] [CrossRef] [PubMed]
- Tolstoy, A.; Diachok, O.; Frazer, L.N. Acoustic tomography via matched field processing. J. Acoust. Soc. Am. 1991, 89, 1119–1127. [Google Scholar] [CrossRef]
- Zhang, W.X.; Gao, G.D.; Mu, G.Y. Research on modeling seawater salinity based on BP neural network. Ocean Technol. 2006, 25, 3. [Google Scholar]
- Sun, W.; Bao, J.; Jin, S.; Xiao, F.; Cui, Y. Inversion of Sound Speed Profiles by Correcting the Terrain Distortion. Geomat. Inf. Sci. Wuhan Univ. 2016, 41, 349–355. [Google Scholar]
- Michael, B.; Peter, G. Compressive Acoustic Sound Speed Profile Estimation. J. Acoust. Soc. Am. 2016, 139, EL90–EL94. [Google Scholar]
- Choo, Y.; Seong, W. Compressive Sound Speed Profile Inversion Using Beamforming Results. Remote Sens. 2018, 10, 704. [Google Scholar] [CrossRef]
- Wang, J.; Xu, T.; Nie, W.; Yu, X. The Construction of Sound Speed Field Based on Back Propagation Neural Network in the Global Ocean. Mar. Geod. 2020, 43, 1–14. [Google Scholar] [CrossRef]
- Yann, S.; Sylvie, T.; Fouad, B. Inverting Tomographic Data with Neural Nets. In Proceedings of the ‘Challenges of Our Changing Global Environment’, OCEANS ’95 MTS/IEEE, San Diego, CA, USA, 9–12 October 1995; pp. 1501–1504. [Google Scholar]
- Ai, R.F.; Cheng, J.; Ouyang, J.; Yang, J. On-line retrieval methodology for sound speed profile of sea area. J. Comput. Appl. 2015, 35, 5. [Google Scholar]
- Huang, W.; Li, D.S.; Jiang, P. Underwater Sound Speed Inversion by Joint Artificial Neural Network and Ray Theory. In Proceedings of the International Conference on Underwater Networks and Systems, Shenzhen, China, 3–5 December 2018; pp. 1–8. [Google Scholar]
- Zhang, X.; Zhang, Y.G.; Zhang, J.X.; Dong, N. A new parameterization method for sound velocity profile structure. J. Oceanogr. 2011, 33, 54–60. [Google Scholar]
- Luo, Z.H.; Lu, B.; Yang, Y. Application of Artificial Neural Network Technology in Sound Velocity Prediction for Marine Sediments. Ocean Technol. 2009, 28, 41–57. [Google Scholar]
- Liu, B.S.; Lei, J.Y. The Principles of Hydro-Acoustics, 2nd ed.; Harbin Institute of Technology Press: Harbin, China, 2011. [Google Scholar]
- Yu, X.K.; Xu, T.H.; Wang, J.T. Sound Velocity Profile Prediction Method Based on RBF Neural Network. In Proceedings of the China Satellite Navigation Conference (CSNC) 2020 Proceedings: Volume III, Chengdu, China, 22–25 November 2020; pp. 475–487. [Google Scholar]
- Ji, C.Y.; Liu, C. Model experiment of intelligent control for deep water jack-up platforms based on BP neural network. Ocean Eng. 2013, 31, 19–27. [Google Scholar]
- Cherkassky, V.; Ma, Y. Practical selection of SVM parameters and noise estimation for SVM regression. Neural Netw. 2004, 17, 113–126. [Google Scholar] [CrossRef] [PubMed]
- Suykens, J. Least Squares Support Vector Machines. Int. J. Circuit Theory Appl. 2002, 27, 605–615. [Google Scholar] [CrossRef]
- Tao, Z.D.; Wang, Y.Q.; Lu, Z.J. Study on the comparison and correction method of far-reaching sea sound velocity data. Hydrogr. Surv. Charting 2020, 40, 20–24. [Google Scholar]
Method | Statistics | Full Ocean Depth (m/s) | Surface Layer (m/s) | Thermocline (m/s) | Isothermal Layer (m/s) |
---|---|---|---|---|---|
PF | Maximum RMS | 2.19 | 2.80 | 2.07 | 2.04 |
Minimum RMS | 0.15 | 0.23 | 0.14 | 0.13 | |
Mean of RMS | 0.82 | 1.01 | 0.74 | 0.79 | |
BPNN | Maximum RMS | 1.16 | 1.40 | 1.04 | 1.27 |
Minimum RMS | 0.35 | 0.64 | 0.22 | 0.14 | |
Mean of RMS | 0.76 | 1.00 | 0.68 | 0.69 | |
LSSVM-1 | Maximum RMS | 1.05 | 1.20 | 0.91 | 1.07 |
Minimum RMS | 0.09 | 0.15 | 0.10 | 0.04 | |
Mean of RMS | 0.51 | 0.66 | 0.47 | 0.47 | |
LSSVM-2 | Maximum RMS | 1.00 | 1.14 | 0.87 | 1.01 |
Minimum RMS | 0.09 | 0.14 | 0.07 | 0.08 | |
Mean of RMS | 0.45 | 0.61 | 0.44 | 0.38 | |
Improvement percentage of LSSVM-1 relative to PF (%) | Mean of RMS | 37.7 | 34.9 | 36.0 | 40.8 |
Improvement percentage of LSSVM-2 relative to PF (%) | Mean of RMS | 44.6 | 39.8 | 41.2 | 51.4 |
Improvement percentage of LSSVM-1 relative to BPNN (%) | Mean of RMS | 33.2 | 34.1 | 30.6 | 32.3 |
Improvement percentage of LSSVM-2 relative to BPNN (%) | Mean of RMS | 40.6 | 39.1 | 36.3 | 44.4 |
Depth | Statistics | PF | BPNN | LSSVM-1 | LSSVM-2 |
---|---|---|---|---|---|
Difference of depth 50 m | Mean | −0.31 | −0.16 | −0.24 | −0.04 |
Max | 1.20 | 0.99 | 1.31 | 0.73 | |
Difference of depth 150 m | Mean | −5.45 | −0.46 | −1.90 | −0.29 |
Max | 15.43 | 59.66 | 9.90 | 7.57 | |
Difference of depth 750 m | Mean | −0.44 | 0.13 | −0.22 | −0.05 |
Max | 1.76 | 1.41 | 1.42 | 1.40 |
Method | PF | BPNN | LSSVM-1 | LSSVM-2 |
---|---|---|---|---|
Mean RMS of full ocean depth (m/s) | 2.63 | 1.77 | 1.35 | 0.64 |
Improvement percentage relative to PF (%) | - | - | 48.8 | 75.8 |
Improvement percentage relative to BPNN (%) | - | - | 23.7 | 63.9 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Wang, J.; Xu, T.; Huang, W.; Zhang, L.; Shu, J.; Liu, Y.; Li, L. Underwater Sound Speed Field Forecasting Based on the Least Square Support Vector Machine. J. Mar. Sci. Eng. 2024, 12, 480. https://doi.org/10.3390/jmse12030480
Wang J, Xu T, Huang W, Zhang L, Shu J, Liu Y, Li L. Underwater Sound Speed Field Forecasting Based on the Least Square Support Vector Machine. Journal of Marine Science and Engineering. 2024; 12(3):480. https://doi.org/10.3390/jmse12030480
Chicago/Turabian StyleWang, Junting, Tianhe Xu, Wei Huang, Liping Zhang, Jianxu Shu, Yangfan Liu, and Linyang Li. 2024. "Underwater Sound Speed Field Forecasting Based on the Least Square Support Vector Machine" Journal of Marine Science and Engineering 12, no. 3: 480. https://doi.org/10.3390/jmse12030480
APA StyleWang, J., Xu, T., Huang, W., Zhang, L., Shu, J., Liu, Y., & Li, L. (2024). Underwater Sound Speed Field Forecasting Based on the Least Square Support Vector Machine. Journal of Marine Science and Engineering, 12(3), 480. https://doi.org/10.3390/jmse12030480