A hybrid forecasting model for depth-averaged current velocities of underwater gliders

Yaojian Zhou; Yonglai Zhang; Wenai Song; Shijie Liu; Baoqiang Tian

doi:10.1007/s13131-022-1994-4

Volume 41 Issue 9

Aug. 2022

Turn off MathJax

Article Contents

Article Navigation > Acta Oceanologica Sinica > 2022 > 41(9): 182-191

Yaojian Zhou, Yonglai Zhang, Wenai Song, Shijie Liu, Baoqiang Tian. A hybrid forecasting model for depth-averaged current velocities of underwater gliders[J]. Acta Oceanologica Sinica, 2022, 41(9): 182-191. doi: 10.1007/s13131-022-1994-4

Citation:

Yaojian Zhou, Yonglai Zhang, Wenai Song, Shijie Liu, Baoqiang Tian. A hybrid forecasting model for depth-averaged current velocities of underwater gliders[J]. Acta Oceanologica Sinica, 2022, 41(9): 182-191. doi: 10.1007/s13131-022-1994-4

Citation:

PDF( 793 KB)

A hybrid forecasting model for depth-averaged current velocities of underwater gliders

doi: 10.1007/s13131-022-1994-4

1.
Software School, North University of China, Taiyuan 030051, China
2.
State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China
3.
School of Mechanical Engineering, North China University of Water Resources and Electric Power, Zhengzhou 450045, China

Funds: The National Natural Science Foundation of China under contract Nos U1709202 and 51809127; the Natural Science Foundation of Shanxi Province, China under contract No. 201901D211248.

More Information

Corresponding author: E-mail: zhangyonglai@nuc.edu.cn
Received Date: 2021-08-02
Accepted Date: 2021-12-20

Available Online: 2022-04-07

Publish Date: 2022-08-31

Abstract

Abstract

In this paper, we propose a hybrid forecasting model to improve the forecasting accuracy for depth-averaged current velocities (DACVs) of underwater gliders. The hybrid model is based on a discrete wavelet transform (DWT), a deep belief network (DBN), and a least squares support vector machine (LSSVM). The original DACV series are first decomposed into several high- and one low-frequency subseries by DWT. Then, DBN is used for high-frequency component forecasting, and the LSSVM model is adopted for low-frequency subseries. The effectiveness of the proposed model is verified by two groups of DACV data from sea trials in the South China Sea. Based on four general error criteria, the forecast performance of the proposed model is demonstrated. The comparison models include some well-recognized single models and some related hybrid models. The performance of the proposed model outperformed those of the other methods indicated above.
- : underwater glider,
- hybrid forecasting model,
- depth-averaged current velocities (DACVs)

FullText(HTML)

References(43)

References

[1]	Amin J, Sharif M, Gul N, et al. 2020. Brain tumor classification based on DWT fusion of MRI sequences using convolutional neural network. Pattern Recognition Letters, 129: 115–122. doi: 10.1016/j.patrec.2019.11.016
[2]	Bengio Y. 2009. Learning Deep Architectures for AI. Hanover: Now Publishers Inc. , 49–60
[3]	Bhardwaj S, Chandrasekhar E, Padiyar P, et al. 2020. A comparative study of wavelet-based ANN and classical techniques for geophysical time-series forecasting. Computers & Geosciences, 138: 104461
[4]	Chang D, Zhang Fumin, Edwards C R. 2015. Real-time guidance of underwater gliders assisted by predictive ocean models. Journal of Atmospheric and Oceanic Technology, 32(3): 562–578. doi: 10.1175/JTECH-D-14-00098.1
[5]	Devi H S, Singh K M. 2020. Red-cyan anaglyph image watermarking using DWT, Hadamard transform and singular value decomposition for copyright protection. Journal of Information Security and Applications, 50: 102424. doi: 10.1016/j.jisa.2019.102424
[6]	Diebold F X, Mariano R S. 1995. Comparing predictive accuracy. Journal of Business & Economic Statistics, 13(3): 253–263
[7]	Eriksen C C, Osse T J, Light R D, et al. 2001. Seaglider: a long-range autonomous underwater vehicle for oceanographic research. IEEE Journal of Oceanic Engineering, 26(4): 424–436. doi: 10.1109/48.972073
[8]	Fan Rong’en, Chang Kaiwei, Hsieh C J, et al. 2008. LIBLINEAR: a library for large linear classification. The Journal of Machine Learning Research, 9: 1871–1874
[9]	Goldstein R M, Zebker H A, Barnett T P. 1989. Remote sensing of ocean currents. Science, 246(4935): 1282–1285. doi: 10.1126/science.246.4935.1282
[10]	Hinton G E, Osindero S, Teh Y W. 2006. A fast learning algorithm for deep belief nets. Neural Computation, 18(7): 1527–1554. doi: 10.1162/neco.2006.18.7.1527
[11]	Jiang Yan, Huang Guoqing, Peng Xinyan, et al. 2018. A novel wind speed prediction method: hybrid of correlation-aided DWT, LSSVM and GARCH. Journal of Wind Engineering and Industrial Aerodynamics, 174: 28–38. doi: 10.1016/j.jweia.2017.12.019
[12]	Kerfoot J, Aragon D. 2020. Long duration underwater glider dataset: Indian Ocean from Perth, Australia to Mirissa, Sri Lanka. Data in Brief, 31: 105752. doi: 10.1016/j.dib.2020.105752
[13]	Kilic A, Goyal A, Miller J K, et al. 2021. Performance of a machine learning algorithm in predicting outcomes of aortic valve replacement. The Annals of Thoracic Surgery, 111(2): 503–510. doi: 10.1016/j.athoracsur.2020.05.107
[14]	Li Shufeng, Zhang Fumin, Wang Shuxin, et al. 2020. Constructing the three-dimensional structure of an anticyclonic eddy with the optimal configuration of an underwater glider network. Applied Ocean Research, 95: 101893. doi: 10.1016/j.apor.2019.101893
[15]	Liu Qiang, Xiang Xuyu, Qin Jiaohua, et al. 2020a. Coverless steganography based on image retrieval of DenseNet features and DWT sequence mapping. Knowledge-Based Systems, 192: 105375. doi: 10.1016/j.knosys.2019.105375
[16]	Liu Zenghong, Xu Jianping, Yu Jiancheng. 2020b. Real-time quality control of data from Sea-Wing underwater glider installed with Glider Payload CTD sensor. Acta Oceanologica Sinica, 39(3): 130–140. doi: 10.1007/s13131-020-1564-6
[17]	Meng Anbo, Ge Jiafei, Yin Hao, et al. 2016. Wind speed forecasting based on wavelet packet decomposition and artificial neural networks trained by crisscross optimization algorithm. Energy Conversion and Management, 114: 75–88. doi: 10.1016/j.enconman.2016.02.013
[18]	Merckelbach L. 2016. Depth-averaged instantaneous currents in a tidally dominated shelf sea from glider observations. Biogeosciences, 13(24): 6637–6649. doi: 10.5194/bg-13-6637-2016
[19]	Merckelbach L M, Briggs R, Smeed D A, et al. 2008. Current measurements from autonomous underwater gliders. In: 2008 IEEE/OES 9th Working Conference on Current Measurement Technology. Charleston: IEEE, 61–67
[20]	Neumann G. 2014. Ocean Currents. Amsterdam: Elsevier, 1–15
[21]	Pan Yubin, Hong Rongjing, Chen Jie, et al. 2020. A hybrid DBN-SOM-PF-based prognostic approach of remaining useful life for wind turbine gearbox. Renewable Energy, 152: 138–154. doi: 10.1016/j.renene.2020.01.042
[22]	Qiu Chunhua, Mao Huanbin, Wang Yanhui, et al. 2019. An irregularly shaped warm eddy observed by Chinese underwater gliders. Journal of Oceanography, 75(2): 139–148. doi: 10.1007/s10872-018-0490-0
[23]	Qiu Chunhua, Mao Huabin, Yu Jiancheng, et al. 2015. Sea surface cooling in the northern South China Sea observed using Chinese sea-wing underwater glider measurements. Deep-Sea Research Part I: Oceanographic Research Papers, 105: 111–118. doi: 10.1016/j.dsr.2015.08.009
[24]	Qiu Xueheng, Ren Ye, Suganthan P N, et al. 2017. Empirical mode decomposition based ensemble deep learning for load demand time series forecasting. Applied Soft Computing, 54: 246–255. doi: 10.1016/j.asoc.2017.01.015
[25]	Rudnick D L. 2016. Ocean research enabled by underwater gliders. Annual Review of Marine Science, 8: 519–541. doi: 10.1146/annurev-marine-122414-033913
[26]	Rudnick D L, Sherman J T, Wu A P. 2018. Depth-average velocity from spray underwater gliders. Journal of Atmospheric and Oceanic Technology, 35(8): 1665–1673. doi: 10.1175/JTECH-D-17-0200.1
[27]	Sherman J, Davis R E, Owens W B, et al. 2001. The autonomous underwater glider “spray”. IEEE Journal of Oceanic Engineering, 26(4): 437–446. doi: 10.1109/48.972076
[28]	Shi Zhigang, Bai Yuting, Jin Xuebo, et al. 2021. Parallel deep prediction with covariance intersection fusion on non-stationary time series. Knowledge-Based Systems, 211: 106523. doi: 10.1016/j.knosys.2020.106523
[29]	Song Jingjing, Wang Jianzhou, Lu Haiyan. 2018. A novel combined model based on advanced optimization algorithm for short-term wind speed forecasting. Applied Energy, 215: 643–658. doi: 10.1016/j.apenergy.2018.02.070
[30]	Su Yanwen, Huang Guoqing, Xu Youlin. 2015. Derivation of time-varying mean for non-stationary downburst winds. Journal of Wind Engineering and Industrial Aerodynamics, 141: 39–48. doi: 10.1016/j.jweia.2015.02.008
[31]	Sun Jie, Hu Feng, Jin Wenming, et al. 2020. Model-aided localization and navigation for underwater gliders using single-beacon travel-time differences. Sensors, 20(3): 893. doi: 10.3390/s20030893
[32]	Sun Xiaochuan, Li Tao, Li Qun, et al. 2017. Deep belief echo-state network and its application to time series prediction. Knowledge-Based Systems, 130: 17–29. doi: 10.1016/j.knosys.2017.05.022
[33]	Talagala T S, Hyndman R J, Athanasopoulos G. 2018. Meta-learning how to forecast time series. Caulfield: Monash University
[34]	Wang Lihua. 2017. Radial basis functions methods for boundary value problems: performance comparison. Engineering Analysis with Boundary Elements, 84: 191–205. doi: 10.1016/j.enganabound.2017.08.019
[35]	Wang Wenchuan, Chau K W, Xu Dongmei, et al. 2015. Improving forecasting accuracy of annual runoff time series using ARIMA based on EEMD decomposition. Water Resources Management, 29(8): 2655–2675. doi: 10.1007/s11269-015-0962-6
[36]	Wang Ping, Hao Wenbang, Jin Yinli. 2021. Fine-grained traffic flow prediction of various vehicle types via fusion of multisource data and deep learning approaches. IEEE Transactions on Intelligent Transportation Systems, 22(11): 6921–6930. doi: 10.1109/TITS.2020.2997412
[37]	Wang Jianzhou, Wu Chunying, Niu Tong. 2019. A novel system for wind speed forecasting based on multi-objective optimization and echo state network. Sustainability, 11(2): 526. doi: 10.3390/su11020526
[38]	Webb D C, Simonetti P J, Jones C P. 2001. SLOCUM: an underwater glider propelled by environmental energy. IEEE Journal of Oceanic Engineering, 26(4): 447–452. doi: 10.1109/48.972077
[39]	Yang Zhongshan, Wang Jian. 2018. A hybrid forecasting approach applied in wind speed forecasting based on a data processing strategy and an optimized artificial intelligence algorithm. Energy, 160: 87–100. doi: 10.1016/j.energy.2018.07.005
[40]	Zeiden K L, Rudnick D L, MacKinnon J A. 2019. Glider observations of a mesoscale oceanic island wake. Journal of Physical Oceanography, 49(9): 2217–2235. doi: 10.1175/JPO-D-18-0233.1
[41]	Zhang Haoran, Wang Xiaodong. 2006. Incremental and online learning algorithm for regression least squares support vector machine. Chinese Journal of Computers, 29(3): 400–406
[42]	Zhang Jinliang, Wei Yiming, Tan Zhongfu. 2020. An adaptive hybrid model for short term wind speed forecasting. Energy, 190: 115615. doi: 10.1016/j.energy.2019.06.132
[43]	Zhou Yaojian, Yu Jiancheng, Wang Xiaohui. 2017. Time series prediction methods for depth-averaged current velocities of underwater gliders. IEEE Access, 5: 5773–5784. doi: 10.1109/ACCESS.2017.2689037