Shear Wave Velocity Estimation Based on Deep-Q Network
Source abstract
Abstract
Geoacoustic inversion is important for seabed geotechnical applications. It can be formulated as a problem that seeks an optimal solution in a high-dimensional parameter space. The conventional inversion approach exploits optimization methods with a pre-defined search strategy whose hyperparameters need to be fine-tuned for a specific scenario. A framework based on the deep-Q network is proposed in this paper and the environment and agent configurations of the framework are specially defined for geoacoustic inversion. Unlike a conventional optimization method with a pre-defined search strategy, the proposed framework determines a flexible strategy by trial and error. The proposed framework is evaluated by two case studies for estimating the shear wave velocity profile. Its performance is compared with three global optimization methods commonly used in underwater geoacoustic inversion. The results demonstrate that the proposed framework performs the inversion more efficiently and accurately.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Underwater Acoustics Research · Seismic Imaging and Inversion Techniques · Underwater Vehicles and Communication Systems
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Electronic Systems, Norwegian University of Science and Technology, 7491 Trondheim, Norway
Funding
China Scholarship Council · Norwegian Research Council and the industry partners of the GAMES consortium at NTNU
References (30)
Show source-provided references
1. Bayesian inversion of interface-wave dispersion for seabed shear-wave speed profiles10.1109/JOE.2010.2100490 ↗
2. Estimation of seabed shear-wave velocity profiles using shear-wave source data10.1121/1.4809719 ↗
3. Review of Geoacoustic Inversion in Underwater Acoustics10.1142/S259172852130004X ↗
4. Comparison of performance of heuristic search methods for phase velocity inversion in shallow surface wave method10.2113/JEEG10.2.163 ↗
5. Skyberg, N.S. (2013). Study of Optimization Algorithms for Underwater Acoustic Applications. [Master’s Thesis, Institutt for Elektronikk og Telekommunikasjon, Norges teknisk-naturvitenskapelige universitet].
6. Estimation of shear wave speed in ocean-bottom sediment using electromagnetic induction source10.1109/JOE.2008.926108 ↗
7. Snellen, M., Simons, D.G., and Van Moll, C. (2004, January 5–8). Application of differential evolution as an optimisation method for geo-acoustic inversion. Proceedings of the 7th European Conference on Underwater Acoustics, Delft, The Netherlands.
8. An adaptive-hybrid algorithm for geoacoustic inversion10.1109/48.946507 ↗
9. Machine learning in acoustics: Theory and applications10.1121/1.5133944 ↗
10. Geoacoustic inversion with generalized additive models10.1121/1.5110244 ↗
11. Matched-field geoacoustic inversion based on radial basis function neural network10.1121/10.0002656 ↗
12. Seabed and range estimation of impulsive time series using a convolutional neural network10.1121/10.0001216 ↗
13. Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., and Riedmiller, M. (2013). Playing atari with deep reinforcement learning. arXiv.
14. Gu, S., Holly, E., Lillicrap, T., and Levine, S. (June, January 29). Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates. Proceedings of the 2017 IEEE international conference on robotics and automation (ICRA), Singapore.10.1109/ICRA.2017.7989385 ↗
15. Mastering the game of go without human knowledge10.1038/nature24270 ↗
16. Joo, H., and Lim, Y. (2021). Traffic Signal Time Optimization Based on Deep Q-Network. Appl. Sci., 11.10.3390/app11219850 ↗
17. Zhou, S., Liu, J., Hou, D., Zhong, X., and Zhang, Y. (2021). Autonomous penetration testing based on improved deep q-network. Appl. Sci., 11.10.3390/app11198823 ↗
18. Park, J.H., Farkhodov, K., Lee, S.H., and Kwon, K.R. (2022). Deep reinforcement learning-based DQN agent algorithm for visual object tracking in a virtual environmental simulation. Appl. Sci., 12.10.3390/app12073220 ↗
19. Gao, S.J., Li, Y.T., and Geng, T.W. (2022). Deep Reinforcement Learning-Based Relay Selection Algorithm in Free-Space Optical Cooperative Communications. Appl. Sci., 12.10.3390/app12104881 ↗
20. Guan, Z., Wang, Y., and He, M. (2022). Deep Reinforcement Learning-Based Spectrum Allocation Algorithm in Internet of Vehicles Discriminating Services. Appl. Sci., 12.10.3390/app12031764 ↗
21. Zhao, S., Wang, L., Zhao, Z., and Bi, L. (2022). Study on the Autonomous Walking of an Underground Definite Route LHD Machine Based on Reinforcement Learning. Appl. Sci., 12.10.3390/app12105052 ↗
22. Qin, Z., Zhang, X., Zhang, X., Lu, B., Liu, Z., and Guo, L. (2022). The UAV Trajectory Optimization for Data Collection from Time-Constrained IoT Devices: A Hierarchical Deep Q-Network Approach. Appl. Sci., 12.10.3390/app12052546 ↗
23. Asaf, K., Khan, B., and Kim, G.Y. (2022). Wireless Lan Performance Enhancement Using Double Deep Q-Networks. Appl. Sci., 12.10.3390/app12094145 ↗
24. Stochastic inversion of magnetotelluric data using deep reinforcement learning10.1190/geo2020-0425.1 ↗
25. Planning with Markov decision processes: An AI perspective
26. Wu, G., Dong, H., Ke, G., and Song, J. (2020). Shear-Wave Tomography Using Ocean Ambient Noise with Interference. Remote Sens., 12.10.3390/rs12182969 ↗
27. Doornbos, D.J. (1988). DISPER80: A subroutine package for the calculation of seismic normal-mode solutions. Seismological Algorithms, Academic Press.
28. Transmission of elastic waves through a stratified solid medium10.1063/1.1699629 ↗
29. The dispersion of surface waves on multilayered media10.1785/BSSA0430010017 ↗
30. Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., and Antiga, L. (2019, January 8–14). Pytorch: An imperative style, high-performance deep learning library. Proceedings of the Advances in Neural Information Processing Systems 32 (NeurIPS 2019), Vancouver, BC, Canada.