Journal of Korean Society of Coastal and Ocean Engineers (한국해안·해양공학회논문집)

Korean Society of Coastal and Ocean Engineers (한국해안·해양공학회)
권호 표지
DOI QR코드

DOI QR Code

Estimation of the Input Wave Height of the Wave Generator for Regular Waves by Using Artificial Neural Networks and Gaussian Process Regression

인공신경망과 가우시안 과정 회귀에 의한 규칙파의 조파기 입력파고 추정

  • Jung-Eun, Oh (Maritime ICT R&D Center, Korea Institute of Ocean Science and Technology) ;
  • Sang-Ho, Oh (Department of Civil Engineering, School of Smart and Green Technology, Changwon National University)
  • 오정은 (한국해양과학기술원 해양ICT융합연구센터) ;
  • 오상호 (창원대학교 스마트그린공학부 건설시스템공학전공)
  • Received : 2022.12.08
  • Accepted : 2022.12.21
  • Published : 2022.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

The experimental data obtained in a wave flume were analyzed using machine learning techniques to establish a model that predicts the input wave height of the wavemaker based on the waves that have experienced wave shoaling and to verify the performance of the established model. For this purpose, artificial neural network (NN), the most representative machine learning technique, and Gaussian process regression (GPR), one of the non-parametric regression analysis methods, were applied respectively. Then, the predictive performance of the two models was compared. The analysis was performed independently for the case of using all the data at once and for the case by classifying the data with a criterion related to the occurrence of wave breaking. When the data were not classified, the error between the input wave height at the wavemaker and the measured value was relatively large for both the NN and GPR models. On the other hand, if the data were divided into non-breaking and breaking conditions, the accuracy of predicting the input wave height was greatly improved. Among the two models, the overall performance of the GPR model was better than that of the NN model.

2차원 조파수조 내에서 취득된 규칙파 실험데이터를 머신러닝 기법으로 분석하여 천수 변형을 경험한 파랑으로부터 조파기의 입력파고를 예측하는 모델을 수립하고 그 성능을 검증하였다. 이를 위해 가장 대표적인 머신러닝 기법인 인공신경망(NN)과 비모수 회귀분석 방법 중 하나인 가우시안 과정 회귀(GPR) 모델을 각각 수립하고 두 모델의 예측 성능을 비교하였다. 전체 실험자료를 모두 한꺼번에 활용한 경우와 쇄파 발생 여부에 따라 자료를 구분한 경우에 대해 독립적으로 분석을 수행하였다. 데이터를 구분하지 않은 경우에는 NN 및 GPR 모델 모두 조파기 입력파고 값과 계측값 사이의 오차가 비교적 크게 나타났다. 반면에 데이터를 비쇄파 및 쇄파 조건으로 구분하면 조파기 입력파고의 예측 정확도가 크게 향상되었다. 두 모델 중에서는 NN 모델보다 GPR 모델의 성능이 전반적으로 더 우수한 것으로 나타났다.

Keywords

Acknowledgement

이 논문은 2021~2022년도 창원대학교 자율연구과제 연구비 지원으로 수행된 연구결과이며, 이에 감사드립니다.

References

  1. Abiodun, O.I., Jantan, A., Omolara, A.E., Dada, K.V., Mohamed, N.A. and Arshad, H. (2018). State-of-the-art in artificial neural network applications: A survey. Heliyon, 4(11), e00938.
  2. Beuzen, T., Goldstein, E.B. and Splinter, K.D. (2019). Ensemble models from machine learning: an example of wave runup and coastal dune erosion. Natural Hazards and Earth System Sciences, 19(10), 2295-2309. https://doi.org/10.5194/nhess-19-2295-2019
  3. da Silva, S. (2018). Data-driven model identification of guided wave propagation in composite structures. Journal of the Brazilian Society of Mechanical Sciences and Engineering, 40(11), 1-10. https://doi.org/10.1007/s40430-017-0921-7
  4. den Bieman, J.P., van Gent, M.R. and van den Boogaard, H.F. (2021). Wave overtopping predictions using an advanced machine learning technique. Coastal Engineering, 166, 103830.
  5. Formentin, S.M. and Zanuttigh, B. (2019). A genetic programming based formula for wave overtopping by crown walls and bullnoses. Coastal Engineering, 152, 103529.
  6. Goda, Y. (2010). Reanalysis of regular and random breaking wave statistics. Coastal Engineering Journal, 52(1), 71-106. https://doi.org/10.1142/S0578563410002129
  7. James, S.C., Zhang, Y. and O'Donncha, F. (2018). A machine learning framework to forecast wave conditions. Coastal Engineering, 137, 1-10. https://doi.org/10.1016/j.coastaleng.2018.03.004
  8. Jordan, M.I. and Mitchell, T.M. (2015). Machine learning: Trends, perspectives, and prospects. Science, 349(6245), 255-260. https://doi.org/10.1126/science.aaa8415
  9. Kamath, A., Vargas-Hernandez, R.A., Krems, R.V., Carrington Jr, T. and Manzhos, S. (2018). Neural networks vs Gaussian process regression for representing potential energy surfaces: A comparative study of fit quality and vibrational spectrum accuracy. The Journal of Chemical Physics, 148(24), 241702.
  10. Kim, H.G., Park, E., Jeong, J., Han, W.S. and Kim, K.-Y. (2016). Groundwater level trend analysis for long-term prediction based on Gaussian process regression. Journal of Soil and Groundwater Environment, 21(4), 30-41 (in Korean). https://doi.org/10.7857/JSGE.2016.21.4.030
  11. Kim, J., Kim, T., Oh, S.-H., Do, K., Ryu, J.-G. and Kim, J. (2021). Deep visual domain adaptation and semi-supervised segmentation for understanding wave elevation using wave flume video images. Scientific Reports, 11, 21776.
  12. Knudde, N., Raes, W., De Bruycker, J., Dhaene, T. and Stevens, N. (2020). Data-efficient gaussian process regression for accurate visible light positioning. IEEE Communications Letters, 24(8), 1705-1709. https://doi.org/10.1109/lcomm.2020.2990950
  13. Lee, J.S. and Suh, K.D. (2016). Calculation of stability number of tetrapods using weights and biases of ANN model. Journal of Korean Society of Coastal and Ocean Engineers, 28(5), 277-283 (in Korean). https://doi.org/10.9765/KSCOE.2016.28.5.277
  14. Lee, K.-H., Kim, T.-G. and Kim, D.-S. (2020). Prediction of wave breaking using machine learning open source platform. Journal of Korean Society of Coastal and Ocean Engineers, 32(4), 262- 272 (in Korean). https://doi.org/10.9765/KSCOE.2020.32.4.262
  15. Oh, S.-H. and Lee, D.S. (2018). Two-dimensional wave flume with water circulating system for controlling water level. Journal of Korean Society of Coastal and Ocean Engineers, 30(6), 337-342 (in Korean). https://doi.org/10.9765/KSCOE.2018.30.6.337
  16. Rasmussen, C.E and Williams, C.K. (2006). Gaussian processes for machine learning, MIT press, Cambridge, Massachusetts.
  17. Stringari, C.E., Guimaraes, P.V., Filipot, J.F., Leckler, F. and Duarte, R. (2021). Deep neural networks for active wave breaking classification. Scientific Reports, 11(1), 1-12. https://doi.org/10.1038/s41598-020-79139-8