Подход на основе машинного обучения для прогнозирования значительной высоты волны
DOI:
https://doi.org/10.26577/JMMCS.2021.v110.i2.08Ключевые слова:
Machine learning, significant wave height, Support vector regressionАннотация
Разработана система машинного обучения для оценки значительной высоты океанской волны. Значительная высота и период волны могут быть использованы при контролируемом машинном обучении для прогнозирования состояния океана. В данной работе предложен метод для прогнозирования значительной высоты волны с помощью регрессии на основе метода опорных векторов (Support vector regression – SVR). Набор данных буев взят с портала открытых данных правительства Квинсленда, входные данные с которого были объединены в наборы данных для контролируемого обучения и тестирования.
Модель SVR воспроизводила значительную высоту волны со среднеквадратической ошибкой 0,044 и выполнялась на тестовых данных с точностью 95%. По сравнению с прогнозированием значительной высоты волны на основе физической модели, для модели SVR с машинным обучением требуется значительно меньше (< 1/1200) времени вычислений.
Ключевые слова: Машинное обучение, значимая высота волны, регрессия на основе метода опорных векторов.
Библиографические ссылки
[1] FAO, The State of the World Fisheries and Aquaculture 2016. Con tributing to the food security and nutrition for all Technical Report, Food and Agriculture Organization of the United Nations (2016).
[2] I. Goodfellow, Y. Bengio, A. Courville, "Deep Learning" , MIT Press, (2016).
[3] Y. LeCun, Y. Bengio, G. Hinton, "Deep learning" , Nature 521 (2015): 436-444.
[4] J. Schmidhuber, "Deep learning in neural networks: An overview" , Neural Networks 61(2015): 85-117.
[5] K. Haas, S. Ahn, V. S. Neary, S. Bredin, "Development of a wave energy resource classification system, in: Waterpower Week" , METS, Washington, DC, 1-5.
[6] P. M. DeVries, T. B. Thompson, B. J. Meade, "Enabling large-scale viscoelastic calculations via neural network acceleration" , Geophysical Research Letters 44 (2017): 2662-2669.
[7] V. Mallet, G. Stoltz, B. Mauricette, "Ozone ensemble forecast with machine learning algorithms" , Journal of Geophysical Research: Atmospheres 114 (2009).
[8] D. Peres, C. Iuppa, L. Cavallaro, A. Cancelliere, E. Foti, "Significant wave height record extension by neural networks and reanalysis wind data" , Ocean Modelling 94 (2015): 128-140.
[9] O. Makarynskyy, "Improving wave predictions with artificial neural networks" , Ocean Engineering 31 (2004): 709-724.
[10] A. Etemad-Shahidi, J. Mahjoobi, "Comparison between M5’ model tree and neural networks for prediction of significant wave height in lake superior" , Ocean Engineering 36 (2009): 1175-1181.
[11] J. Mahjoobi, A. Etemad-Shahidi, "An alternative approach for the prediction of significant wave heights based on classification and regression trees" , Applied Ocean Research 30 (2008): 172-177.
[12] M. Browne, D. Strauss, B. Castelle, M. Blumenstein, R. Tomlinson, C. Lane, "Empirical estimation of nearshore waves from a global deep-water wave model" , IEEE Geoscience and Remote Sensing Letters 3 (2006): 462-466.
[13] M. Browne, B. Castelle, D. Strauss, R. Tomlinson, M. Blumenstein, C. Lane, "Near-shore swell estimation from a global wind-wave model: Spectral process, linear, and artificial neural network models" , Coastal Engineering 54 (2007): 445-460.
[14] The SWAN Team, SWAN Scientific and Technical Documentation Technical Report SWAN Cycle III version 40.51, Delft University of Technology (2006).
[15] G. J. Komen, L. Cavaleri, M. Donelan, "Dynamics and Modelling of Ocean Waves" , Cambridge University Press (1996).
[16] C. C. Mei, M. Stiassnie, D. K.-P. Yue, "Theory and Applications of Ocean Surface Waves: Part 1: Linear Aspects. Part 2: Nonlinear Aspects" , World Scientific (1989).
[17] Y. Song, D. Haidvogel, "A semi-implicit ocean circulation model using a generalized topography-following coordinate system" , Journal of Computational Physics 115 (1994): 228-244.
[18] J. Patterson, J. Thomas, L. Rosenfeld, J. Newton, L. Hazard, J. Scianna, R. Kudela, E. Mayorga, C. Cohen, M. Cook, et al., "Addressing ocean and coastal issues at the west coast scale through regional ocean observing system collaboration,
in: Oceans’12" , IEEE 1-8.
[19] The Weather Company The Weather Company (2017).
[20] G. Chang, K. Ruehl, C. Jones, C. C. Roberts, J. D.and Chartrand, "Numerical modeling of the effects of wave energy converter characteristics on nearshore wave conditions" , Renewable Energy 89 (2016): 636-648.
[21] F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, et al., "SciKit-Learn: Machine learning in Python" , Journal of Machine Learning Research 12 (2011):
2825-2830.
[22] Scott C James, Yushan Zhang, Fearghal O’Donncha, "See discussions, A Machine Learning Framework to Forecast Wave Conditions" , Coastal Engineering (2017): 46556-5637.
[23] N. Cesa-Bianchi, A. Conconi, C. Gentile, "On the generalization ability of on-line learning algorithms" , IEEE Transactions on Information Theory 50 (2004): 2050-2057.
[24] Queensland Government Coastal Data System - Near real time wave data, open data portal https://www.data.qld.gov.au/dataset/coastal-data-system-near-real-time-wave-data
[25] Vapnik, V. The Nature of Statistical Learning Theory (Springer, New York, 1995).
[2] I. Goodfellow, Y. Bengio, A. Courville, "Deep Learning" , MIT Press, (2016).
[3] Y. LeCun, Y. Bengio, G. Hinton, "Deep learning" , Nature 521 (2015): 436-444.
[4] J. Schmidhuber, "Deep learning in neural networks: An overview" , Neural Networks 61(2015): 85-117.
[5] K. Haas, S. Ahn, V. S. Neary, S. Bredin, "Development of a wave energy resource classification system, in: Waterpower Week" , METS, Washington, DC, 1-5.
[6] P. M. DeVries, T. B. Thompson, B. J. Meade, "Enabling large-scale viscoelastic calculations via neural network acceleration" , Geophysical Research Letters 44 (2017): 2662-2669.
[7] V. Mallet, G. Stoltz, B. Mauricette, "Ozone ensemble forecast with machine learning algorithms" , Journal of Geophysical Research: Atmospheres 114 (2009).
[8] D. Peres, C. Iuppa, L. Cavallaro, A. Cancelliere, E. Foti, "Significant wave height record extension by neural networks and reanalysis wind data" , Ocean Modelling 94 (2015): 128-140.
[9] O. Makarynskyy, "Improving wave predictions with artificial neural networks" , Ocean Engineering 31 (2004): 709-724.
[10] A. Etemad-Shahidi, J. Mahjoobi, "Comparison between M5’ model tree and neural networks for prediction of significant wave height in lake superior" , Ocean Engineering 36 (2009): 1175-1181.
[11] J. Mahjoobi, A. Etemad-Shahidi, "An alternative approach for the prediction of significant wave heights based on classification and regression trees" , Applied Ocean Research 30 (2008): 172-177.
[12] M. Browne, D. Strauss, B. Castelle, M. Blumenstein, R. Tomlinson, C. Lane, "Empirical estimation of nearshore waves from a global deep-water wave model" , IEEE Geoscience and Remote Sensing Letters 3 (2006): 462-466.
[13] M. Browne, B. Castelle, D. Strauss, R. Tomlinson, M. Blumenstein, C. Lane, "Near-shore swell estimation from a global wind-wave model: Spectral process, linear, and artificial neural network models" , Coastal Engineering 54 (2007): 445-460.
[14] The SWAN Team, SWAN Scientific and Technical Documentation Technical Report SWAN Cycle III version 40.51, Delft University of Technology (2006).
[15] G. J. Komen, L. Cavaleri, M. Donelan, "Dynamics and Modelling of Ocean Waves" , Cambridge University Press (1996).
[16] C. C. Mei, M. Stiassnie, D. K.-P. Yue, "Theory and Applications of Ocean Surface Waves: Part 1: Linear Aspects. Part 2: Nonlinear Aspects" , World Scientific (1989).
[17] Y. Song, D. Haidvogel, "A semi-implicit ocean circulation model using a generalized topography-following coordinate system" , Journal of Computational Physics 115 (1994): 228-244.
[18] J. Patterson, J. Thomas, L. Rosenfeld, J. Newton, L. Hazard, J. Scianna, R. Kudela, E. Mayorga, C. Cohen, M. Cook, et al., "Addressing ocean and coastal issues at the west coast scale through regional ocean observing system collaboration,
in: Oceans’12" , IEEE 1-8.
[19] The Weather Company The Weather Company (2017).
[20] G. Chang, K. Ruehl, C. Jones, C. C. Roberts, J. D.and Chartrand, "Numerical modeling of the effects of wave energy converter characteristics on nearshore wave conditions" , Renewable Energy 89 (2016): 636-648.
[21] F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, et al., "SciKit-Learn: Machine learning in Python" , Journal of Machine Learning Research 12 (2011):
2825-2830.
[22] Scott C James, Yushan Zhang, Fearghal O’Donncha, "See discussions, A Machine Learning Framework to Forecast Wave Conditions" , Coastal Engineering (2017): 46556-5637.
[23] N. Cesa-Bianchi, A. Conconi, C. Gentile, "On the generalization ability of on-line learning algorithms" , IEEE Transactions on Information Theory 50 (2004): 2050-2057.
[24] Queensland Government Coastal Data System - Near real time wave data, open data portal https://www.data.qld.gov.au/dataset/coastal-data-system-near-real-time-wave-data
[25] Vapnik, V. The Nature of Statistical Learning Theory (Springer, New York, 1995).
Загрузки
Опубликован
2021-09-27
Выпуск
Раздел
Информатика
