Abstract
The accurate prediction of wave height is of paramount importance in many oceanic, coastal and offshore activities. To this end, the traditional approach is the application of numerical wave prediction models with great success but also drawbacks under particular conditions. In this work, a two-step hybrid system is proposed to optimize wave height forecasts. It is based on the well-known wave model WAM, which is primarily used to obtain the simulated parameters, and the gradient boosting regression tree algorithm, which is subsequently applied to improve the wave height forecasts of the numerical model. The developed system and the underlying algorithm, use as features the information available only from the WAM model, without the need of meteorological data records from buoys or other sources. These are replaced with the WAM model simulated parameters. The predictive performance of the proposed method is evaluated in three different study areas, in order to avoid any area dependencies, and to justify the method’s applicability despite the local wave climatology. The results demonstrate that, the developed hybrid system can output more accurate wave height predictions than the original WAM forecasts, in terms of different statistical divergence metrics. In addition, the system’s predictions follow a realistic trend, in accordance with the general pattern of the real values of wave height, while the reduction of the systematic error of the WAM model is significant.
Similar content being viewed by others
Availability of data and material
The datasets analyzed during the current study are available from the corresponding author on reasonable request.
References
Ardhuin F, Rogers E, Babanin AV, Filipot JF, Magne R, Roland A, van de Westhuysen A, Queffeulou P, Lefevre JM, Aouf L, Collard F (2010) Semiempirical dissipation source functions for ocean waves. Part I: definition, calibration, and validation. J Phys Oceanogr 40(9):1917–1941
Berbić J, Ocvirk E, Carević D, Lončar G (2017) Application of neural networks and support vector machine for significant wave height prediction. Oceanologia 59(3):331–349
Bidlot JR (2012) Present status of wave forecasting at ECMWF. In: Proceedings from the ECMWF Workshop on Ocean Waves. Reading, United Kingdom
Breiman L (1996) Bias, variance, and arcing classifiers. Technical Report 460. Statistics Department, University of California, Berkeley, CA, USA
Callens A, Morichon D, Abadie S, Delpey M, Liquet B (2020) Using Random forest and Gradient boosting trees to improve wave forecast at a specific location. Appl Ocean Res 104:1–9
Chang YC, Chang KH, Wu GJ (2018) Application of eXtreme gradient boosting trees in the construction of credit risk assessment models for financial institutions. Appl Soft Comput 73:914–920
Cheng CT, Lin JY, Sun YG, Chau K (2005). Long-term prediction of discharges in Manwan Hydropower using adaptive-network-based fuzzy inference systems models. Springer, Berlin, pp 1152–1161
Den Bieman JP, Wilms JM, van den Boogaard HF, van Gent MR (2020) Prediction of mean wave overtopping discharge using gradient boosting decision trees. Water 12(6):1703
Elith J, Leathwick JR, Hastie T (2008) A working guide to boosted regression trees. J Animal Ecol 77(4):802–813
Freund Y, Schapire RE (1997) A decision-theoretic generalization of on-line learning and an application to boosting. J Comput Syst Sci 55(1):119–139
Friedman JH (2001) Greedy function approximation: a gradient boosting machine. Ann Stat 1189-1232
Friedman JH (2002) Stochastic gradient boosting. Comput Stat Data Anal 38(4):367–378
Friedman J, Hastie T, Tibshirani R (2000) Additive logistic regression: a statistical view of boosting (with discussion and a rejoinder by the authors). Ann Stat 28(2):337–407
Friedman JH, Meulman JJ (2003) Multiple additive regression trees with application in epidemiology. Stat Med 22(9):1365–1381
Galanis G (2018) Information geometry applications for optimizing numerical simulations. Math Methods Appl Sci 41(3):994–997
Galanis G, Chu PC, Kallos G (2011) Statistical post processes for the improvement of the results of numerical wave prediction models. A comb Kolmogorov Zurbenko Kalman Filters J Oper Oceanogr 4(1):23–31
Galanis G, Chu PC, Kallos G, Kuo YH, Dodson CTJ (2012) Wave height characteristics in the north Atlantic ocean: a new approach based on statistical and geometrical techniques. Stochast Environ Res Risk Assess 26(1):83–103
Galanis G, Famelis I, Liakatas A (2017a) A new Kalman filter based on Information Geometry techniques for optimizing numerical environmental simulations. Stochast Environ Res Risk Assess 31(6):1423–1435
Galanis G, Kafatos M, Chu PC, Hatzopoulos N, Papageorgiou E, Liakatas A (2017b) Operational atmospheric and wave modelling in the California‘s coastline and offshore area with applications to wave energy monitoring and assessment. J Oper Oceanogr 10(2):135–153
Galanis G, Papageorgiou E, Liakatas A (2017c) A hybrid Bayesian Kalman filter and applications to numerical wind speed modeling. J Wind Eng Ind Aerodyn 167:1–22
James SC, Zhang Y, O‘Donncha F (2018) A machine learning framework to forecast wave conditions. Coastal Eng 137:1–10
Janssen P (2004) The interaction of ocean waves and wind. Cambridge University Press, Cambridge
Joensen A, Giebel G, Landberg L, Madsen H, Nielsen HA (1999) Model output statistics applied to wind power prediction. James and James Science Publishers, London, pp 1177–1180
Khan N, Shahid S, Ismail TB, Behlil F (2021) Prediction of heat waves over Pakistan using support vector machine algorithm in the context of climate change. Stochast Environ Res Risk Assess, pp 1–19
Komen GJ, Cavaleri L, Donelan M, Hasselmann K, Hasselmann S, Janssen PAEM (1996) Dynamics and modelling of ocean waves. Cambridge University Press, Cambridge
Li M, Liu K (2020) Probabilistic prediction of significant wave height using dynamic Bayesian network and information flow. Water 12(8):2075
Mahjoobi J, Etemad-Shahidi A (2008) An alternative approach for the prediction of significant wave heights based on classification and regression trees. Appl Ocean Res 30(3):172–177
Malekmohamadi I, Bazargan-Lari MR, Kerachian R, Nikoo MR, Fallahnia M (2011) Evaluating the efficacy of SVMs, BNs, ANNs and ANFIS in wave height prediction. Ocean Eng 38(2–3):487–497
Mass CF, Ovens D, Westrick K, Colle BA (2002) Does increasing horizontal resolution produce more skillful forecasts?: The results of two years of real-time numerical weather prediction over the Pacific Northwest. Bull Am Meteorol Soc 83(3):407–430
Mosavi A, Ozturk P, Chau KW (2018) Flood prediction using machine learning models: literature review. Water 10(11):1536
Natekin A, Knoll A (2013) Gradient boosting machines, a tutorial. Front Neurorobot 7:21
Otero-Casal C, Patlakas P, Prósper MA, Galanis G, Miguez-Macho G (2019) Development of a high-resolution wind forecast system based on the WRF model and a hybrid Kalman–Bayesian filter. Energies 12(16):3050
Papayiannis GI, Galanis GN, Yannacopoulos AN (2018) Model aggregation using optimal transport and applications in wind speed forecasting. Environmetrics 29(8):e2531
Patlakas P, Drakaki E, Galanis G, Spyrou C, Kallos G (2017) Wind gust estimation by combining a numerical weather prediction model and statistical post-processing. Energy Procedia 125:190–198
Ridgeway G (2007) Generalized Boosted Models: A guide to the gbm package. http://cran.r-project.org/web/packages/gbm/index.html
Roy C, Motamedi S, Hashim R, Shamshirband S, Petković D (2016) A comparative study for estimation of wave height using traditional and hybrid soft-computing methods. Environ Earth Sci 75(7):1–12
Samadianfard S, Hashemi S, Kargar K, Izadyar M, Mostafaeipour A, Mosavi A, Nabipour N, Shamshirband S (2020) Wind speed prediction using a hybrid model of the multi-layer perceptron and whale optimization algorithm. Energy Rep 6:1147–1159
Samalot A, Astitha M, Yang J, Galanis G (2019) Combined kalman filter and universal kriging to improve storm wind speed predictions for the northeastern United States. Weather Forecast 34(3):587–601
Savitha R, Al Mamun A (2017) Regional ocean wave height prediction using sequential learning neural networks. Ocean Eng 129:605–612
Skamarock W, Klemp J, Dudhi J, Gill D, Barker D, Duda M, Huang XY, Wang W, Powers J (2008) A description of the advanced research WRF version 3. Technical Report, NCAR, Boulder
Shamshirband S, Mosavi A, Rabczuk T, Nabipour N, Chau KW (2020) Prediction of significant wave height; comparison between nested grid numerical model, and machine learning models of artificial neural networks, extreme learning and support vector machines. Eng Appl Comput Fluid Mech 14(1):805–817
Stathopoulos C, Galanis G, Bartsotas NS, Kallos G (2018) A methodology for optimizing probabilistic wind power forecasting. Adv Geosci 45:289–294
Touzani S, Granderson J, Fernandes S (2018) Gradient boosting machine for modeling the energy consumption of commercial buildings. Energy Build 158:1533–1543
Vanem E (2011) Long-term time-dependent stochastic modelling of extreme waves. Stochast Environ Res Risk Assess 25(2):185–209
Vanem E, Huseby AB, Natvig B (2012) A Bayesian hierarchical spatio-temporal model for significant wave height in the North Atlantic. Stochast Environ Res Risk Assess 26(5):609–632
WAMDIG, The WAM-Development and Implementation Group: Hasselmann, S, Hasselmann, K, Bauer, E, Bertotti L, Cardone CV, Ewing JA, Greenwood JA, Guillaume A, Janssen PAEM, Komen GJ, Lionello P, Reistad M, Zambresky L (1988) The WAM model-a third generation ocean wave prediction model. J Phys Oceanogr 18(12):1775–1810
Wang L, Li X, Bai Y (2018) Short-term wind speed prediction using an extreme learning machine model with error correction. Energy Convers Manag 162:239–250
Yang JC, Chuang HC, Kuan CM (2020) Double machine learning with gradient boosting and its application to the Big N audit quality effect. J Economet 216(1):268–283
Yang J, Yuan G (2021) Application of stochastic gradient boosting algorithm in human behavior recognition. World Sci Res J 7(1):12–20
Zhang Y, Haghani A (2015) A gradient boosting method to improve travel time prediction. Transp Res Part C Emerg Technol 58:308–324
Acknowledgements
We would like to thank the Editor and the referees for their useful comments which led to a substantial improvement in the content and the presentation of the article.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflicts of interest
The authors have no conflicts of interest or competing interests to declare.
Code availability
Available only under a signed confidential agreement.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Androulakis, E., Galanis, G. A two-step hybrid system towards optimized wave height forecasts. Stoch Environ Res Risk Assess 36, 753–766 (2022). https://doi.org/10.1007/s00477-021-02075-0
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00477-021-02075-0