WAVE HEIGHT PREDICTION WITH GRADIENT BOOSTING: CASE STUDY IN JAMAICA BAY, NEW YORK

Hoda El Safty, Michael Ibrahim

Abstract


This study introduces a machine learning framework for forecasting wave heights in back- barrier bays using meteorological inputs, specifically wind and pressure data. A high-resolution coupled hydrodynamic-wave model, driven by local weather station data and ERA5 reanalysis, produced a 40-year (1980-2019) hindcast of wave heights in Jamaica Bay, New York. After validation and bias correction using field measurements, the model output was used to train a CatBoost model. Comparative analysis at two locations showed that machine learning predictions closely matched numerical model results while reducing computational cost. The machine learning model achieved slightly Root Mean Square Errors (RMSE) and Mean Absolute Errors (MAE) values, with RMSEs of 0.065 m and 0.11 m, and MAEs of 0.045 m and 0.08 m. To demonstrate practical application, a two-week hourly forecast was generated using GFS weather input. This study highlights the potential of machine learning as a fast, accurate, and efficient tool for wave height forecasting in data-scarce coastal environments. 

Keywords


Boosting trees, CatBoost model, Coupled ADCIRC + SWAN, Wind Wave Forecast, Back Barrier Bay, Jamaica Bay.

Full Text:

PDF

References


Smith, Stuart D. (1988). “Coefficients for Sea Surface Wind Stress, Heat Flux, and Wind Profiles as a Function of Wind Speed and Temperature.” Journal of Geophysical Research: Oceans 93, no. C12 (1988): 15,467-15,482. https://doi.org/10.1029/JC093iC12p15467.

Drennan, W. M., K. K. Kahma, and M. A. Donelan. 1999. “On Momentum Flux and Velocity Spectra over Waves.” Boundary-Layer Meteorology 92 (1999): 489-515. https://doi.org/10.1023/A:1002054820455.

Reidenbach, M. A., J. R. Koseff, and M. A. Koehl. 2009. “Hydrodynamic Forces on Larvae Affect Their Settlement on Coral Reefs in Turbulent, Wave-driven Flow.” Limnology and Oceanography 54, no. 1 (2009): 318-330. https://doi.org/10.4319/lo.2009.54.1.0318.

Heij, C., and S. Knapp. 2014. “Effects of Wind Strength and Wave Height on Ship Incident Risk: Regional Trends and Seasonality.” Econometric Institute Research Papers (2014). 10.13140/RG.2.1.1946.6407.

Reguero, B. G., Iñigo J. Losada, and F. J. Méndez. 2019. “A Recent Increase in Global Wave Power as a Consequence of Oceanic Warming.” Nature Communications 10, no. 1 (2019): 1-14. https://doi.org/10.1038/s41467-018-08066-0.

Fan, S., N. Xiao, and S. Dong. 2020. “A Novel Model to Predict Significant Wave Height Based on Long Short-Term Memory Network.” Ocean Engineering 205 (2020): 107298. https://doi.org/10.1016/j.oceaneng.2020.107298.

Drennan, Kaloop, M. R., D. Kumar, F. Zarzoura, B. Roy, and J. W. Hu. 2020. “A Wavelet-Particle Swarm Optimization Extreme Learning Machine Hybrid Modeling for Significant Wave Height Prediction.” Ocean Engineering 213 (2020). https://doi.org/10.1016/j.oceaneng.2020.107777.

Guan, X. 2020. “Wave Height Prediction Based on CNN-LSTM.” In Proceedings of the 2nd International Conference on Machine Learning, Big Data and Business Intelligence (MLBDBI), 10-17, 2020. 10.1109/MLBDBI51377.2020.00009.

Pushpam, P. M., and V. S. Enigo. 2020. “Forecasting Significant Wave Height Using RNN-LSTM Models.” In Proceedings of the 4th International Conference on Intelligent Computing and Control Systems (ICICCS), Vol. 2020, 1141-1146. 10.1109/ICICCS48265.2020.9121040.

Zhou, S., W. Xie, Y. Lu, Y. Wang, Y. Zhou, N. Hui, and C. Dong. 2021. “ConvLSTM-Based Wave Forecasts in the South and East China Seas.” Frontiers in Marine Science 8 (2021): 680079. https://doi.org/10.3389/fmars.2021.680079.

Feng, Z., P. Hu, S. Li, and D. Mo. 2022. “Prediction of Significant Wave Height in Offshore China Based on the Machine Learning Method.” Journal of Marine Science and Engineering 6 (2022): 10. https://doi.org/10.3390/jmse10060836.

Hu, H., and P. Chu. 2021. “Predicting Lake Erie Wave Heights and Periods Using XGBoost and LSTM.” Ocean Modelling 164 (2021). https://doi.org/10.1016/j.ocemod.2021.101832.

Marsooli, R., P. M. Orton, J. Fitzpatrick, and H. Smith. 2018. “Residence Time of a Highly Urbanized Estuary.” Journal of Marine Science and Engineering 6 (2018). https://doi.org/10.3390/jmse6020044.

Marsooli, R., P. M. Orton, and G. Mellor. 2017. “Modeling Wave Attenuation by Salt Marshes in Jamaica Bay Using a New Rapid Wave Model.” Journal of Geophysical Research: Oceans 122 (2017): 5,689-5,707. https://doi.org/10.1002/2016JC012546.

Dietrich, J. C., M. Zijlema, J. J. Westerink, L. H. Holthuijsen, C. Dawson, R. A. Luettich, W.-G. Stone, and others. 2011. “Modeling Hurricane Waves and Storm Surge Using Integrally-Coupled, Scalable Computations.” Coastal Engineering 58, no. 1 (2011): 45-65. https://doi.org/10.1016/j.coastaleng.2010.08.001.

Etemad-Shahidi, A., and J. Mahjoobi. 2009. “Comparison between M5j Model Tree and Neural Networks for Prediction of Significant Wave Height in Lake Superior.” Ocean Engineering 36 (2009): 1175-1181. https://doi.org/10.1016/j.oceaneng.2009.08.008.

Marsooli, R., and N. Lin. 2020. “Impacts of Climate Change on Hurricane Flood Hazards in Jamaica Bay.” Climatic Change 163, no. 4 (2020): 2153-2171. 10.1007/s10584-020-02932-x.

Safty, H. E., & Marsooli, R. (2020). “Ship Wakes and Their Potential Impacts on Salt Marshes in Jamaica Bay, New York.” Journal of Marine Science and Engineering 2020. Vol. 8, Page 325, 8(5), 325 (2020). doi:10.3390/JMSE8050325.

Chant, R. J., D. K. Ralston, N. K. Ganju, C. Pianca, A. E. Simonson, and R. A. Cartwright. 2021. “Sediment Budget Estimates for a Highly Impacted Embayment with Extensive Wetland Loss.” Estuaries and Coasts 44, no. 3 (2021): 608-626. 10.1007/s12237-020-00784-3.

Petropoulos, F., D. Apiletti, V. Assimakopoulos, M. Z. Babai, D. K. Barrow, S. B. Taieb, and Ziel. “Forecasting: Theory and Practice.” International Journal of Forecasting 38, no. 3: 705-871. https://doi.org/10.1016/j.ijforecast.2021.11.001.

Makridakis, S., and M. Hibon. 2000. “The M3-Competition: Results, Conclusions and Implications.” International Journal of Forecasting 16, no. 4 (2000): 451-476. https://doi.org/10.1016/S0169-2070(00)00057-1.

Freund, Y., and R. E. Schapire. 1997. “A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting.” Journal of Computer and System Sciences 55, no. 1 (1997): 119-139. https://doi.org/10.1006/jcss.1997.1504.

Friedman, J. H. 2001. “Greedy Function Approximation: A Gradient Boosting Machine.” Annals of Statistics 29 (2001): 1189-1232. 10.1214/aos/1013203451.

Chen, T., and C. Guestrin. 2016. “XGBoost: A Scalable Tree Boosting System.” Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (2016): 785-794. https://doi.org/10.1145/2939672.2939785.

Dorogush, A. V., V. Ershov, and A. G. Yandex. 2018. “CatBoost: Gradient Boosting with Categorical Features Support.” https://doi.org/10.48550/arXiv.1810.11363.

Mohaghegh, F., M. R. Alam, and J. Murthy. 2021. “Rapid Phase-Resolved Prediction of Nonlinear Dispersive Waves Using Machine Learning.” Applied Ocean Research 117 (2021). https://doi.org/10.1016/j.apor.2021.102634.

Scott, C., Y. James, Zhang, O. Fearghal. “A Machine Learning Framework to Forecast Wave Conditions.” Journal of Coastal Engineering (2017). https://doi.org/10.1016/j.coastaleng.2018.03.004.

Wang, W., R. Tang, C. Li, P. Liu, and L. Luo. 2018. “A BP Neural Network Model Optimized by Mind Evolutionary Algorithm for Predicting the Ocean Wave Heights.” Ocean Engineering 162 (2018): 98-107. https://doi.org/10.1016/j.oceaneng.2018.02.025.




DOI: https://dx.doi.org/10.21622/MARLOG.2026.15.1.80

Refbacks

  • There are currently no refbacks.


Copyright (c) 2026 Hoda El Safty, Michael Ibrahim

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

The International Maritime Transport and Logistics Journal (MARLOG)

E-ISSN: 2974-3141
P-ISSN: 2974-3133

Published by:

Academy Publishing Center (APC)

Arab Academy for Science, Technology and Maritime Transport (AASTMT)

Alexandria, Egypt