Recursive Multi-Step Forecasting of Ocean Wave Height Using Data from Oceanographic Wave Buoys
DOI:
https://doi.org/10.37278/insearch.v25i1.1521Abstract
Ocean wave fluctuations significantly impact maritime activities, coastal infrastructure, and disaster mitigation systems. However, predicting wave heights accurately remains a challenge due to the complex temporal dynamics of oceanographic data. This study proposes a recursive multi-step forecasting ap-proach using the XGBoost regression model to predict wave heights up to 30 days ahead. The dataset was obtained from wave buoys at Mooloolaba, Queensland, covering a 30-month observation period. After preprocessing and exploratory data analysis (EDA), relevant lag-based features were engineered to sup-port model learning. The XGBoost model was trained using past wave height, period, sea surface tempera-ture, and peak direction as predictive inputs. The results show that the model achieved RMSE values of 0.0851, 0.0899, and 0.0958 for step-ahead forecasts at t+1, t+2, and t+3, respectively. Visualization fur-ther confirms the model’s ability to capture wave trends consistently. These findings suggest that the pro-posed method is effective and can be utilized to support early warning systems and decision-making in coastal areas.
References
A. Halicki, A. Dudkowska, and G. Gic-Grusza, “Short-term wave forecasting for offshore wind energy in the Baltic Sea,” Ocean Eng., vol. 315, p. 119700, 2025.
L. Porlan-Ferrando, J. D. Nuñez-Gonzalez, A. Ulazia Manterola, N. Martinez-Iturricastillo, and J. V. Ringwood, “Maximum Individ-ual Wave Height Prediction Using Different Machine Learning Techniques with Data Collected from a Buoy Located in Bilbao (Bay of Biscay),” J. Mar. Sci. Eng., vol. 13, no. 4, p. 625, 2025.
Y. Xie, H. J. Kim, Y. Yin, K. Liu, T. Smith, and J. K. Paik, “Enhancing the safety and sustainability of aging jacket-type offshore wind turbines in extreme weather conditions through digital healthcare engineering: a literature review,” Ships Offshore Struct., pp. 1–28, 2025.
A. Shadmani, M. R. Nikoo, and A. H. Gandomi, Ocean Wave Energy Technology: Fundamentals of Wave Farm Design. Springer Nature, 2025.
B. J. Bethel, C. Dong, J. Wang, and Y. Cao, “An investigation of swell in the western Atlantic Ocean and Caribbean Sea,” Ocean Dyn., vol. 75, no. 5, p. 44, 2025.
C. G. Shankar and M. K. Cambazoglu, “Enhancing Storm Wave Predictions in the Gulf of Mexico: A Study on Wind Drag Parame-terization in WAVEWATCH III,” J. Mar. Sci. Eng., vol. 13, no. 3, p. 403, 2025.
M. A. Souames, L. A. Mohammedi, I. Zouaghi, A. Gunasekaran, S. Beldjoudi, and A. Laghouag, “Estimating import lead times using business intelligence and machine learning within the CRISP-DM framework: A case study in oil and gas services industry,” IEEE Access, 2025.
N. Alamsyah, A. Hendra, E. Setiana, T. P. Yoga, V. R. Danestiara, and others, “Improved Prediction Of Global Temperature Via LSTM Using ReLU Activation And Hyperparameter Optimization,” in 2024 International Conference on Information Technology Research and Innovation (ICITRI), IEEE, 2024, pp. 41–46.
J. Wang, D. Zhang, Q. Huang, and Z. Cui, “Multiple-step accurate prediction of wave energy: A hybrid model based on quadratic decomposition, SSA and LSTM,” Int. J. Green Energy, vol. 22, no. 1, pp. 100–123, 2025.
M. Sakib, S. Mustajab, and M. Alam, “Ensemble deep learning techniques for time series analysis: a comprehensive review, applica-tions, open issues, challenges, and future directions,” Clust. Comput., vol. 28, no. 1, p. 73, 2025.
J. Si, J. Wang, and Y. Deng, “Improving significant wave height prediction via temporal data imputation,” Dyn. Atmospheres Oceans, p. 101549, 2025.
S. Ozgen, A. Wu, and F. Ruiz, “Modeling approaches for data-driven model predictive control of acid gases in waste-to-energy plants,” Waste Manag., vol. 204, p. 114902, 2025.
A. R. Khan, M. S. B. Ab Razak, B. B. Yusuf, H. Z. B. M. Shafri, and N. B. Mohamad, “Harnessing artificial neural networks for coastal erosion prediction: A systematic review,” Mar. Policy, vol. 178, p. 106704, 2025.
R. S. Kumar, P. Meera, V. Lavanya, and S. Hemamalini, “Brown bear optimized random forest model for short term solar power fore-casting,” Results Eng., vol. 25, p. 104583, 2025.
Q. Yu, G. Yang, X. Wang, Y. Shi, Y. Feng, and A. Liu, “A review of time series forecasting and spatio-temporal series forecasting in deep learning,” J. Supercomput., vol. 81, no. 10, pp. 1–48, 2025.
S. Demir and E. K. Sahin, “An innovative machine learning approach for slope stability prediction by combining shap interpretabil-ity and stacking ensemble learning,” Environ. Sci. Pollut. Res., pp. 1–17, 2025.
F. Z. Che Rose, N. A. K. Rosili, and M. F. Marsani, “Comparison of machine learning model performance for predicting the climate variables in Johor Bahru, Malaysia,” Sci. Rep., vol. 15, no. 1, p. 23465, 2025.
N. Alamsyah, A. P. Kurniati, and others, “Event Detection Optimization Through Stacking Ensemble and BERT Fine-Tuning for Dynamic Pricing of Airline Tickets,” IEEE Access, 2024.
N. Alamsyah, B. Budiman, E. Setiana, V. C. Jennifer, and others, “THE ROLE OF L1 REGULARIZATION IN ENHANCING LOGISTIC REGRESSION FOR EGG PRODUCTION PREDICTION,” JITK J. Ilmu Pengetah. Dan Teknol. Komput., vol. 10, no. 4, pp. 821–832, 2025.
N. Alamsyah, B. Budiman, R. Nursyanti, E. Setiana, and V. R. Danestiara, “Approximate Bayesian Inference for Bayesian Confi-dence Quantification in DNA Sequence Classification Using Monte Carlo Dropout Approach,” Innov. Res. Inform. Innov., vol. 7, no. 1, 2025.
C. S. Alfredo, D. A. Adytia, and others, “Time series forecasting of significant wave height using GRU, CNN-GRU, and LSTM,” J. RESTI Rekayasa Sist. Dan Teknol. Inf., vol. 6, no. 5, pp. 776–781, 2022.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Nur Alamsyah, Muhammad Nizar Haikal, Arnold Ropen Sinaga, Budiman
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
