تعیین ارتفاع موج شاخص در بندر انزلی با بکارگیری روش‌های مبتنی بر هوش‌مصنوعی (GEP, SVM) و مقایسه نتایج با مدل سوان

نوع مقاله : مقاله پژوهشی

نویسندگان

دانشکده مهندسی عمران، دانشگاه تبریز، تبریز، ایران

چکیده

ارتفاع موج شاخص در طراحی و تحلیل سازه‌های دریایی و بهره برداری از آنها پارامتر بسیار با اهمیتی می‌باشد در نتیجه پیش‌بینی این پارامتر کمک شایانی به بهبود طراحی و آنالیز سازه‌های دریایی می‌نماید. مدل‌ها و روش‌های متعددی برای پیش‌بینی ارتفاع موج شاخص از جمله روش‌های تجربی، نیمه تجربی و عددی ابداع شده است. در پژوهش حاضر، مدل سوان برای آب‌های کم عمق و نیمه عمیق ساحلی توسعه داده شده است. داده‌های سرعت باد به‌عنوان ورودی مدل‌ها در نظر گرفته شده است. برای محاسبه و پیش‌بینی ارتفاع موج شاخص، سه مدل سوان، مدل ماشین بردار پشتیبان و مدل برنامه‌نویسی بیان ژن در منطقه انزلی به‌کار گرفته شده است. بدین منظور از اطلاعات میدانی باد و موج ثبت شده بویه انزلی در بازه زمانی مشخصی استفاده گردیده است. پس از اجرای مدلها و رسم نمودارهای مربوطه، میزان خطای هر مدل محاسبه شده است. با توجه به معیارهای آماری ارزیابی نتیجه گرفته شد که روند کلی ارتفاع موج شاخص حاصل از هر سه مدل با مقادیر واقعی ثبت شده بویه تطابق قابل‌قبولی دارند. همچنین دو مدل ماشین بردار پشتیبان و مدل برنامه‌نویسی بیان ژن توانستند با دقت بالایی ارتفاع موج شاخص را پیش‌بینی نمایند. مقایسه نتایج حاصل از مدل‌ها نشان داد که مدل ماشین بردار پشتیبان با توجه به شاخص‌های آماری (Bias = 0.13)، (RSME = 0.198)، (CC = 0.981) و (CV = 0.147) نسبت به مدل برنامه‌نویسی بیان ژن، با دقت بیشتری پارامتر هدف را تخمین زده است. هر دو مدل در شبیه‌سازی مقادیر اوج دقت کمتری داشته‌اند.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Determining Significant Wave Height in Anzali Port Using Artificial Intelligence-Based Methods (GEP, SVM) and Comparing the Results with SWAN Model

نویسندگان [English]

  • Mohammad Ali Lotfollahi Yaghin
  • Alireza Mojtahedi
  • Ata Aghayi
  • Milad Mahmoudi
Faculty of Civil Engineering, Tabriz University, Tabriz, Iran
چکیده [English]

The significant wave height is a highly important parameter in the design, analysis, and operation of marine structures. Therefore, predicting this parameter significantly contributes to improving the design and analysis of marine structures. Numerous models and methods, including empirical, semi-empirical, and numerical approaches, have been developed to predict significant wave height. In the present study, the SWAN model has been developed for shallow and semi-deep coastal waters. Wind speed data were used as input for the models. To calculate and predict significant wave height, three models including SWAN, Support Vector Machine (SVM), and Gene Expression Programming (GEP) were applied in the Anzali region. For this purpose, field data on wind and waves recorded by the Anzali buoy over a specific time period were utilized. After running the models and plotting the relevant graphs, the error rates of each model were calculated. Based on statistical evaluation criteria, it was concluded that the overall trend of significant wave height predicted by all three models shows acceptable agreement with the actual values recorded by the buoy. Additionally, both the Support Vector Machine and Gene Expression Programming models were able to predict significant wave height with high accuracy. A comparison of the results from the models revealed that the Support Vector Machine model, with statistical indices (Bias = 0.13, RMSE = 0.198, CC = 0.981, and CV = 0.147), estimated the target parameter more accurately than the Gene Expression Programming model. However, both models showed lower accuracy in simulating peak values.

کلیدواژه‌ها [English]

  • Significant wave height
  • Anzali port
  • Gene expression programming model
  • Support vector mechine model
  • SWAN numerical model

مراجع

[1] Yang, Lisitai, Enrique Rodriguez Quinones, Evan B. Yao, Qiufeng Lin, Zepei Tang, and Yang Deng. "Making waves: Harnessing stormwater for resilient water supply-A blueprint for vulnerable continental coasts and oceanic islands." Water Research 268 (2025): 122593.
[2] Dodet, Guillaume, Angélique Melet, Fabrice Ardhuin, Xavier Bertin, Déborah Idier, and Rafael Almar. "The contribution of wind-generated waves to coastal sea-level changes." Surveys in Geophysics 40, no. 6 (2019): 1563-1601.
[3] Oladejo, Hafeez O., Diana N. Bernstein, M. Kemal Cambazoglu, Dmitri Nechaev, Ali Abdolali, and Jerry D. Wiggert. "Wind forcing, source term and grid optimization for hurricane wave modelling in the Gulf of Mexico." Coastal Engineering 197 (2025): 104692.
[4] Diez, Matteo, Andrea Serani, Emilio F. Campana, and Frederick Stern. "Time-series forecasting of ships maneuvering in waves via dynamic mode decomposition." Journal of Ocean Engineering and Marine Energy 8, no. 4 (2022): 471-478.
[5] Dionísio António, Sara, Jebbe van der Werf, Erik Horstman, Iván Cáceres, José Alsina, Joep van der Zanden, and Suzanne Hulscher. "Influence of beach slope on morphological changes and sediment transport under irregular waves." Journal of marine science and engineering 11, no. 12 (2023): 2244.
[6] Ahn, Seongho, Trung Duc Tran, and Jongho Kim. "Systematization of short-term forecasts of regional wave heights using a machine learning technique and long-term wave hindcast." Ocean Engineering 264 (2022): 112593.
[7] Alday, Matias, Fabrice Ardhuin, Guillaume Dodet, and Mickael Accensi. "Accuracy of numerical wave model results: Application to the Atlantic coasts of Europe." Ocean Science 18, no. 6 (2022): 1665-1689.
[8] Umesh, P. A., and Manasa R. Behera. "On the improvements in nearshore wave height predictions using nested SWAN-SWASH modelling in the eastern coastal waters of India." Ocean Engineering 236 (2021): 109550.
[9] Li, Guigeng, Hao Zhang, Tingting Lyu, and Huaifeng Zhang. "Regional significant wave height forecast in the East China Sea based on the Self-Attention ConvLSTM with SWAN model." Ocean Engineering 312 (2024): 119064.
[10] Hu, Xiaonong, Genshen Fang, and Yaojun Ge. "Simplified models of wind-wave relationships in China's shallow-water coasts based on SWAN+ ADCIRC simulations." Ocean Engineering 305 (2024): 117983.
[11] Peláez-Rodríguez, C., J. Pérez-Aracil, A. M. Gomez-Orellana, D. Guijo-Rubio, V. M. Vargas, P. Antonio Gutiérrez, C. Hervás-Martínez, and S. Salcedo-Sanz. "Fuzzy-based ensemble methodology for accurate long-term prediction and interpretation of extreme significant wave height events." Applied Ocean Research 153 (2024): 104273.
[12] Reisi-Dehkordi, Ashkan, Alireza Tavakkoli, and Frederick C. Harris Jr. "Integrating LSTM and EEMD methods to improve significant wave height prediction." In International Conference on Information Technology-New Generations, pp. 19-25. Cham: Springer International Publishing, 2023.
[13] Abbas, Muhammad, Zhaoyi Min, Zhongying Liu, and Duanjin Zhang. "Unravelling oceanic wave patterns: A comparative study of machine learning approaches for predicting significant wave height." Applied Ocean Research 145 (2024): 103919.
[14] Afzal, Mohammad Saud, Lalit Kumar, Vikram Chugh, Yogesh Kumar, and Mohd Zuhair. "Prediction of significant wave height using machine learning and its application to extreme wave analysis." Journal of Earth System Science 132, no. 2 (2023): 51.
[15] Su, Zuohang, Hailong Chen, and Can Yang. "Hybrid framework of deep extreme learning machine (DELM) based on sparrow search algorithm for non-stationary wave prediction." Ocean Engineering 311 (2024): 118993.
[16] Yang, Can, Qingchen Kong, Zuohang Su, Hailong Chen, and Lars Johanning. "A hybrid model based on chaos particle swarm optimization for significant wave height prediction." Ocean Modelling 195 (2025): 102511.
[17] Cavaleri, Luigi, Sabique Langodan, Paolo Pezzutto, and Alvise Benetazzo. "The earliest stages of wind wave generation in the open sea." Journal of Physical Oceanography 54, no. 3 (2024): 755-766.
[18] Luo, Min, Abbas Khayyer, and Pengzhi Lin. "Particle Methods in Ocean and Coastal Engineering." Applied Ocean Research 114 (2021): 102734.
[19] Kessali, N., M. Bouhamadouche, and Y. Hemdane. "Near-shore and Regional Validation of the WAVEWATCH III and SWAN wave models through in situ and satellite observations in the Barcelona Bay and Algerian Coast." Russian Meteorology and Hydrology 48, no. 3 (2023): 267-279.
[20] Lakshmi, Potharlanka Jhansi, Rubén Apaza Apaza, Ahmed Alkhayyat, Haydar Abdulameer Marhoon, and Ameer A. Alameri. "Hybrid wavelet-gene expression programming and wavelet-support vector machine models for rainfall-runoff modeling." Water Science & Technology 86, no. 12 (2022): 3205-3222.
[21] Zijlema, Marcel, Gerbrant P. van Vledder, Leo H. Holthuijsen, Jane E. Salmon, and P.B. Smit "SWAN and Its Recent Developments." Proceedings of the 13th International Workshop on Wave Hindcasting and Forecasting and 4th coastal hazards symposium, 27 Oct–1 Nov, 2013, Banff, Canada.
[22] Ferreira, Candida. "Gene expression programming: a new adaptive algorithm for solving problems." arXiv preprint cs/0102027 (2001).
[23] Kaiser, Júlia, Izabel CM Nogueira, Ricardo M. Campos, Carlos E. Parente, Renato P. Martins, and Wellington C. Belo. "Evaluation of wave model performance in the South Atlantic Ocean: a study about physical parameterization and wind forcing calibration." Ocean Dynamics 72, no. 2 (2022): 137-150.
[24] Samiksha, S. V., Lincy Jancy, K. Sudheesh, V. Sanil Kumar, and P. R. Shanas. "Evaluation of wave growth and bottom friction parameterization schemes in the SWAN based on wave modelling for the central west coast of India." Ocean Engineering 235 (2021): 109356.
[25] Van der Westhuysen, Andre J. "Modeling of depth-induced wave breaking under finite depth wave growth conditions." Journal of Geophysical Research: Oceans 115 (C1) (2010): C02008.
[26] Allahdadi, Mohammad Nabi, Ruoying He, and Vincent S. Neary. "Predicting ocean waves along the US east coast during energetic winter storms: Sensitivity to whitecapping parameterizations." Ocean Science 15, no. 3 (2019): 691-715.
 
مدل سازی در مهندسی
دوره 23، شماره 83
دی 1404
صفحه 133-144

فایل ها

سابقه مقاله

  • تاریخ دریافت: 20 آذر 1403
  • تاریخ بازنگری: 29 بهمن 1403
  • تاریخ پذیرش: 11 اسفند 1403

هم رسانی

ارجاع به این مقاله

آمار