A Generalized Machine Learning Model to Predict  Significant Wave Height from Wind Parameters

Kayes, Imrul; Hasan, Abid; Alam, Minhazul

IUT Repository Home
→
Mechanical and Production Engineering (MPE)
→
Thesis
→
Undergraduate
→
2023
→
View Item

dc.contributor.author	Kayes, Imrul
dc.contributor.author	Hasan, Abid
dc.contributor.author	Alam, Minhazul
dc.date.accessioned	2024-09-10T05:50:54Z
dc.date.available	2024-09-10T05:50:54Z
dc.date.issued	2023-04-30
dc.identifier.citation	[1] A. Agarwal, V. Venugopal, and G. P. Harrison, “The assessment of extreme wave analysis methods applied to potential marine energy sites using numerical model data,” Renew. Sustain. Energy Rev., vol. 27, pp. 244–257, Nov. 2013, doi: 10.1016/j.rser.2013.06.049. [2] M. Zhu, “Soil erosion risk assessment with CORINE model: case study in the Danjiangkou Reservoir region, China,” Stoch. Environ. Res. Risk Assess., vol. 26, no. 6, pp. 813–822, Aug. 2012, doi: 10.1007/s00477-011-0511-7. [3] D. D. Wu, “Introduction to the special SERRA issue on ‘Risks, Uncertainties and the Environment,’” Stoch. Environ. Res. Risk Assess., vol. 25, no. 3, pp. 301–304, Mar. 2011, doi: 10.1007/s00477-010-0368-1. [4] M. Nazir, F. Khan, and P. Amyotte, “Fatigue reliability analysis of deep water rigid marine risers associated with Morison-type wave loading,” Stoch. Environ. Res. Risk Assess., vol. 22, no. 3, pp. 379–390, Apr. 2008, doi: 10.1007/s00477-007-0125-2. [5] P. Dixit and S. Londhe, “Prediction of extreme wave heights using neuro wavelet technique,” Appl. Ocean Res., vol. 58, pp. 241–252, Jun. 2016, doi: 10.1016/j.apor.2016.04.011. [6] R. Mínguez, A. Tomás, F. J. Méndez, and R. Medina, “Mixed extreme wave climate model for reanalysis databases,” Stoch. Environ. Res. Risk Assess., vol. 27, no. 4, pp. 757–768, May 2013, doi: 10.1007/s00477-012-0604-y. [7] M. A. Benitz, M. A. Lackner, and D. P. Schmidt, “Hydrodynamics of offshore structures with specific focus on wind energy applications,” Renew. Sustain. Energy Rev., vol. 44, pp. 692–716, Apr. 2015, doi: 10.1016/j.rser.2015.01.021. [8] C. W. Zheng and C. Y. Li, “Variation of the wave energy and significant wave height in the China Sea and adjacent waters,” Renew. Sustain. Energy Rev., vol. 43, pp. 381– 387, Mar. 2015, doi: 10.1016/j.rser.2014.11.001. [9] E. Vanem, “Long-term time-dependent stochastic modelling of extreme waves,” Stoch. Environ. Res. Risk Assess., vol. 25, no. 2, pp. 185–209, Feb. 2011, doi: 10.1007/s00477-010-0431-y. 118 [10] L. Liu, D. Wang, and Z. Peng, “Path following of marine surface vehicles with dynamical uncertainty and time-varying ocean disturbances,” Neurocomputing, vol. 173, pp. 799–808, Jan. 2016, doi: 10.1016/j.neucom.2015.08.033. [11] D. Demetriou, C. Michailides, G. Papanastasiou, and T. Onoufriou, “Coastal zone significant wave height prediction by supervised machine learning classification algorithms,” Ocean Eng., vol. 221, p. 108592, Feb. 2021, doi: 10.1016/j.oceaneng.2021.108592. [12] S. Foteinis, “Wave energy converters in low energy seas: Current state and opportunities,” Renew. Sustain. Energy Rev., vol. 162, no. September 2021, p. 112448, Jul. 2022, doi: 10.1016/j.rser.2022.112448. [13] A. F. d. O. Falcão, “Wave energy utilization: A review of the technologies,” Renew. Sustain. Energy Rev., vol. 14, no. 3, pp. 899–918, 2010, doi: 10.1016/j.rser.2009.11.003. [14] D. Qiao, R. Haider, J. Yan, D. Ning, and B. Li, “Review of wave energy converter and design of mooring system,” Sustain., vol. 12, no. 19, pp. 1–31, 2020, doi: 10.3390/su12198251. [15] L. Cuadra, S. Salcedo-Sanz, J. C. Nieto-Borge, E. Alexandre, and G. Rodríguez, “Computational intelligence in wave energy: Comprehensive review and case study,” Renew. Sustain. Energy Rev., vol. 58, pp. 1223–1246, May 2016, doi: 10.1016/j.rser.2015.12.253. [16] I. Malekmohamadi, M. R. Bazargan-Lari, R. Kerachian, M. R. Nikoo, and M. Fallahnia, “Evaluating the efficacy of SVMs, BNs, ANNs and ANFIS in wave height prediction,” Ocean Eng., vol. 38, no. 2–3, pp. 487–497, Feb. 2011, doi: 10.1016/j.oceaneng.2010.11.020. [17] S. P. Nitsure, S. N. Londhe, and K. C. Khare, “Wave forecasts using wind information and genetic programming,” Ocean Eng., vol. 54, pp. 61–69, Nov. 2012, doi: 10.1016/j.oceaneng.2012.07.017. [18] S. Elipot, A. Sykulski, R. Lumpkin, L. Centurioni, and M. Pazos, “A dataset of hourly sea surface temperature from drifting buoys,” Sci. Data, vol. 9, no. 1, pp. 1–27, 2022, doi: 10.1038/s41597-022-01670-2. 119 [19] “The Use of Buoys In The Ocean And What Weather Conditions They Measure.” . [20] “NDBC - NDBC’s Drifting Buoy Program.” . [21] “NDBC - Moored Buoy Program.” . [22] S. Elipot, R. Lumpkin, R. C. Perez, J. M. Lilly, J. J. Early, and A. M. Sykulski, “A global surface drifter data set at hourly resolution,” J. Geophys. Res. Ocean., vol. 121, no. 5, pp. 2937–2966, 2016, doi: 10.1002/2016JC011716. [23] H. Hu, A. J. van der Westhuysen, P. Chu, and A. Fujisaki-Manome, “Predicting Lake Erie wave heights and periods using XGBoost and LSTM,” Ocean Model., vol. 164, Aug. 2021, doi: 10.1016/j.ocemod.2021.101832. [24] K. Hasselmann et al., “Measurements of wind-wave growth and swell decay during the joint North Sea wave project (JONSWAP).,” no. July 2015, 1973. [25] T. W. Group, “The WAM Model—A Third Generation Ocean Wave Prediction Model,” J. Phys. Oceanogr., vol. 18, no. 12, pp. 1775–1810, Dec. 1988, doi: 10.1175/1520-0485(1988)018<1775:TWMTGO>2.0.CO;2. [26] N. Booij, R. C. Ris, and L. H. Holthuijsen, “A third-generation wave model for coastal regions: 1. Model description and validation,” J. Geophys. Res. Ocean., vol. 104, no. C4, pp. 7649–7666, Apr. 1999, doi: 10.1029/98JC02622. [27] H. L. Tolman et al., “Development and Implementation of Wind-Generated Ocean Surface Wave Modelsat NCEP,” Weather Forecast., vol. 17, no. 2, pp. 311–333, Apr. 2002, doi: 10.1175/1520-0434(2002)017<0311:DAIOWG>2.0.CO;2. [28] M. Zijlema, “Computation of wind-wave spectra in coastal waters with SWAN on unstructured grids,” Coast. Eng., vol. 57, no. 3, pp. 267–277, Mar. 2010, doi: 10.1016/j.coastaleng.2009.10.011. [29] N. K. Kumar, R. Savitha, and A. Al Mamun, “Ocean wave height prediction using ensemble of Extreme Learning Machine,” Neurocomputing, vol. 277, pp. 12–20, Feb. 2018, doi: 10.1016/j.neucom.2017.03.092. [30] M. Browne, B. Castelle, D. Strauss, R. Tomlinson, M. Blumenstein, and C. Lane, “Near-shore swell estimation from a global wind-wave model: Spectral process, linear, and artificial neural network models,” Coast. Eng., vol. 54, no. 5, pp. 445–460, May 120 2007, doi: 10.1016/j.coastaleng.2006.11.007. [31] J.-H. G. M. Alves, A. Chawla, H. L. Tolman, D. Schwab, G. Lang, and G. Mann, “The Operational Implementation of a Great Lakes Wave Forecasting System at NOAA/NCEP,” Weather Forecast., vol. 29, no. 6, pp. 1473–1497, Dec. 2014, doi: 10.1175/WAF-D-12-00049.1. [32] F. Zabihian and A. S. Fung, “Review of marine renewable energies: Case study of Iran,” Renew. Sustain. Energy Rev., vol. 15, no. 5, pp. 2461–2474, 2011, doi: 10.1016/j.rser.2011.02.006. [33] M. Fadaeenejad, R. Shamsipour, S. D. Rokni, and C. Gomes, “New approaches in harnessing wave energy: With special attention to small islands,” Renew. Sustain. Energy Rev., vol. 29, pp. 345–354, 2014, doi: 10.1016/j.rser.2013.08.077. [34] M. A. J. R. Quirapas, H. Lin, M. L. S. Abundo, S. Brahim, and D. Santos, “Ocean renewable energy in Southeast Asia: A review,” Renew. Sustain. Energy Rev., vol. 41, pp. 799–817, 2015, doi: 10.1016/j.rser.2014.08.016. [35] N. Khan, A. Kalair, N. Abas, and A. Haider, “Review of ocean tidal, wave and thermal energy technologies,” Renew. Sustain. Energy Rev., vol. 72, no. January, pp. 590–604, 2017, doi: 10.1016/j.rser.2017.01.079. [36] D. Khojasteh, S. M. Mousavi, W. Glamore, and G. Iglesias, “Wave energy status in Asia,” Ocean Eng., vol. 169, no. April, pp. 344–358, 2018, doi: 10.1016/j.oceaneng.2018.09.034. [37] R. Pelc and R. M. Fujita, “Renewable energy from the ocean,” Mar. Policy, vol. 26, no. 6, pp. 471–479, Nov. 2002, doi: 10.1016/S0308-597X(02)00045-3. [38] T. . Thorpe, “An overview of wave energy technologies: Status, performance and costs,” Wave Power Mov. Towar. Commer. viability, no. November, p. not paginated, 1999. [39] M. L. Ae et al., “Wave Energy from the North Sea: Experiences from the Lysekil Research Site,” vol. 29, pp. 221–240, 2008, doi: 10.1007/s10712-008-9047-x. [40] Y. P. Wimalaratna et al., “Comprehensive review on the feasibility of developing wave energy as a renewable energy resource in Australia,” Clean. Energy Syst., vol. 3, no. April, p. 100021, 2022, doi: 10.1016/j.cles.2022.100021. 121 [41] E. Al Shami, R. Zhang, and X. Wang, “Point absorber wave energy harvesters: A review of recent developments,” Energies, vol. 12, no. 1, 2019, doi: 10.3390/en12010047. [42] T. Hirohisa, “Sea trial of a heaving buoy wave power absorber,” in Proceedings of 2nd international symposium on wave energy utilization, Trondheim, Norway, 1982, pp. 403–417. [43] K. Budal et al., “The Norwegian wave-power buoy project,” 1982. [44] M. E. McCormick, “Wave-powered reverse-osmosis desalination,” Sea Technol., vol. 42, pp. 37–39, 2001. [45] J. Ringwood, “The dynamics of wave energy,” pp. 23–34, Jan. 2007, doi: 10.1049/CP:20060408. [46] “Pelamis Wave Power - Wikipedia.” https://en.wikipedia.org/wiki/Pelamis_Wave_Power (accessed Jan. 25, 2023). [47] A. H. Clément et al., “Wave energy in Europe: current status and perspectives,” Renew. \& Sustain. Energy Rev., vol. 6, pp. 405–431, 2002. [48] “WPP A/S Products- Waveplane.” http://www.waveplane.com/products.html (accessed Jan. 25, 2023). [49] “Wave Dragon.” wavedragon.net. [50] H. C. Soerensen, W. Panhauser, D. Dunce, J. Nedkvintne, P. Frigaard, and J. P. Kofoed, “Development of Wave Dragon from Scale 1 : 50 to Prototype,” Coast. Eng., pp. 5–11, 2003. [51] L. Cameron et al., “Design of the Next Generation of the Oyster Wave Energy Converter,” 2010. [52] “Home - AW-Energy.” https://aw-energy.com/ (accessed Jan. 25, 2023). [53] S. Salter, “Apparatus and method for extracting wave energy,” United States Pat., vol. 3,928,967, no. 521,385, p. 8, 1975. [54] N. Tom, Y. Yu, A. Wright, N. Tom, Y. Yu, and A. Wright, “Submerged Pressure Differential Plate Wave Energy Converter with Variable Geometry Preprint Submerged Pressure Differential Plate Wave Energy Converter with Variable 122 Geometry Preprint,” no. October, 2019. [55] “News - AWS Ocean Energy.” https://awsocean.com/news/ (accessed Jan. 28, 2023). [56] “AWS wave energy converter takes shape in Glasgow ahead of testing - AWS Ocean Energy.” https://awsocean.com/2021/06/waveswing-takes-shape-in-glasgow/ (accessed Jan. 28, 2023). [57] “AWS Waveswing trials exceed expectations - AWS Ocean Energy.” https://awsocean.com/2022/11/aws-waveswing-trials-exceed-expectations/ (accessed Jan. 28, 2023). [58] “Tide - Wikipedia.” https://en.wikipedia.org/wiki/Tide (accessed Jan. 28, 2023). [59] R. Pelc and R. M. Fujita, “Renewable energy from the ocean,” Mar. Policy, vol. 26, no. 6, pp. 471–479, 2002, doi: https://doi.org/10.1016/S0308-597X(02)00045-3. [60] “Sihwa Lake Tidal Power Station - Wikipedia.” https://en.wikipedia.org/wiki/Sihwa_Lake_Tidal_Power_Station (accessed Jan. 28, 2023). [61] “Sihwa Tidal Power Plant \| Tethys,” tethys.pnnl.gov, Accessed: Jan. 28, 2023. [Online]. Available: https://tethys.pnnl.gov/project-sites/sihwa-tidal-power plant#:~:text=To date, the Sihwa TBPP is the largest and most expensive tidal installation in the world. [62] Korea’s Uldolmok tidal power project completed. . [63] “Uldolmok Tidal Power Station - Wikipedia.” https://en.wikipedia.org/wiki/Uldolmok_Tidal_Power_Station (accessed Jan. 29, 2023). [64] “Rance Tidal Power Station - Wikipedia.” https://en.wikipedia.org/wiki/Rance_Tidal_Power_Station (accessed Jan. 28, 2023). [65] “Jiangxia Tidal Power Station - Wikipedia.” https://en.wikipedia.org/wiki/Jiangxia_Tidal_Power_Station (accessed Jan. 29, 2023). [66] “Tidal stream generator - Wikipedia.” https://en.wikipedia.org/wiki/Tidal_stream_generator (accessed Jan. 29, 2023). [67] “ScotRenewables SR2000 at EMEC \| Tethys.” https://tethys.pnnl.gov/project- 123 sites/scotrenewables-sr2000-emec (accessed Jan. 31, 2023). [68] M. Dickie, “Scotland unveils world’s largest tidal stream power project,” Sep. 2016, Accessed: Jan. 29, 2023. [Online]. Available: https://webcache.googleusercontent.com/search?q=cache:NLYheToLCeAJ:https://ww w.ft.com/content/d197308a-7826-11e6-97ae 647294649b28+&cd=1&hl=en&ct=clnk&gl=us. [69] M. Nachtane, M. Tarfaoui, I. Goda, and M. Rouway, “A review on the technologies, design considerations and numerical models of tidal current turbines,” Renew. Energy, vol. 157, pp. 1274–1288, 2020, doi: 10.1016/j.renene.2020.04.155. [70] “Project overview - FORWARD2030.” https://forward2030.tech/project-overview (accessed Jan. 31, 2023). [71] “Orbital Marine Power Launches O2: World’s Most Powerful Tidal Turbine - Orbital Marine.” https://orbitalmarine.com/orbital-marine-power-launches-o2/# (accessed Jan. 31, 2023). [72] “Innovation - Orbital Marine.” https://orbitalmarine.com/innovation/# (accessed Jan. 31, 2023). [73] “Kvalsund Tidal Turbine Prototype \| Tethys.” https://tethys.pnnl.gov/project sites/kvalsund-tidal-turbine-prototype (accessed Jan. 31, 2023). [74] “MeyGen - Wikipedia.” https://en.wikipedia.org/wiki/MeyGen (accessed Jan. 29, 2023). [75] “MeyGen Tidal Energy Project - Phase I \| Tethys.” https://tethys.pnnl.gov/project sites/meygen-tidal-energy-project-phase-i (accessed Jan. 31, 2023). [76] H. Chen, T. Tang, N. Ait-Ahmed, M. E. H. Benbouzid, M. MacHmoum, and M. E. H. Zaim, “Attraction, Challenge and Current Status of Marine Current Energy,” IEEE Access, vol. 6, pp. 12665–12685, Jan. 2018, doi: 10.1109/ACCESS.2018.2795708. [77] “World’s First Open Sea Tidal Turbine \| REUK.co.uk.” http://www.reuk.co.uk/wordpress/tidal/worlds-first-open-sea-tidal-turbine/ (accessed Jan. 31, 2023). [78] “Worldchanging \| Evaluation + Tools + Best Practices: Gorlov’s Helical Turbine.” 124 https://web.archive.org/web/20130511010214/http://www.worldchanging.com/archive s/002383.html (accessed Jan. 31, 2023). [79] “Shark biomimicry produces renewable energy system.” https://news.mongabay.com/2006/11/shark-biomimicry-produces-renewable-energy system/ (accessed Jan. 31, 2023). [80] “Underwater kite-turbine may turn tides into green electricity \| Renewable energy \| The Guardian.” https://www.theguardian.com/environment/damian-carrington blog/2011/mar/02/underwater-kite-turbine-green-electricity (accessed Jan. 31, 2023). [81] “Tidal power - Wikipedia.” https://en.wikipedia.org/wiki/Tidal_power (accessed Jan. 28, 2023). [82] S. Waters and G. Aggidis, “A world first: Swansea Bay tidal lagoon in review,” Renew. Sustain. Energy Rev., vol. 56, pp. 916–921, Apr. 2016, doi: 10.1016/J.RSER.2015.12.011. [83] “Green light expected for multi-billion-pound tidal lagoon project,” Nation.Cymru, Jan. 2023, Accessed: Feb. 01, 2023. [Online]. Available: https://nation.cymru/news/green-light-expected-for-multi-billion-pound-tidal-lagoon project/. [84] “Tidal Lagoon Swansea Bay - Wikipedia.” https://en.wikipedia.org/wiki/Tidal_Lagoon_Swansea_Bay (accessed Feb. 01, 2023). [85] D. Vandercruyssen, S. Baker, D. Howard, and G. Aggidis, “Tidal range electricity generation: A comparison between estuarine barrages and coastal lagoons,” Heliyon, vol. 8, no. 11, p. e11381, 2022, doi: 10.1016/j.heliyon.2022.e11381. [86] P. Dai et al., “Numerical study of hydrodynamic mechanism of dynamic tidal power,” Water Sci. Eng., vol. 11, no. 3, pp. 220–228, 2018, doi: 10.1016/j.wse.2018.09.004. [87] “Dynamic tidal power - Wikipedia.” https://en.wikipedia.org/wiki/Dynamic_tidal_power (accessed Feb. 01, 2023). [88] Y. H. Park, “Analysis of characteristics of Dynamic Tidal Power on the west coast of Korea,” Renew. Sustain. Energy Rev., vol. 68, no. October 2016, pp. 461–474, 2017, doi: 10.1016/j.rser.2016.10.008. 125 [89] P. Dai, J. Zhang, and J. Zheng, “Predictions for Dynamic Tidal Power and Associated Local Hydrodynamic Impact in the Taiwan Strait, China,” J. Coast. Res., vol. 33, no. 1, pp. 149–157, 2017, doi: 10.2112/JCOASTRES-D-16-00068.1. [90] D. Shao, W. Feng, X. Feng, and Y. Xu, “Reinvestigation of the Dynamic Tidal Power Dams and their Influences on Hydrodynamic Environment,” IOP Conf. Ser. Earth Environ. Sci., vol. 63, no. 1, 2017, doi: 10.1088/1755-1315/63/1/012048. [91] Y. H. Park, “The Application of Dynamic Tidal Power in Korea,” J. Coast. Res., vol. 85, pp. 1306–1310, 2018, doi: 10.2112/SI85-262.1. [92] E. Armoudli, A. Mohseni, A. Sheykhi, and K. Javaherdeh, “A Case Study of Energy Harvesting by Dynamic Tidal Power in the Persian Gulf,” 2019 Iran. Conf. Renew. Energy Distrib. Gener. ICREDG 2019, pp. 11–12, 2019, doi: 10.1109/ICREDG47187.2019.194178. [93] J. G. McGowan, “Ocean thermal energy conversion—A significant solar resource,” Sol. Energy, vol. 18, no. 2, pp. 81–92, Jan. 1976, doi: 10.1016/0038-092X(76)90042-6. [94] W. Liu et al., “A review of research on the closed thermodynamic cycles of ocean thermal energy conversion,” Renew. Sustain. Energy Rev., vol. 119, p. 109581, Mar. 2020, doi: 10.1016/J.RSER.2019.109581. [95] S. M. Abbas, H. D. S. Alhassany, D. Vera, and F. Jurado, “Review of enhancement for ocean thermal energy conversion system,” J. Ocean Eng. Sci., no. xxxx, 2022, doi: 10.1016/j.joes.2022.03.008. [96] F. Chen, L. Zhang, W. Liu, L. Liu, and J. Peng, “Thermodynamic analysis of rankine cycle in ocean thermal energy conversion,” Int. J. Simul. Syst. Sci. Technol., vol. 17, no. 13, pp. 7.1-7.4, 2016, doi: 10.5013/IJSSST.A.17.13.07. [97] K. Rajagopalan and G. C. Nihous, “Estimates of global Ocean Thermal Energy Conversion (OTEC) resources using an ocean general circulation model,” Renew. Energy, vol. 50, pp. 532–540, Feb. 2013, doi: 10.1016/J.RENENE.2012.07.014. [98] J. Langer, J. Quist, and K. Blok, “Upscssssaling scenarios for ocean thermal energy conversion with technological learning in Indonesia and their global relevance,” Renew. Sustain. Energy Rev., vol. 158, no. January, p. 112086, 2022, doi: 10.1016/j.rser.2022.112086. 126 [99] J. Langer, C. Infante Ferreira, and J. Quist, “Is bigger always better? Designing economically feasible ocean thermal energy conversion systems using spatiotemporal resource data,” Appl. Energy, vol. 309, no. July 2021, p. 118414, 2022, doi: 10.1016/j.apenergy.2021.118414. [100] T. Mitsui, F. Ito, Y. Seya, and Y. Nakamoto, “Outline of the 100 kW OTEC Pilot Plant in the Republic of Nauru,” IEEE Trans. Power Appar. Syst., vol. PAS-102, no. 9, pp. 3167–3171, 1983, doi: 10.1109/TPAS.1983.318124. [101] “Hawaii About to Crack Ocean Thermal Energy Conversion Roadblocks? \| OilPrice.com.” https://oilprice.com/Alternative-Energy/Renewable-Energy/Hawaii About-To-Crack-Ocean-Thermal-Energy-Conversion-Roadblocks.html (accessed Feb. 04, 2023). [102] “Ocean thermal energy conversion - Wikipedia.” https://en.wikipedia.org/wiki/Ocean_thermal_energy_conversion (accessed Feb. 04, 2023). [103] “Ocean Thermal to begin talks for renewable energy plants in St. Croix, St. Thomas \| Local Business \| lancasteronline.com.” https://lancasteronline.com/business/local_business/ocean-thermal-to-begin-talks-for renewable-energy-plants-in/article_e68b41f4-4da4-11e6-8d72-1352558baa6f.html (accessed Feb. 04, 2023). [104] “Celebrating Hawaii ocean thermal energy conversion power plant.” https://techxplore.com/news/2015-08-celebrating-hawaii-ocean-thermal-energy.html (accessed Feb. 04, 2023). [105] “OTEC – Ocean Thermal Energy Conversion \| Makai Ocean Engineering.” https://www.makai.com/renewable-energy/otec/ (accessed Feb. 04, 2023). [106] “Okinawa OTEC Demonstration Project.” http://otecokinawa.com/en/Project/index.html (accessed Feb. 04, 2023). [107] “Salinity Gradient \| Tethys.” https://tethys.pnnl.gov/technology/salinity-gradient (accessed Feb. 04, 2023). [108] “Statkraft osmotic power prototype in Hurum - Wikipedia.” https://en.wikipedia.org/wiki/Statkraft_osmotic_power_prototype_in_Hurum 127 (accessed Feb. 04, 2023). [109] “Osmotic power - Wikipedia.” https://en.wikipedia.org/wiki/Osmotic_power (accessed Feb. 04, 2023). [110] N. Guillou, “Estimating wave energy flux from significant wave height and peak period,” Renew. Energy, vol. 155, pp. 1383–1393, 2020, doi: 10.1016/j.renene.2020.03.124. [111] J. Mahjoobi and A. Etemad-Shahidi, “An alternative approach for the prediction of significant wave heights based on classification and regression trees,” Appl. Ocean Res., vol. 30, no. 3, pp. 172–177, 2008, doi: 10.1016/j.apor.2008.11.001. [112] M. S. Elbisy and A. M. S. Elbisy, “Prediction of significant wave height by artificial neural networks and multiple additive regression trees,” Ocean Eng., vol. 230, p. 109077, Jun. 2021, doi: 10.1016/j.oceaneng.2021.109077. [113] S. Gracia, J. Olivito, J. Resano, B. Martin-del-Brio, M. de Alfonso, and E. Álvarez, “Improving accuracy on wave height estimation through machine learning techniques,” Ocean Eng., vol. 236, p. 108699, Sep. 2021, doi: 10.1016/j.oceaneng.2021.108699. [114] N. K. kumar, R. Savitha, and A. Al Mamun, “Regional ocean wave height prediction using sequential learning neural networks,” Ocean Eng., vol. 129, pp. 605–612, Jan. 2017, doi: 10.1016/j.oceaneng.2016.10.033. [115] K. Günaydin, “The estimation of monthly mean significant wave heights by using artificial neural network and regression methods,” Ocean Eng., vol. 35, no. 14–15, pp. 1406–1415, Oct. 2008, doi: 10.1016/j.oceaneng.2008.07.008. [116] S. Shamshirband, A. Mosavi, T. Rabczuk, N. Nabipour, and K. Chau, “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., vol. 14, no. 1, pp. 805–817, Jan. 2020, doi: 10.1080/19942060.2020.1773932. [117] S. C. James, Y. Zhang, and F. O’Donncha, “A machine learning framework to forecast wave conditions,” Coast. Eng., vol. 137, pp. 1–10, Jul. 2018, doi: 10.1016/j.coastaleng.2018.03.004. 128 [118] A. Etemad-Shahidi and J. Mahjoobi, “Comparison between M5′ model tree and neural networks for prediction of significant wave height in Lake Superior,” Ocean Eng., vol. 36, no. 15–16, pp. 1175–1181, Nov. 2009, doi: 10.1016/j.oceaneng.2009.08.008. [119] M. C. Deo, A. Jha, A. S. Chaphekar, and K. Ravikant, “Neural networks for wave forecasting,” Ocean Eng., vol. 28, no. 7, pp. 889–898, Jul. 2001, doi: 10.1016/S0029- 8018(00)00027-5. [120] O. Makarynskyy, “Improving wave predictions with artificial neural networks,” Ocean Eng., vol. 31, no. 5–6, pp. 709–724, Apr. 2004, doi: 10.1016/j.oceaneng.2003.05.003. [121] J. D. Agrawal and M. C. Deo, “On-line wave prediction,” Mar. Struct., vol. 15, no. 1, pp. 57–74, Jan. 2002, doi: 10.1016/S0951-8339(01)00014-4. [122] A. Zamani, D. Solomatine, A. Azimian, and A. Heemink, “Learning from data for wind-wave forecasting,” Ocean Eng., vol. 35, no. 10, pp. 953–962, 2008, doi: 10.1016/j.oceaneng.2008.03.007. [123] M. Ali and R. Prasad, “Significant wave height forecasting via an extreme learning machine model integrated with improved complete ensemble empirical mode decomposition,” Renew. Sustain. Energy Rev., vol. 104, pp. 281–295, 2019, doi: https://doi.org/10.1016/j.rser.2019.01.014. [124] J. Berbić, E. Ocvirk, D. Carević, and G. Lončar, “Application of neural networks and support vector machine for significant wave height prediction,” Oceanologia, vol. 59, no. 3, pp. 331–349, 2017, doi: 10.1016/j.oceano.2017.03.007. [125] V. Domala, W. Lee, and T. Kim, “Wave data prediction with optimized machine learning and deep learning techniques,” J. Comput. Des. Eng., May 2022, doi: 10.1093/jcde/qwac048. [126] A. M. Gómez-Orellana, D. Guijo-Rubio, P. A. Gutiérrez, and C. Hervás-Martínez, “Simultaneous short-term significant wave height and energy flux prediction using zonal multi-task evolutionary artificial neural networks,” Renew. Energy, vol. 184, pp. 975–989, Jan. 2022, doi: 10.1016/j.renene.2021.11.122. [127] C. Jörges, C. Berkenbrink, and B. Stumpe, “Prediction and reconstruction of ocean wave heights based on bathymetric data using LSTM neural networks,” Ocean Eng., vol. 232, no. March, 2021, doi: 10.1016/j.oceaneng.2021.109046. 129 [128] J. Mahjoobi and E. Adeli Mosabbeb, “Prediction of significant wave height using regressive support vector machines,” Ocean Eng., vol. 36, no. 5, pp. 339–347, Apr. 2009, doi: 10.1016/j.oceaneng.2009.01.001. [129] J. C. Fernández, S. Salcedo-Sanz, P. A. Gutiérrez, E. Alexandre, and C. Hervás Martínez, “Significant wave height and energy flux range forecast with machine learning classifiers,” Eng. Appl. Artif. Intell., vol. 43, pp. 44–53, 2015, doi: 10.1016/j.engappai.2015.03.012. [130] D. Guijo-Rubio, A. M. Gómez-Orellana, P. A. Gutiérrez, and C. Hervás-Martínez, “Short- and long-term energy flux prediction using Multi-Task Evolutionary Artificial Neural Networks,” Ocean Eng., vol. 216, no. July, p. 108089, 2020, doi: 10.1016/j.oceaneng.2020.108089. [131] “Wave power - U.S. Energy Information Administration (EIA).” . [132] “ERDDAP - NDBC Standard Meteorological Buoy Data, 1970-present - Subset.” . [133] F. Pedregosa FABIANPEDREGOSA et al., “Scikit-learn: Machine Learning in Python,” J. Mach. Learn. Res., vol. 12, no. 85, pp. 2825–2830, 2011. [134] S. R. Massel, “Ocean Surface Waves: Their Physics and Prediction,” vol. 11, Feb. 1996, doi: 10.1142/2285. [135] T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system,” Proc. ACM SIGKDD Int. Conf. Knowl. Discov. Data Min., vol. 13-17-Augu, pp. 785–794, 2016, doi: 10.1145/2939672.2939785. [136] B. J. H. Friedman, “1999 REITZ LECTURE,” vol. 29, no. 5, pp. 1189–1232, 2001. [137] G. Ke et al., “LightGBM: A highly efficient gradient boosting decision tree,” Adv. Neural Inf. Process. Syst., vol. 2017-Decem, no. Nips, pp. 3147–3155, 2017. [138] F. Rosenblatt, “The perceptron: A probabilistic model for information storage and organization in the brain,” Psychol. Rev., vol. 65, no. 6, pp. 386–408, Nov. 1958, doi: 10.1037/H0042519. [139] D. E. Rumelhart, G. E. Hinton, and R. J. Williams, “Learning representations by back propagating errors,” Nat. 1986 3236088, vol. 323, no. 6088, pp. 533–536, 1986, doi: 10.1038/323533a0. 130 [140] A. M. Fred Agarap, “Deep Learning using Rectified Linear Units (ReLU),” Mar. 2018. [141] H. Kaiming, Z. Xiangyu, R. Shaoqing, and S. Jian, “Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification Kaiming,” Biochem. Biophys. Res. Commun., vol. 498, no. 1, pp. 254–261, 2018. [142] D. P. Kingma and J. L. Ba, “Adam: A Method for Stochastic Optimization,” 3rd Int. Conf. Learn. Represent. ICLR 2015 - Conf. Track Proc., Dec. 2014. [143] N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, “Dropout: A Simple Way to Prevent Neural Networks from Overfitting,” J. Mach. Learn. Res., vol. 15, no. 56, pp. 1929–1958, 2014. [144] S. Ioffe and C. Szegedy, “Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift,” 32nd Int. Conf. Mach. Learn. ICML 2015, vol. 1, pp. 448–456, Feb. 2015. [145] G. Klambauer, T. Unterthiner, A. Mayr, and S. Hochreiter, “Self-Normalizing Neural Networks,” Adv. Neural Inf. Process. Syst., vol. 2017-Decem, pp. 972–981, Jun. 2017. [146] T. Akiba, S. Sano, T. Yanase, T. Ohta, and M. Koyama, “Optuna: A Next-generation Hyperparameter Optimization Framework,” Proc. ACM SIGKDD Int. Conf. Knowl. Discov. Data Min., pp. 2623–2631, Jul. 2019, doi: 10.1145/3292500.3330701	en_US
dc.identifier.uri	http://hdl.handle.net/123456789/2180
dc.description	Supervised by Prof. Dr. Mohammad Ahsan Habib, Co-Superviser Mr. Tanvir Shahriar, Assistant Professor, Department of Production and Mechanical Engineering(MPE), Islamic University of Technology (IUT) Board Bazar, Gazipur-1704, Bangladesh	en_US
dc.description.abstract	Due to recent energy crises in the post-pandemic world, exploration of marine renewable energy sources is more crucial than ever. Significant wave height is a key parameter for wave energy extraction, it also has a wide range of applications, including ship navigation, oil and gas extraction, and the construction of coastal structures. Among the existing methods of measuring significant wave height, direct measurements using buoys are very expensive and limited in number, moreover these provide data with low time and spatial resolutions whereas numerical models are based on mathematical equations, assumptions and becomes complex when they are applied for generalization purpose. With a view to facilitate the utilization of wave energy and foster research activities by providing cheap dataset of wave properties with high spatial and time resolution, this work focuses on developing a generalized machine learning model that is able to predict significant wave height from wind parameters on a huge area around the coastlines of USA and Canada. Four machine learning models have been used in this work; 2 deep learning models (Artificial Neural Network (ANN) and Self Normalizing Neural Network (SNN)) and 2 gradient boosting tree-based models (XGBoost and LightGBM) and performance of these models have been evaluated on test data, distinct from the one used for training. The deep learning models have showed greater fitting capacity compared to tree based model on the training data, achieving the lowest Mean Squared Error(MSE) (0.047 for ANN, 0.063 for SNN, 0.226 for XGBoost, 0.108 for LightGBM) and highest R2 score (0.953 for ANN & 0.937 for SNN, 0.894 for XGBoost, 0.892 for LightGBM) whereas the gradient boosting models demonstrate better generalizing capacity compared to the deep learning models on both the known (data from these buoys are included in the training set) and unknown (data from these buoys are not included in the training set) buoys. Furthermore, impact of outlier detection and removal using Tukey’s Fence method on the performance of ANN & SNN has been evaluated and found to be insignificant.	en_US
dc.language.iso	en	en_US
dc.publisher	Department of Mechanical and Production Engineering(MPE), Islamic University of Technology(IUT), Board Bazar, Gazipur-1704, Bangladesh	en_US
dc.title	A Generalized Machine Learning Model to Predict Significant Wave Height from Wind Parameters	en_US
dc.type	Thesis	en_US