prikaz prve stranice dokumenta Hindcast of Significant Wave Heights in Sheltered Basins Using Machine Learning and the Copernicus Database
  Download
PDF 3.38 MB
Scientific paper - Original scientific paper
Hindcast of Significant Wave Heights in Sheltered Basins Using Machine Learning and the Copernicus Database
Naše more : znanstveni časopis za more i pomorstvo, 70 (2023), 2; 103-114. https://doi.org/10.17818/NM/2023/2.5
Bujak, Damjan; Carević, Dalibor; Bogovac, Tonko; Kulić, Tin

Institutional repository: Repository of the Faculty of Civil Engineering, University of Zagreb

Cite this document

Bujak, D., Carević, D., Bogovac, T. & Kulić, T. (2023). Hindcast of Significant Wave Heights in Sheltered Basins Using Machine Learning and the Copernicus Database. Naše more : znanstveni časopis za more i pomorstvo, 70. (2), 103-114. doi: 10.17818/NM/2023/2.5

Bujak, Damjan, et al. "Hindcast of Significant Wave Heights in Sheltered Basins Using Machine Learning and the Copernicus Database." Naše more : znanstveni časopis za more i pomorstvo, vol. 70, no. 2, 2023, pp. 103-114. https://doi.org/10.17818/NM/2023/2.5

Bujak, Damjan, Dalibor Carević, Tonko Bogovac and Tin Kulić. "Hindcast of Significant Wave Heights in Sheltered Basins Using Machine Learning and the Copernicus Database." Naše more : znanstveni časopis za more i pomorstvo 70, no. 2 (2023): 103-114. https://doi.org/10.17818/NM/2023/2.5

Bujak, D., et al. (2023) 'Hindcast of Significant Wave Heights in Sheltered Basins Using Machine Learning and the Copernicus Database', Naše more : znanstveni časopis za more i pomorstvo, 70(2), pp. 103-114. doi: 10.17818/NM/2023/2.5

Bujak D, Carević D, Bogovac T, Kulić T. Hindcast of Significant Wave Heights in Sheltered Basins Using Machine Learning and the Copernicus Database. Naše more : znanstveni časopis za more i pomorstvo [Internet]. 2023 [cited 2024 November 28];70(2):103-114. doi: 10.17818/NM/2023/2.5

D. Bujak, D. Carević, T. Bogovac and T. Kulić, "Hindcast of Significant Wave Heights in Sheltered Basins Using Machine Learning and the Copernicus Database", Naše more : znanstveni časopis za more i pomorstvo, vol. 70, no. 2, pp. 103-114, 2023. [Online]. Available at: https://urn.nsk.hr/urn:nbn:hr:237:751620. [Accessed: 28 November 2024]

Metadata
Title (english)Hindcast of Significant Wave Heights in Sheltered Basins Using Machine Learning and the Copernicus Database
AuthorDamjan Bujak
AuthorDalibor Carević
AuthorTonko Bogovac
AuthorTin Kulić
Author's institutionUniversity of Zagreb
Faculty of Civil Engineering
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Civil Engineering
Abstract (english)
Long-term time series of wave parameters play a critical role in coastal structure design and maritime activities. At sites with limited buoy measurements, methods are used to extend the available time series data. To date, wave hindcasting research using machine learning methods has mainly focused on filling in missing buoy measurements or finding a mapping function between two nearshore buoy locations. This work aims to implement machine learning methods for hindcasting wave parameters using only publicly available Copernicus data. Ensemble regression and artificial neural networks were used as machine learning methods and the optimal hyperparameters were determined by the Bayesian optimization algorithm. As inputs, data from the MEDSEA reanalysis wave model were used for the wave parameters and data from the ERA5 atmospheric reanalysis model were used for the wind parameters. The results of this study show that the normalized RMSE of the test data improved by 29% for Rijeka and 12% for Split compared to the original MEDSEA wave hindcast at buoy locations. The proposed method was extremely efficient in removing bias in the original MEDSEA hindcasts (e.g., NBIAS = -0.35 for Rijeka) to negligible values for both Split and Rijeka (NBIAS < 0.03).
Keywords (english)
Languageenglish
Publication typeScientific paper - Original scientific paper
Publication statusPublished
Peer reviewPeer review - international
Publication versionPublished version
Journal titleNaše more : znanstveni časopis za more i pomorstvo
Numberingvol. 70, no. 2, pp. 103-114
e-ISSN1848-6320
DOIhttps://doi.org/10.17818/NM/2023/2.5
URN:NBNurn:nbn:hr:237:751620
Publication2023
Type of resourceText
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2024-09-05 07:30:13