Statistical models for improving significant wave height predictions in offshore operations

被引:27
作者
Emmanouil, Stergios [1 ,2 ]
Aguilar, Sandra Gaytan [3 ]
Nane, Gabriela F. [4 ]
Schouten, Jan-Joost [3 ]
机构
[1] Delft Univ Technol, Dept Civil Engn & Geosci, Delft, Netherlands
[2] Univ Connecticut, Dept Civil & Environm Engn, Storrs, CT USA
[3] Deltares, Delft, Netherlands
[4] Delft Univ Technol, Dept Appl Math, Delft, Netherlands
关键词
Bayesian networks; Offshore operations; Real-time predictions; Statistical techniques; Improved forecasts; BAYESIAN NETWORKS; NEURAL-NETWORK; COASTAL REGIONS; UNCERTAINTIES; ASSIMILATION;
D O I
10.1016/j.oceaneng.2020.107249
中图分类号
U6 [水路运输]; P75 [海洋工程];
学科分类号
0814 ; 081505 ; 0824 ; 082401 ;
摘要
Installation and maintenance strategies regarding offshore wind farm operations involve extensive logistics. The main focus is the right temporal and spatial placement of personnel and equipment, while taking into account forecasted meteorological and ocean conditions. For these operations to be successful, weather windows characterized by certain permissive wave conditions are of enormous importance, whereas unforeseen events result in high cost and risk of safety. Numerical modelling of waves, water levels and current related variables has been used extensively to forecast ocean conditions. To account for the inherited model uncertainty, several error modelling techniques can be implemented for the numerical model forecasts to be corrected. In this study, various Bayesian Network (BN) models are incorporated, in order to enhance the accuracy of the significant wave height predictions and to be compared with other techniques, in conditions resembling the real-time nature of the application. The implemented BN models differ in terms of training and structure and provide overall the most satisfying performance. Supplementary, it is shown that the BN models illustrate significant advantages as both quantitative and conceptual tools, since they produce estimates for the underlying uncertainty of the phenomena, while providing information about the incorporated variables' dependence relationships through their structure.
引用
收藏
页数:10
相关论文
共 65 条
[1]  
Aagaard T., 2017, COAST DYN P, P1909
[2]   Bayesian networks in environmental modelling [J].
Aguilera, P. A. ;
Fernandez, A. ;
Fernandez, R. ;
Rumi, R. ;
Salmeron, A. .
ENVIRONMENTAL MODELLING & SOFTWARE, 2011, 26 (12) :1376-1388
[3]   NEW LOOK AT STATISTICAL-MODEL IDENTIFICATION [J].
AKAIKE, H .
IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 1974, AC19 (06) :716-723
[4]  
Aminov Y., 2020, FBD FIND BEST DISTRI
[5]   DISTRIBUTION OF 2-SAMPLE CRAMER-VON MISES CRITERION [J].
ANDERSON, TW .
ANNALS OF MATHEMATICAL STATISTICS, 1962, 33 (03) :1148-&
[6]  
[Anonymous], 2014, Shore \& Beach
[7]  
[Anonymous], 2014, Bayesian Networks: With Examples in R. Chapman & Hall/CRC Texts in Statistical Science
[8]  
[Anonymous], 1996, An introduction to Bayesian networks
[9]  
[Anonymous], 1956, T SOC NAV ARCHIT MAR
[10]  
Asgarpour M., 2016, Offshore Wind Farms, P527, DOI [10.1016/B978-0-08-100779-2.00017-9, DOI 10.1016/B978-0-08-100779-2.00017-9]