A deep learning approach to predict significant wave height using long short-term memory

被引:54
作者
Minuzzi, Felipe C. [1 ]
Farina, Leandro [1 ,2 ]
机构
[1] Fed Univ Rio Grande do Sul UFRGS, Inst Math & Stat, Ave Bento Goncalves 9500,POB 15080, Porto Alegre, RS, Brazil
[2] Fed Univ Rio Grande do Sul UFRGS, Ctr Study Coastal & Ocean Geol CECO, Ave Bento Goncalves 9500,Bulding 43 125, Porto Alegre, Rio Grande do S, Brazil
关键词
Ocean waves; Deep learning; Long-short term memory; Significant wave height; Forecast;
D O I
10.1016/j.ocemod.2022.102151
中图分类号
P4 [大气科学(气象学)];
学科分类号
0706 ; 070601 ;
摘要
We present a new deep learning training framework for forecasting significant wave height on the Southwestern Atlantic Ocean. We use the long short-term memory algorithm (LSTM), trained with the ERA5 dataset and also with buoy data. The forecasts are made for seven different locations in the Brazilian coast, where buoy data are available. We consider four different lead times, e.g., 6, 12, 18 and 24 h. Experiments are conducted using exclusively historical series at the selected locations. The influence of other variables as inputs for training is investigated. Results of the LSTM forecast show that a data-driven methodology can be used as a surrogate to the computational expensive physical models and also as an alternative to the reanalysis data. Accuracy of the forecasted significant wave height is close to 87% when compared to real buoy data.
引用
收藏
页数:18
相关论文
共 45 条
[1]   Wave parameter estimation using neural networks [J].
Agrawal, JD ;
Deo, MC .
MARINE STRUCTURES, 2004, 17 (07) :536-550
[2]  
[Anonymous], 2015, TENSORFLOW LARGE SCA
[3]   Observing Sea States [J].
Ardhuin, Fabrice ;
Stopa, Justin E. ;
Chapron, Bertrand ;
Collard, Fabrice ;
Husson, Romain ;
Jensen, Robert E. ;
Johannessen, Johnny ;
Mouche, Alexis ;
Passaro, Marcello ;
Quartly, Graham D. ;
Swail, Val ;
Young, Ian .
FRONTIERS IN MARINE SCIENCE, 2019, 6
[4]   Ocean wave power forecasting using convolutional neural networks [J].
Bento, Pedro ;
Pombo, Jose ;
Calado, Maria do Rosario ;
Mariano, Silvio .
IET RENEWABLE POWER GENERATION, 2021, 15 (14) :3341-3353
[5]  
Booij N., 1997, 25th International Conference on Coastal Engineering, P668, DOI [DOI 10.1061/9780784402429.053, 10.1061/9780784402429.053]
[6]   Assessing wind datasets and boundary conditions for wave hindcasting in the southern Brazil nearshore [J].
Bose, Nicolas de A. ;
Ramos, Marilia S. ;
Correia, Gustavo S. ;
Saidelles, Claus W. ;
Farina, Leandro ;
Parise, Claudia K. ;
Nicolodi, Joao L. .
COMPUTERS & GEOSCIENCES, 2022, 159
[7]  
Boukabara S., 2022, ASSESSMENT SOLUTION
[8]  
Boukabara S.-A., 2022, Bulletin of the American Meteorological Society
[9]   Leveraging Modern Artificial Intelligence for Remote Sensing and NWP: Benefits and Challenges [J].
Boukabara, Sid-Ahmed ;
Krasnopolsky, Vladimir ;
Stewart, Jebb Q. ;
Maddy, Eric S. ;
Shahroudi, Narges ;
Hoffman, Ross N. .
BULLETIN OF THE AMERICAN METEOROLOGICAL SOCIETY, 2019, 100 (12) :ES473-ES491
[10]   Near-shore swell estimation from a global wind-wave model: Spectral process, linear, and artificial neural network models [J].
Browne, Matthew ;
Castelle, Bruno ;
Strauss, Darrell ;
Tomlinson, Rodger ;
Blumenstein, Michael ;
Lane, Chris .
COASTAL ENGINEERING, 2007, 54 (05) :445-460