Operational Wave Forecast Selection in the Atlantic Ocean Using Random Forests

被引:15
|
作者
Campos, Ricardo M. [1 ]
Costa, Mariana O. [1 ]
Almeida, Fabio [1 ]
Guedes Soares, C. [1 ]
机构
[1] Univ Lisbon, Inst Super Tecn, Ctr Marine Technol & Ocean Engn CENTEC, Av Rovisco Pais, P-1049001 Lisbon, Portugal
关键词
wave forecasts; random forests; decision trees; numerical wave modeling; ensemble forecasting; extreme events; data mining; NEURAL-NETWORKS; SYSTEM; ASSESSMENTS; PREDICTION; WIND;
D O I
10.3390/jmse9030298
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
The existence of multiple wave forecasts leads to the question of which one should be used in practical ocean engineering applications. Ensemble forecasts have emerged as an important complement to deterministic forecasts, with better performances at mid-to-long ranges; however, they add another option to the variety of wave predictions that are available nowadays. This study developed random forest (RF) postprocessing models to identify the best wave forecast between two National Centers for Environmental Protection (NCEP) products (deterministic and ensemble). The supervised learning classifier was trained using National Data Buoy Center (NDBC) buoy data and the RF model accuracies were analyzed as a function of the forecast time. A careful feature selection was performed by evaluating the impact of the wind and wave variables (inputs) on the RF accuracy. The results showed that the RF models were able to select the best forecast only in the very short range using input information regarding the significant wave height, wave direction and period, and ensemble spread. At forecast day 5 and beyond, the RF models could not determine the best wave forecast with high accuracy; the feature space presented no clear pattern to allow for successful classification. The challenges and limitations of such RF predictions for longer forecast ranges are discussed in order to support future studies in this area.
引用
收藏
页数:17
相关论文
共 50 条
  • [1] Implementation of a multi-grid operational wave forecast in the South Atlantic Ocean
    Campos, R. M.
    D'Agostini, A.
    Franca, B. R. L.
    Damiao, A. L. A.
    Guedes Soares, C.
    OCEAN ENGINEERING, 2022, 243
  • [2] Wave forecast in the Atlantic Ocean using a double-stage ConvLSTM network
    Ouyang, Lin
    Ling, Fenghua
    Li, Yue
    Bai, Lei
    Luo, Jing-Jia
    ATMOSPHERIC AND OCEANIC SCIENCE LETTERS, 2023, 16 (04)
  • [3] Wave forecast in the Atlantic Ocean using a double-stage ConvLSTM network
    Lin Ouyang
    Fenghua Ling
    Yue Li
    Lei Bai
    Jing-Jia Luo
    AtmosphericandOceanicScienceLetters, 2023, 16 (04) : 47 - 52
  • [4] Variable selection using random forests
    Genuer, Robin
    Poggi, Jean-Michel
    Tuleau-Malot, Christine
    PATTERN RECOGNITION LETTERS, 2010, 31 (14) : 2225 - 2236
  • [5] Variable selection using random forests
    Sandri, Marco
    Zuccolotto, Paola
    DATA ANALYSIS, CLASSIFICATION AND THE FORWARD SEARCH, 2006, : 263 - +
  • [6] Importance Based Selection Method for Day-ahead Photovoltaic Power Forecast Using Random Forests
    Lahouar, Ali
    Mejri, Amal
    Slama, Jaleleddine Ben Hadj
    2017 INTERNATIONAL CONFERENCE ON GREEN ENERGY & CONVERSION SYSTEMS (GECS), 2017,
  • [7] Evaluation of the NOAA real time ocean forecast system - Atlantic for operational use at the NOAA ocean prediction center
    Daniels, R. M.
    OCEANS 2006, VOLS 1-4, 2006, : 265 - 268
  • [8] Selection of Numerical Weather Forecast Features for PV Power Predictions with Random Forests
    Wolff, Bjoern
    Kramer, Oliver
    Heinemann, Detlev
    DATA ANALYTICS FOR RENEWABLE ENERGY INTEGRATION (DARE 2016), 2017, 10097 : 78 - 91
  • [9] Combining random forests and physics-based models to forecast the electricity generated by ocean waves: A case study of the Mutriku wave farm
    Serras, Paula
    Ibarra-Berastegi, Gabriel
    Saenz, Jon
    Ulazia, Main
    OCEAN ENGINEERING, 2019, 189
  • [10] Wave data assimilation using ensemble error covariances for operational wave forecast
    Sannasiraj, S. A.
    Babovic, Vladan
    Chan, Eng Soon
    OCEAN MODELLING, 2006, 14 (1-2) : 102 - 121