Spatial ocean wave height prediction with CNN mixed-data deep neural networks using random field simulated bathymetry

With climate change impacts like sea level rise and changing storms, proper prediction of significant wave height (SWH) becomes increasingly important for coastal protection and marine disaster prevention. In the coastal areas of the North Sea, the morphodynamically changing ebb-tidal delta (ETD) sandbanks cause non-linear wave propagation. Therefore, consideration of spatial dependencies using bathymetric data is essential for accurate machine learning predictions. We developed a novel two-dimensional mixed-data deep convolutional neural network (CNN) for spatial SWH prediction in the nearshore area of Norderney, Germany. To overcome the problem of limited bathymetry data, dynamic ETD sandbank morphologies were simulated using random fields and used as model input for the first time. The regional mixed-data CNN was also trained and tested with in-situ metocean input data from 2004 to 2017 and SWAN-modeled ground truth wave fields as output. The proposed CNN architecture outperformed other benchmark models on the test data (RMSE = 0.097 m, R2 = 0.977, MAAPE = 6.7%). Further validation on 59 buoy measurements revealed very similar accuracy of the CNN and SWAN. Compared to the commonly used numerical SWAN model, the trained CNN reduced the computational cost by a factor of more than 300000, making it an efficient surrogate predictive model. •CNN prediction of spatial significant wave height with MAAPE of 6.7%.•Speed-up of the prediction by more than 300 000 times compared to SWAN.•CNN neural networks outperformed other algorithms.•Simulation of dynamic bathymetries using random fields.