VI
Figure III-7 Wave fields and current directions for the NNE direction in the Bay of Algiers (For
10 years return period) .................................................................................................................. 48
Figure III-8 Wave fields and current directions for the NNE direction in the Bay of Algiers (For
30 years return period) .................................................................................................................. 49
Figure III-9 Wave fields and current directions for the NNE direction in the Bay of Algiers (For
100 years return period) ................................................................................................................ 50
Figure IV-1 Typical cross section of a rubble mound breakwater (Troch, P. 2001). .................. 52
Figure IV-2 Breaker types as a function of the surf similarity parameter, ξ (Battjes, 1974). ....... 56
Figure IV-3 Notional permeability factor P for the formulae by Van der Meer (1988b) ............. 56
Figure V-1 Hydraulic interactions related to waves and governing parameters (CETMEF, 2009).
....................................................................................................................................................... 62
Figure VI-1 Machine Learning workflow diagram ....................................................................... 70
Figure VI-2 The random forest algorithm relies on multiple decision trees that are all trained
slightly differently. ........................................................................................................................ 73
Figure VI-3 Flow diagram of gradient boosting machine learning method. ................................. 73
Figure VI-4 Evolution of XGBoost Algorithm from Decision Trees. .......................................... 74
Figure VI-5 Articificial Neural Network Architecture. ............................................................... 75
Figure VI-6 Feature definitions, adapted from Van Gent et al. (2007). ........................................ 76
Figure VI-7 Overview of the cleaned Database ............................................................................ 79
Figure VI-8 Predictions of the replicated ANN method. .............................................................. 81
Figure VI-9 Predictions of the published ANN method (2007). ................................................... 82
Figure VI-10 Predictions of the replicated XGBoost method. ...................................................... 83
Figure VI-11 Predictions of the published XGBoost method (2020). .......................................... 83
Figure VI-12 Overview of the Rubble mound breakwater database. ............................................ 84
Figure VI-13 Predictions of the developed model for rubble mound breakwater Database. ........ 85
Figure VII-1 Two-Dimensional Wave Flume Definition Sketch. ................................................. 87
Figure VII-2 Wave flume sketch (Mario, 2019). .......................................................................... 90
Figure VII-3 Plot of k as a function of σ^2. .................................................................................. 92
Figure VII-4 Plot of different actuator strokes limits. ................................................................... 93
Figure VII-5 Plot of the result maximum actuator strokes limit. .................................................. 93
Précédent

Wave overtopping predictions using machine learning technique - 10/131

Suivant