Modelling for Coastal Hydraulics and Engineering

by Chau; Kw

• ISBN13: 9780415482547
• ISBN10: 0415482542
• Edition: 1st
• Format: Hardcover
• Copyright: 2010-02-22
• Publisher: CRC Press

Summary

Mechanistic models are often employed to simulate processes in coastal environments. However, these predictive tools are highly specialized, involve certain assumptions and limitations, and can be manipulated only by experienced engineers who have a thorough understanding of the underlying principles. This results in significant constraints on their manipulation as well as large gaps in understanding and expectations between the developers and users of a model. Recent advancements in soft computing technologies make it possible to integrate machine learning capabilities into numerical modelling systems in order to bridge the gaps and lessen the demands on human experts. This book reviews the state-of-the-art in conventional coastal modelling as well as in the increasingly popular integration of various artificial intelligence technologies into coastal modelling. Conventional hydrodynamic and water quality modelling techniques comprise finite difference and finite element methods. The novel algorithms and methods include knowledge-based systems, genetic algorithms, artificial neural networks, and fuzzy inference systems. Different soft computing methods contribute towards accurate and reliable prediction of coastal processes. Combining these techniques and harnessing their benefits has the potential to make extremely powerful modelling tools.

Author Biography

K.W. Chau is an Associate Professor at Hong Kong Polytechnic University.

Table of Contents

Introduction	p. 1
Coastal modelling	p. 3
Introduction	p. 3
Hydrodynamic modelling	p. 3
Water quality modelling	p. 6
Governing equations	p. 6
Conclusions	p. 7
Conventional modelling techniques for coastal engineering	p. 8
Introduction	p. 8
Mechanistic modelling	p. 8
Model manipulation	p. 9
Generations of modelling	p. 9
Incorporation of artificial intelligence (AI) into modelling	p. 10
Temporal and spatial discretizations	p. 10
Conclusions	p. 17
Finite difference methods	p. 18
Introduction	p. 18
Basic philosophy	p. 18
One-dimensional models	p. 19
Two-dimensional models	p. 20
2-D depth-integrated models	p. 21
2-D lateral-integrated models	p. 22
Three-dimensional models	p. 22
A 3-D hydrodynamic and pollutant transport model	p. 23
Hydrodynamic equations	p. 25
Pollutant transport equation	p. 30
Advantages and disadvantages	p. 32
Applications and case studies	p. 33
Description of the Pearl River estuary	p. 34
Boundary and initial conditions	p. 35
Calibrations	p. 40
Simulated results	p. 48
Conclusions	p. 51
Finite element methods	p. 53
Introduction	p. 53
Basic philosophy	p. 53
One-dimensional models	p. 54
Two-dimensional models	p. 55
2-D depth-integrated models	p. 55
2-D lateral-integrated models	p. 56
Three-dimensional models	p. 57
Characteristic-Galerkin method	p. 58
Formulation of the discretized equations	p. 58
Two-step algorithm	p. 61
A characteristics-based approach	p. 62
The conservative hydrodynamic and mass transport equations	p. 64
Accuracy analysis of advection-dominated problems	p. 66
Verification of the numerical scheme	p. 68
Pure advection of a Gaussian hill	p. 69
Pure rotation of a Gaussian hill	p. 70
Advective diffusion in a plane shear flow	p. 71
Continuous source in a tidal flow	p. 73
Long wave in a rectangular channel with quadratic bottom bathymetry	p. 74
Advantages and disadvantages	p. 76
Prototype application I: mariculture management	p. 77
General description of Tolo Harbour	p. 77
Dynamic steady-state simulation: M2 tidal forcing	p. 79
Real tide simulation for seven days (42 tidal constituents)	p. 81
Prototype application II: the effect of reclamation on tidal current	p. 83
General description of Victoria Harbour	p. 83
Hydrodynamic simulation for an M2 tidal forcing	p. 83
Real tide simulation for four principal tidal constituents	p. 86
Effect of reclamation	p. 86
Conclusions	p. 89
Soft computing techniques	p. 91
Introduction	p. 91
Soft computing	p. 93
Data-driven machine learning (ML) algorithms	p. 97
Knowledge-based expert systems	p. 105
Manipulation of conventional models	p. 107
Conclusions	p. 109
Artificial neural networks	p. 110
Introduction	p. 110
Supervised learning algorithm	p. 110
Backpropagation neural networks	p. 113
Advantages and disadvantages of artificial neural networks	p. 116
Prototype application I: algal bloom prediction	p. 117
Description of the study site	p. 117
Criterion of model performance	p. 119
Model inputs and output	p. 120
Significant input variables	p. 120
Results and discussion	p. 125
Prototype application II: long-term prediction of discharges	p. 127
Scaled conjugate gradient (SCG) algorithm	p. 127
Prediction of discharges in Manwan hydropower station	p. 128
Results and discussion	p. 129
Conclusions	p. 131
Fuzzy inference systems	p. 133
Introduction	p. 133
Fuzzy logic	p. 133
Fuzzy inference systems	p. 136
Adaptive-network-based fuzzy inference system (ANFIS)	p. 138
ANFIS architecture	p. 139
Hybrid learning algorithm	p. 142
Advantages and disadvantages of fuzzy inference systems	p. 143
Applications and case studies	p. 143
Model development and testing	p. 144
Results and discussion	p. 145
Result comparison with an ANN model	p. 147
Conclusions	p. 148
Evolutionary algorithms	p. 150
Introduction	p. 150
Genetic algorithms (GA)	p. 150
Genetic programming (GP)	p. 153
Particle swarm optimization (PSO)	p. 154
Advantages and disadvantages of evolutionary algorithms	p. 156
Prototype application I: algal bloom prediction by GP	p. 156
Description of the study site	p. 157
Criterion of model performance	p. 158
Model inputs and output	p. 158
Significant input variables	p. 159
Results and discussion	p. 163
Prototype application II: flood forecasting in river by ANN-GA	p. 166
Algorithm of ANN-GA flood forecasting model	p. 166
The study site and data	p. 167
Results and discussion	p. 170
Prototype application III: water stage forecasting by PSO-based ANN	p. 174
The study site and data	p. 174
Results and discussion	p. 175
Conclusions	p. 176
Knowledge-based systems	p. 178
Introduction	p. 178
Knowledge-based systems	p. 178
Components of knowledge-based systems	p. 179
Characteristics of knowledge-based systems	p. 181
Comparisons with conventional programs	p. 181
Development process of knowledge-based systems	p. 182
Development tools for knowledge-based systems	p. 183
Knowledge representation	p. 185
Rule-based expert systems	p. 186
Problem-solving strategy	p. 186
Blackboard architecture	p. 187
Advantages and disadvantages of knowledge-based systems	p. 190
Advantages of knowledge-based systems	p. 190
Drawbacks of knowledge-based systems	p. 191
Applications and case studies	p. 192
Coastal_Water	p. 195
Ontology_Kms	p. 199
Conclusions	p. 204
Conclusions	p. 205
References	p. 208
Index	p. 226
Table of Contents provided by Ingram. All Rights Reserved.