Muutke küpsiste eelistusi

Modelling for Coastal Hydraulics and Engineering [Kõva köide]

3.00/5 (1 hinnangut Goodreads-ist)
  • Formaat: Hardback, 232 pages, kõrgus x laius: 234x156 mm, kaal: 476 g
  • Ilmumisaeg: 18-Jan-2010
  • Kirjastus: CRC Press
  • ISBN-10: 0415482542
  • ISBN-13: 9780415482547
Teised raamatud teemal:
Modelling for Coastal Hydraulics and EngineeringSuurem pilt
  • Formaat: Hardback, 232 pages, kõrgus x laius: 234x156 mm, kaal: 476 g
  • Ilmumisaeg: 18-Jan-2010
  • Kirjastus: CRC Press
  • ISBN-10: 0415482542
  • ISBN-13: 9780415482547
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9780415482547.html
Märksõnad:
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.
Introduction
1(2)
Coastal modelling
3(5)
Introduction
3(1)
Hydrodynamic modelling
3(3)
Water quality modelling
6(1)
Governing equations
6(1)
Conclusions
7(1)
Conventional modelling techniques for coastal engineering
8(10)
Introduction
8(1)
Mechanistic modelling
8(2)
Model manipulation
9(1)
Generations of modelling
9(1)
Incorporation of artificial intelligence (AI) into modelling
10(1)
Temporal and spatial discretizations
10(7)
Conclusions
17(1)
Finite difference methods
18(35)
Introduction
18(1)
Basic philosophy
18(1)
One-dimensional models
19(1)
Two-dimensional models
20(2)
2-D depth-integrated models
21(1)
2-D lateral-integrated models
22(1)
Three-dimensional models
22(1)
A 3-D hydrodynamic and pollutant transport model
23(9)
Hydrodynamic equations
25(5)
Pollutant transport equation
30(2)
Advantages and disadvantages
32(1)
Applications and case studies
33(18)
Description of the Pearl River estuary
34(1)
Boundary and initial conditions
35(5)
Calibrations
40(8)
Simulated results
48(3)
Conclusions
51(2)
Finite element methods
53(38)
Introduction
53(1)
Basic philosophy
53(1)
One-dimensional models
54(1)
Two-dimensional models
55(2)
2-D depth-integrated models
55(1)
2-D lateral-integrated models
56(1)
Three-dimensional models
57(1)
Characteristic-Galerkin method
58(10)
Formulation of the discretized equations
58(3)
Two-step algorithm
61(1)
A characteristics-based approach
62(2)
The conservtive hydrodynamic and mass transport equations
64(2)
Accuracy analysis of advection-dominated problems
66(2)
Verification of the numerical scheme
68(8)
Pure advection of a Gaussian hill
69(1)
Pure rotation of a Gaussian hill
70(1)
Advective diffusion in a plane shear flow
71(2)
Continuous source in a tidal flow
73(1)
Long wave in a rectangular channel with quadratic bottom bathymetry
74(2)
Advantages and disadvantages
76(1)
Prototype application I: mariculture management
77(6)
General description of Tolo Harbour
77(2)
Dynamic steady-state simulation: M2 tidal forcing
79(2)
Real tide simulation for seven days (42 tidal constituents)
81(2)
Prototype application II: the effect of reclamation on tidal current
83(6)
General description of Victoria Harbour
83(1)
Hydrodynamic simulation for an M2 tidal forcing
83(3)
Real tide simulation for four principal tidal constituents
86(1)
Effect of reclamation
86(3)
Conclusions
89(2)
Soft Computing techniques
91(19)
Introduction
91(2)
Soft computing
93(4)
Data-driven machine learning (ML) algorithms
97(8)
Knowledge-based expert systems
105(2)
Manipulation of conventional models
107(2)
Conclusions
109(1)
Artificial neural networks
110(23)
Introduction
110(1)
Supervised learning algorithm
110(3)
Backpropagation neural networks
113(3)
Advantages and disadvantages of artificial neural networks
116(1)
Prototype application I: algal bloom prediction
117(10)
Description of the study site
117(2)
Criterion of model performance
119(1)
Model inputs and output
120(1)
Significant input variables
120(5)
Results and discussion
125(2)
Prototype application II: long-term prediction of discharges
127(4)
Scaled conjugate gradient (SCG) algorithm
127(1)
Prediction of discharges in Manwan hydropower station
128(1)
Results and discussion
129(2)
Conclusions
131(2)
Fuzzy inference systems
133(17)
Introduction
133(1)
Fuzzy logic
133(3)
Fuzzy inference systems
136(2)
Adaptive-network-based fuzzy inference system (ANFIS)
138(5)
ANFIS architecture
139(3)
Hybrid learning algorithm
142(1)
Advantages and disadvantages of fuzzy inference systems
143(1)
Applications and case studies
143(5)
Model development and testing
144(1)
Results and discussion
145(2)
Result comparison with an ANN model
147(1)
Conclusions
148(2)
Evolutionary algorithms
150(28)
Introduction
150(1)
Genetic algorithms (GA)
150(3)
Genetic programming (GP)
153(1)
Particle swarm optimization (PSO)
154(2)
Advantages and disadvantages of evolutionary algorithms
156(1)
Prototype application I: algal bloom prediction by GP
156(10)
Description of the study site
157(1)
Criterion of model performance
158(1)
Model inputs and output
158(1)
Significant input variables
159(4)
Results and discussion
163(3)
Prototype application II: flood forecasting in river by ANN-GA
166(8)
Algorithm of ANN-GA flood forecasting model
166(1)
The study site and data
167(3)
Results and discussion
170(4)
Prototype application III: water stage forecasting by PSO-based ANN
174(2)
The study site and data
174(1)
Results and discussion
175(1)
Conclusions
176(2)
Knowledge-based systems
178(27)
Introduction
178(1)
Knowledge-based systems
178(8)
Components of knowledg-based systems
179(2)
Characteristics of knowledge-based systems
181(1)
Comparisons with conventional programs
181(1)
Development process of knowledge-based systems
182(1)
Development tools for knowledge-based systems
183(2)
Knowledge representation
185(1)
Rule-based expert systems
186(1)
Problem-solving strategy
186(1)
Blackboard architecture
187(3)
Advantages and disadvantages of knowledge-based systems
190(2)
Advantages of knowledge-based systems
190(1)
Drawbacks of knowledge-based systems
191(1)
Applications and case studies
192(12)
COASTAL_WATER
195(4)
ONTOLOGY_KMS
199(5)
Conclusions
204(1)
Conclusions
205(3)
References 208(18)
Index 226
K.W. Chau is an Associate Professor at Hong Kong Polytechnic University.