Calibration of Manning's roughness coefficients for shallow-water flows on complex bathymetries using optimization algorithms and surrogate neural network models

Keyphrases

• Optimization Algorithm 100%
• Neural Network Model 100%
• Complex Bathymetry 100%
• Shallow Water Flows 100%
• Manning's Roughness Coefficient 100%
• Surrogate Neural Network 100%
• Neural Network 50%
• Particle Swarm Optimization 50%
• Machine Learning 50%
• Proposed Methodology 50%
• Genetic Algorithm 50%
• Computational Efficiency 50%
• Deep Neural Network 50%
• Calibration Approach 50%
• Crucial Parameters 50%
• Hybrid Particle Swarm Optimization 50%
• Volume-based 50%
• Automatic Calibration 50%
• Trial-and-error 50%
• Parallelizing 50%
• Finite Volume 50%
• Equation Solver 50%
• Shallow Water Equations 50%
• Conventional Techniques 50%
• Free Surface Flow 50%
• Ensemble Model 50%
• Data Availability 50%
• Learning Objectives 50%
• Multi-GPU 50%
• Manning Coefficient 50%
• Numerical Robustness 50%
• Flow Area 50%
• Inverse Optimization 50%
• Metaheuristic Optimization Algorithms 50%
• Flow Scenarios 50%
• Time Availability 50%

Computer Science

• Machine Learning 100%
• Learning System 100%
• Neural Network 100%
• Particle Swarm Optimization 100%
• Genetic Algorithm 100%
• Computational Efficiency 100%
• Optimization Algorithm 100%
• Optimization Problem 100%
• Deep Neural Network 100%
• Neural Network Model 100%
• Large Data Set 100%
• Graphics Processing Unit 100%
• Data Availability 100%
• Metaheuristic Optimization Algorithm 100%
• Free Surface Flow 100%
• hybrid particle swarm optimization 100%

Engineering

• Particle Swarm Optimization 100%
• Network Model 100%
• Learning System 50%
• Optimisation Problem 50%
• Genetic Algorithm 50%
• Deep Neural Network 50%
• Free Surface 50%
• Optimal Value 50%
• Field Measurement 50%
• Computational Efficiency 50%
• Graphics Processing Unit 50%
• Conventional Technique 50%
• Flow Area 50%
• Flow Domain 50%
• Constrainedness 50%
• Finite Volume 50%
• Metaheuristic Optimization Algorithm 50%