Training a neural-network-based surrogate model for aerodynamic optimization using a gaussian process

Engineering

• Surrogate Model 100%
• Gaussians 100%
• Parameter Space 100%
• Uncertainty Quantification 50%
• Numerical Experiment 50%
• Critical Application 50%
• Learning Approach 50%
• Airfoil 50%
• Demonstrates 50%
• Drag Ratio 50%
• Shape Design Variable 50%
• Design Optimization 50%
• Flight Condition 50%

Keyphrases

• Aerodynamic Optimization 100%
• Design Uncertainty 33%
• Time-critical Applications 33%
• Acquisition Function 33%
• Shape Design Variables 33%
• Drag Ratio 33%

Chemical Engineering

• Neural Network 100%