A hierarchical machine learning framework for real-time reconstruction of urban wind fields from sparse sensor networks

Keyphrases

• Coefficient Space 50%
• Fine Mapping 50%
• Full-field Reconstruction 50%
• Height Level 50%
• Hierarchical Formulation 50%
• Hierarchical Machine Learning 100%
• Hierarchical Reconstruction 50%
• Inflow Direction 50%
• Intermediate Resolution 50%
• Multiple Heights 50%
• Near Real-time Operation 50%
• Niigata 50%
• Order Learning 50%
• Sensing Constraints 100%
• Sparse Information 50%
• Sparse Sensor Network 100%
• Structure Dynamics 50%
• Temporal Segment 50%
• Unseen Conditions 50%
• Unsteady Dynamics 50%
• Urban District 50%
• Urban Wind Field 100%
• Winds Reconstruction 50%

Engineering

• Computational Fluid Dynamics 50%
• Constrainedness 50%
• Decomposition Coefficient 50%
• Digital Twin 50%
• Dimensionality 50%
• Field Measurement 50%
• Flow Distribution 50%
• Flow Structure 50%
• High Resolution 100%
• Japan 50%
• Large Eddy Simulation 50%
• Learning System 100%
• Lstm 50%
• Multiscale 50%
• Proper Orthogonal Decomposition 100%
• Reynolds' Number 100%
• Sensor Network 100%
• Spatial Structure 50%
• Structural Health Monitoring 50%
• Wind Tunnels 50%

Computer Science

• Resolution Level 50%
• Sparse Information 50%