GIDPC.Green Infrastructure · Disaster Prevention
Projects
R&D · ThermalUrban Thermal

Seocho/Gangnam GATv2 CFD surrogate + Bayesian street-tree placement

A GATv2 trained on 1,500 OpenFOAM scenarios delivers zero-shot R²=0.845 across districts; Bayesian optimization identifies 5–8 m street-tree spacing as the top cooling strategy.

Year
2026
Client
Internal R&D
Status
Under review (Building and Environment)
Stack
OpenFOAM · PyTorch Geometric · GATv2 · Optuna · Transfer Learning

Background

Urban-microclimate CFD is physically credible but each scenario takes hours to days — making thousand-scale design-space exploration practically infeasible.

Existing ML surrogates either force urban geometry onto regular grids or treat spatial elements independently. But urban microclimate is governed by neighborhood interactions: canyon effects, wind corridors, vegetation shading.

Approach

  • Urban blocks represented as graphs — nodes = buildings/roads/vegetation, edges = spatial proximity
  • GATv2 (Graph Attention Network v2) with attention-weighted message passing
  • Training data: 30 Seocho-gu blocks × 1,500 OpenFOAM CFD scenarios
  • Three-stage transfer learning evaluated on 10 adjacent Gangnam-gu blocks
  • Optuna Bayesian optimization sweeps tree spacing, LAI, green-roof coverage
  • Budget constraint: 50 million KRW per block

Key Results

| Metric | Value | |---|---| | Zero-shot transfer R² | 0.845 | | Few-shot (10-block fine-tune) R² | 0.887 | | Full retraining R² | 0.962 | | Optimal tree spacing | 5–8 m | | Optimal LAI | 4–5 | | Block-average cooling | 0.23 °C | | Block-maximum cooling | 1.98 °C |

Implications

  • In the cost of one CFD run, the GNN can compare thousands of scenarios.
  • Adjacent districts with no training data still get usable predictions out-of-the-box (zero-shot R²=0.845).
  • Recommendations move from qualitative ("plant trees") to quantitative ("5–8 m spacing, LAI 4–5").

Related solutions

  • Urban Thermal Diagnosis (CFD · GNN) — core technology stack
  • Spatial Optimization of Green Infrastructure — extend Bayesian → NSGA-II multi-objective