WindMiL: Equivariant Graph Learning for Wind Loading Prediction

TL;DR

WindMiL introduces a symmetry-aware graph neural network framework trained on a large LES-generated dataset to accurately and efficiently predict wind loads on buildings, outperforming non-equivariant models especially under mirrored geometries.

Contribution

The paper presents a novel equivariant GNN model combined with a large-scale wind load dataset, enabling physically consistent and scalable predictions for building wind loading analysis.

Findings

High accuracy in predicting mean and std of surface pressure coefficients.

Maintains over 96% hit rate under reflected geometries.

Outperforms non-equivariant baseline models in accuracy and consistency.

Abstract

Accurate prediction of wind loading on buildings is crucial for structural safety and sustainable design, yet conventional approaches such as wind tunnel testing and large-eddy simulation (LES) are prohibitively expensive for large-scale exploration. Each LES case typically requires at least 24 hours of computation, making comprehensive parametric studies infeasible. We introduce WindMiL, a new machine learning framework that combines systematic dataset generation with symmetry-aware graph neural networks (GNNs). First, we introduce a large-scale dataset of wind loads on low-rise buildings by applying signed distance function interpolation to roof geometries and simulating 462 cases with LES across varying shapes and wind directions. Second, we develop a reflection-equivariant GNN that guarantees physically consistent predictions under mirrored geometries. Across interpolation and extrapolation evaluations, WindMiL achieves high accuracy for both the mean and the standard deviation of surface pressure coefficients (e.g., RMSE $\leq 0.02$ for mean $C_p$) and remains accurate under reflected-test evaluation, maintaining hit rates above $96\%$ where the non-equivariant baseline model drops by more than $10\%$. By pairing a systematic dataset with an equivariant surrogate, WindMiL enables efficient, scalable, and accurate predictions of wind loads on buildings.