English

Towards Sustainable Architecture: 3D Convolutional Neural Networks for Computational Fluid Dynamics Simulation and Reverse DesignWorkflow

Graphics 2019-12-05 v1 Image and Video Processing

Abstract

We present a general and flexible approximation model for near real-time prediction of steady turbulent flow in a 3D domain based on residual Convolutional Neural Networks (CNNs). This approach can provide immediate feedback for real-time iterations at the early stage of architectural design. This work-flow is then reversed and offers a designer a tool that generates building volumes based on target wind flow.

Keywords

Cite

@article{arxiv.1912.02125,
  title  = {Towards Sustainable Architecture: 3D Convolutional Neural Networks for Computational Fluid Dynamics Simulation and Reverse DesignWorkflow},
  author = {Josef Musil and Jakub Knir and Athanasios Vitsas and Irene Gallou},
  journal= {arXiv preprint arXiv:1912.02125},
  year   = {2019}
}

Comments

NeurIPS Workshop on Machine Learning for Creativity and Design 3.0, 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada

R2 v1 2026-06-23T12:35:55.867Z