Description
Integrating building performance analysis results in the early stage of conceptual design supports effective design exploration and decision making. Such integration requires domain expertise and can be technically challenging, time consuming, and computationally expensive. Machine learning demonstrates great potential for building seamless workflows that provide faster analysis feedback. However, one of the challenges in the architecture domain is the lack of diverse data sets to train effective prediction models. This talk will provide a brief overview of the potential of machine learning in building analysis-prediction models and demonstrate how we can capitalize on generative design to compensate for the lack of data. We will present a workflow where generative design features for Revit software, Dynamo software, and Insight software are used to generate a synthetic data set for training a machine-learning model for energy-analysis prediction.
Key Learnings
- Learn how to design workflows with Generative Design in Revit and Dynamo for building synthetic data sets to be used in training machine-learning models.
- Discover the diversity of mass model geometry required to represent a comprehensive set of possible building types.
- Learn how to represent your data to be used in training machine-learning models.
- Discover potential uses of machine-learning models toward achieving faster analysis in early conceptual design stages.