Research Project // The Royal Danish Academy, 2021-2022
Visualising Change
A Chained Machine-Learning Approach to Motivate Retro-Cladding of Residential Buildings
Research project by: Paul Nicholas, CITA
Role: Research Assistant - Digital workflows, ML Dataset, Visualization
This project investigates how a novel approach to visualisation could help address the challenge of motivating residential retrofitting. Emerging retrofitting research and practice emphasises retro-cladding - the upgrading of the exterior facade of a building - using a modular approach. We present a machine-learning based approach aimed to motivate residential retrofitting through the generation of images and cost/benefit information describing climatically specific additions of external insulation and green roof panels to the façade of a Danish type house. Our approach chains a series of different models together, and implements amethod for the controlled navigation of the principle generative styleGAN model. The attached publication details our processes and considerations for the generation of new datasets, the specification and chaining of models, and the linking of climatic data to travel through the latent space of a styleGAN model to visualise and provide a simple cost-benefit report for retro-cladding specific to the local climates of five different Danish cities.
I worked closely with Paul to generate a parametric workflow to generate the visual dataset on which the machine was trained. The dataset included visualizations of all the different environmental scenarios and pre-defined parameters.
Related publication:
A Chained Machine Learning Approach to Motivate Retro- Cladding of Residential Buildings (eCAADe 2021: Towards a New, Configurable Architecture):
