House Block was designed and built using AUAR’s discrete housing system consisting of a kit of parts, known as Block Type A. Each block was CNC milled from a single sheet of plywood, assembled by hand, and then post-tensioned on site. Constructed from 270 identical blocks, there are no predefined geometric types or hierarchy between parts. The discrete enables an open-ended, adaptive system where each block can be used as a column, floor slab, wall, or stair—allowing for disconnection, reconfiguration, and reassembly (Retsin 2019). The democratisation of design and production that defines the discrete creates points for alternative value systems to enter, for critical realignments in architectural production.

CityMatrix was introduced to address these challenges. Machine learning techniques were applied to achieve real-time prediction of multiple urban simulations, and thousands of city configurations were simulated. The simulation results were used to train a convolutional neural network (CNN) to predict the traffic and solar performance of unseen city configurations. The prediction with the CNN is thousands of times faster than the original simulations and maintains a high-quality representation of the results. This machine learning approach was applied as a versatile, quick, accurate, and computationally efficient method not only for real-time feedback, but also for optimized design recommendations. Users involved in the evaluation of this project had a better understanding of the embodied trade-offs of the city and achieved their goals in an efficient manner.