Rational Energy Architects (REAr)
project Background
Ng, P., Doria, D., Karastathi, N., Rivera Salaverry, C., & Fernandez, A. (2025, July). Cellular automata as a teacher of machine learning: A human-machine collaboration to contextualise environmental architecture. In Proceedings of The 7th International Conference on Computational Design and Robotic Fabrication (CDRF 2025), DigitalFUTURES, Tongji University, Shanghai.
synthetic dataset generation for machine learning
AI in+form Workshop Series
Technology Pipeline
The workshop develops with its participant a critical understanding towards the synthesis between various forms of intelligence, including designer intention, agent-based system, and machine learning.
Special thanks to CAADRIA 2021 and all workshop participants.
especially Riva Tomasowa, Giovanna Pillaca Morote, and Yuwen Qian for the documentation.
Design Showreel
The project aims to build interrelations between energy problem mapping, bio-inspired form-finding, and human-machine interactions to reflect and rethink the future of design.
Special thanks to DigitalFUTURES 2021 and all workshop participants.
Workshop Results
AI is being studied as rule/agent-based and machine learning (ML) systems. Working with constraints of proprietary softwares, the combinatorial pipeline interfaces Rhino, Grasshopper, Houdini, and Python implementations of algorithm Pix2pix.
Special thanks to CAADfutures 2021 and all workshop participants.
research paper
Ng, P., Fernandez, A., Doria, D., Odaibat, B., & Karastathi, N. (2021, November). AI In+form: Intelligence and Aggregation for Solar Designs in the Built Environment. In XXV International Conference of the Ibero-American Society of Digital Graphics | SIGraDi 2021 | Designing possibilities. https://doi.org/10.5151/sigradi2021-5
Sampled workshop outcomes
Panoramic gallery
01/15
Full lecture
Our approach emphasizes options over optimal solutions, channelling this to diversify solar designs that can be aggregated for diverse building topologies.
Instead of generating one design to be used for every solar problem, our pipeline focuses on AI informed workflows that generate families of designs that can be fabricated in similar methods using the same mathematical conception.
Contact Us
Better yet, see us in person!
We love our users, so feel free to visit us!
Schedule an appointment via email.
Address
The Univeristy of Hong Kong Pao Siu Loong Building, Pao Siu Loong Building, Lung Fu Shan, Hong Kong
Copyright © 2026 Digital Common(s) - All Rights Reserved.