Related Concept Videos
Polymer Classification: Architecture
Design Example: Aggregate Gradation
The grading, or particle-size distribution, of sand is determined using sieve analysis, with standard sizes ranging from 150 μm to 10 mm (ASTM No. 100 sieve to 3⁄8 in. sieve). Sand is...
Design Example: Sustainability in Concrete Building
There are multiple approaches to achieve sustainability in a commercial concrete building. For instance, construct a concrete parking area under the building, utilizing pervious concrete paver blocks in open areas to facilitate rainwater collection through an underground...
Spanning Openings in Brick Walls
Lintels are primary supports used to span openings and can be crafted from materials such as reinforced concrete, steel-reinforced brick masonry, or simple steel angles. These are straightforward to install and are typically concealed...
Position-effect Variegation
Gradient and Del Operator
You might also read
Related Articles
Articles linked to this work by shared authors, journal, and citation graph.
Evo-Devo Strategies for Generative Architecture: Colour-Based Patterns in Polygon Meshes.
Evo-Devo Algorithms: Gene-Regulation for Digital Architecture.
Multiphysics Investigation on Thermal Characteristics of Internal Bio-Inspired V-Ribbed Cooling Channels for Outer Rotor PMSM.
Smart Logistics Model for Supply Chain Management via Brain-Inspired Geometric Deep Networks.
A Systematic Taxonomy of the Sunflower Optimization Algorithm: Variants, Hybridization Strategies, Applications, and Research Directions.
Toward a Compositional Theory of Trust in Embodied Intelligence: A QNLP Framework for Modeling Context, Interaction, and Trustworthiness.
Empirical Logic for Bio-Inspired Soft Computing: Illustrative Applications in Control Engineering and Cluster Analysis.
A Modified Multi-Strategy Dhole Optimization Algorithm and Its Engineering Applications.
Related Experiment Video
Updated: Nov 15, 2025

Using Generative Art to Convey Past and Future Climate Transitions
Published on: March 31, 2023
Color-Patterns to Architecture Conversion through Conditional Generative Adversarial Networks.
Diego Navarro-Mateu1, Oriol Carrasco2, Pedro Cortes Nieves3
1School of Architecture, Universitat Internacional de Catalunya, 08017 Barcelona, Spain.
This study explores using gene regulatory patterns and machine learning to generate complex architectural designs. Conditional Generative Adversarial Networks (cGANs) are tested for coding architectural patterns into images and creating 2D representations.
Area of Science:
- Computational Design
- Artificial Intelligence in Architecture
- Generative Design
Background:
- Complex realities can be simplified into recognizable patterns found in nature.
- Architecture design consciously or unconsciously uses these patterns.
- Evo-Devo gene regulators and Machine Learning offer new design/analysis workflows.
Purpose of the Study:
- To test the feasibility of using conditional Generative Adversarial Networks (cGANs) for architectural pattern coding.
- To explore generating complex phenotypic architecture from genotypic patterns.
- To assess the potential of cGANs in creating novel architectural representations.
Main Methods:
- Utilizing conditional Generative Adversarial Networks (cGANs) to code architectural patterns.
- Translating color pattern-based images into 2D architectural representations.
- Conducting scaled tests to validate the hypothesis and network flexibility.
Main Results:
- Demonstrated feasibility of using cGANs for architectural pattern encoding.
- Successfully translated image patterns into 2D architectural forms.
- Assessed the adaptability of trained networks to novel, out-of-database cases.
Conclusions:
- Conditional Generative Adversarial Networks (cGANs) show promise as a tool for architectural design and analysis.
- This approach can generate complex architectural phenotypes from recognized patterns.
- Further research can explore disruptive workflows combining Evo-Devo principles and AI.

