AI Sampling Singapore Pensaernïaeth Tai by Immanuel Koh

AI Sampling Singapore Pensaernïaeth Tai by Immanuel Koh is a highly esteemed winner of the very prestigious 2025 Gwobr Haearn A' Design Award in Cynhyrchiol Competition Category.

HaearnCynhyrchiol· 2025

AI Sampling Singapore Pensaernïaeth Tai

by Immanuel Koh

Client: Immanuel Koh

Gwobr Haearn A' Design Award Winner in Cynhyrchiol Category

60,008

Verified Award Winner

Verify Award Status for #170593

Visit Site View at A' Design Award Press Release Award Badge

Colors

The Design

About AI Sampling Singapore Pensaernïaeth Tai

Mae Singapôr yn ddinas artiffisial. Wedi'i hyfforddi gyda set ddata fawr o fodelau digidol 3D o adeiladau uchel a geir yn Singapôr, mae'r model AI a ddyluniwyd yn arbennig nid yn unig yn cynhyrchu cyfluniadau sy'n gredadwy yn ffurfiol ac yn gydlynol yn semantig, ond mae hefyd yn dechrau dychmygu ffurfiau pensaernïol newydd a rhyfeddol, gan ryngosod ac allosod ymysg teipolegau tai uchel safonol megis y blociau slab, pwynt, a chlwstwr.

The Recognition

About the Gwobr Haearn A' Design Award

Mae AI Sampling Singapore Pensaernïaeth Tai yn enillydd Gwobr Haearn A' Design Award, cydnabyddiaeth fawreddog a roddir i ddyluniadau da sydd yn bodloni'r gofynion proffesiynol a diwydiannol a ddisgwylir gan greadigaethau wedi'u dylunio'n dda. Mae enillwyr Haearn yn dangos medrusrwydd mawr, arbenigedd uchel, dealltwriaeth arbenigol a gallu creadigol eu crewyr. Disgwylir i AI Sampling Singapore Pensaernïaeth Tai fod yn greadigaeth uchel ei bri, a edmygir ac a anwylir, sydd yn ymarferol ac yn arloesol. Mae'r dyluniad buddugol hwn o Wobr Haearn A' Design Award yn integreiddio arferion gorau'r diwydiant ac mae ganddo nodweddion technegol cymwys wedi'u cysylltu â gwybodaeth ymarferol a dawn. Parchir AI Sampling Singapore Pensaernïaeth Tai am ei drylwyredd ac fe'i dyluniwyd i ddarparu gwelliannau ansawdd bywyd sydd yn helpu i wneud y byd yn lle gwell.

Behind the Design

Press Kit

Credits, team members and technical details provided by the designer.

Unique Properties: Is it possible to sample at scale and at high-resolution every single building ever built in a country? If so, can such a dataset be used to train an AI model in generating new yet locally compliant buildings without any explicit regulatory control inputs? The project explores the design agency of deep generative neural networks in learning three-dimensional exteriority and interiority with a redesigned 3D generative adversarial network (3D-GAN) AI model. Winner of WAFX2024, IDA2024 and BLT2024.
Dimensions & Packaging: This is a digital AI x Architecture project. Each generated output is a new high-rise high-density residential public housing of up to 30 floors.
Tags: AI
Production Technology: A custom generative AI model was trained from scratch using proprietary code base and dataset. Specifically, a 3D generative adversarial network (3D-GAN) AI model was trained to learn semantic and spatial configuration of high-rise high-density residential public housing in Singapore.
Design Challenge: The non-existence of 3D models and their corresponding floor plans was the first challenge. New workflow and tools had to be developed to not only collect (i.e., digitally and physically), but create (annotate) and curate (i.e., exploratory data analysis) such high quality dataset to train an AI model from scratch. Technically difficult due to the scalability of similar CAD representation which was overcome via a novel AI latent representation of 3D.
Research: A custom generative AI model was trained from scratch using proprietary code base and dataset. Specifically, a 3D generative adversarial network (3D-GAN) AI model was trained to learn semantic and spatial configuration of high-rise high-density residential public housing in Singapore.
Inspiration: Singapore is an artificial city! Trained with a large dataset of 3D digital models of high-rise buildings found in Singapore, the custom-designed AI model generates not only formally plausible and semantically coherent configurations, but begins to also imagine novel and uncanny architectural forms, interpolating and extrapolating among standard high-rise housing typologies such as the slab, point, and cluster blocks. Project exhibited at Venice Architecture Biennale and Singapore's Arts House.
Project Duration: This is an on-going and longer-term AI x Architecture research being conducted at the university design lab since 2021. It was however only published much later as an official architectural design award entry from 2024 onwards.
Operation Flow: This is a digital AI x Architecture generative research project, while the dataset was digitally collected from existing physical buildings in Singapore.
Patents: Currently no patent.
Team Members: Artificial-Architecture
Image Credits: All credits: Artificial-Architecture