1st Edition

The Routledge Companion to Artificial Intelligence in Architecture

Edited By Imdat As, Prithwish Basu Copyright 2021
    486 Pages 341 B/W Illustrations
    by Routledge

    486 Pages 341 B/W Illustrations
    by Routledge

    Providing the most comprehensive source available, this book surveys the state of the art in artificial intelligence (AI) as it relates to architecture. This book is organized in four parts: theoretical foundations, tools and techniques, AI in research, and AI in architectural practice. It provides a framework for the issues surrounding AI and offers a variety of perspectives. It contains 24 consistently illustrated contributions examining seminal work on AI from around the world, including the United States, Europe, and Asia. It articulates current theoretical and practical methods, offers critical views on tools and techniques, and suggests future directions for meaningful uses of AI technology. Architects and educators who are concerned with the advent of AI and its ramifications for the design industry will find this book an essential reference.

    Part 1 – Background, History and Theory of AI

    1. Significant Others: Machine Learning as Actor, Material, and Provocateur in Art and Design Kyle Steinfeld

    2. Sculpting Probabilistic Spaces: Brief History and Prospects of Machine Learning in Design Daniel Cardoso Llach

    3. Mapping generative models for architectural design Pedro Veloso,

    Ramesh Krishnamurti

    4. The Network of Interactions for an Artificial Architectural Intelligence Can Uzun

    Part 2 – AI Tools, Methods and Techniques

    5. Machine Learning in Architecture: An Overview of Existing Tool Ilija Vukorep,

    Anatolii Kotov

    6. Fundamental Aspects of Pattern Recognition in Architectural Drawing Tyler Kvochick

    7. AI as a collaborator in the early stage of design Sam Conrad Joyce

    8. AI in space planning Danil Nagy

    9. Generating new architectural designs using topological AI Prithwish Basu, Imdat As, Elizabeth Munch

    Part 3 – AI in Architectural Research

    10. Artificial Intelligence in Architectural Heritage Research: Simulating Networks of Caravanserais through Machine Learning Guzden Varinlioglu, Özgün Balaban

    11. A Deep Learning approach to Real Time Solar Radiation Prediction Theodoros Galanos, Angelos Chronis

    12. Artificial Intelligence and Machine Learning in Landscape Architecture Bradley Cantrell, Zihao Zhang, Xun Liu

    Part 4 – Case Studies of AI in Architecture

    13. Combining AI and BIM in the design and construction of a Mars habitat Naveen K. Muthumanickam, Jose Pinto Duarte, Shadi Nazarian, Ali Memari, Sven G. Bilén

    14. Towards Dynamic and Explorative Optimization for Architectural Design David Newton

    15. Synergizing smart building technologies with data analytics Andrzej Zarzycki

    16. Explainable ML: Augmenting the interpretability of numerical simulation using Bayesian networks Zack Xuereb Conti, Sawako Kaijima

    17. Image Analytics for Strategic Planning Aldo Sollazzo

    18. Urban Development Predictor SOM (Skidmore, Owings and Merrill)

    19. AI in Crowdsourced Design: Sourcing Collective Design Intelligence Imdat As, Prithwish Basu, Sergey Burukin

    20. Interfacing Architecture and Artificial Intelligence - Machine Learning for Architectural Design and Fabrication Bastian Wibranek, Oliver Tessmann

    21. Machining and machine learning: Extending architectural fabrication through AI Paul Nicholas

    22. Augmented Intuition - Encoding Ideas, Matter and why it matters Mathias Bernhard, Maria Smigielska, Benjamin Dillenburger

    23. AI & Architecture – An Experimental Perspective Stanislas Chaillou

    24. An Anonymous Composition: A Case Study of Form Finding Optimization through Machine Learning Algorithm Akshay Srivastava, Longtai Liao, Henan Liu

    25. Turbulent Intelligences: Liquid Architectures in Latent Spaces Marcos Novak

    Index

     

    Biography

    Imdat As is the recipient of the prestigious International Fellowship for Outstanding Researchers and a grant from the Scientific and Technological Research Council of Turkey (TUBITAK) and researches and teaches at the Istanbul Technical University (ITU). Imdat received his BArch from the Middle East Technical University (METU), his MSc in architecture from the Massachusetts Institute of Technology (MIT), and his doctorate from the Harvard University Graduate School of Design. He has coauthored Dynamic Digital Representations in Architecture: Visions in Motion (Taylor & Francis, 2008). In 2011, he founded Arcbazar.com, a first-of-its-kind crowdsourcing platform for architectural design, which has been featured as one of the "Top 100 Most Brilliant Companies" by Entrepreneur magazine. In 2017, he used Arcbazar’s design data through a DARPA-funded research project to generate conceptual designs via artificial intelligence (AI). Imdat is currently heading the City Design through Design Intelligence (CIDDI) lab at ITU and investigates the impact of emerging technologies on urban morphology and the future of the city.

    Prithwish Basu is a principal scientist at Raytheon BBN Technologies (BBN). He has a PhD in computer engineering from Boston University (2003) and a BTech in computer science and engineering from the Indian Institute of Technology (IIT), Delhi (1996). Prithwish has been the Principal Investigator of several U.S. government funded research projects on networking and network science during his 17-year tenure at BBN. He was the Program Director for U.S. Army Research Laboratory’s Network Science Collaborative Technology Alliance (NS CTA) program, which ran from 2009 until early 2020, and made fundamental contributions to advancing the state-of-the-art for the science of dynamic intertwined multigenre networks. Prithwish also led the DARPA-funded Fundamental Design (FUN Design) in 2017–2018, which explored the application of state-of-the-art AI/ML algorithms for graphs encoding architectural design data. Currently, he is leading the development of algorithms in the DARPA-funded FastNICs program for speeding up deep neural network (DNN) training by automatically parallelizing DNN workloads on fast network hardware. Prithwish recently served as an associate editor for the IEEE Transactions of Mobile Computing and was the lead guest editor for the IEEE Journal of Selected Areas in Communications (JSAC) special issue on network science. He has co-authored over 110 peer-reviewed articles (in conferences, journals, and book chapters) and has won the best paper award at IEEE NetSciCom 2014 and PAKDD 2014. He was also a recipient of the MIT Technology Review’s TR35 (Top 35 Innovators Under 35) award in 2006.