Machine learning for generative architectural design: Advancements, opportunities, and challenges

被引：0
作者：
Zhuang, Xinwei [1 ]
Zhu, Pinru [1 ]
Yang, Allen [2 ]
Caldas, Luisa [1 ]
机构：
[1] Univ Calif Berkeley, Dept Architecture, Berkeley, CA 94720 USA
[2] Univ Calif Berkeley, Dept Elect Engn & Comp Sci, Berkeley, CA 94720 USA
来源：
AUTOMATION IN CONSTRUCTION | 2025年 / 174卷
关键词：
Generative design; Machine learning; Artificial intelligence; Design exploration; Design optimization;
D O I：
10.1016/j.autcon.2025.106129
中图分类号：
TU [建筑科学];
学科分类号：
0813 ;
摘要：
Generative design has its roots in the 1990s and has become an intense research topic for bringing the power of artificial intelligence to various aspects of architecture practices. The recent advancements in artificial intelligence have made a methodological shift in innovative approaches to generative design, fueled by the proliferation of big data. This paper provides a comprehensive review of emerging machine learning algorithms and their applications in architecture. It investigates the concepts and principles behind machine learning, assesses the strengths and limitations of current algorithms, and examines their applications and exploratory uses with a data-centric approach. This work aims to assess current research, identify emerging opportunities and challenges, and suggest viable solutions for future investigations. This work contributes to a deeper understanding of the rapidly evolving landscape of machine learning in architecture, shedding light on how the field can adapt to and leverage these transformative changes.
引用
收藏
页数：20
相关论文
共 161 条
[31]  
El Bouchefry K., 2020, Knowledge Discovery in Big Data from Astronomy and Earth Observation, DOI [10.1016/B978-0-12-819154-5.00023-0, DOI 10.1016/B978-0-12-819154-5.00023-0]
[32]  
Emmons Paul., 2006, The Journal of Architecture, V11, P441, DOI DOI 10.1080/13602360601037867
[33]  
Fan Z., 2021, arXiv, DOI [10.48550/arXiv.2105.07147, DOI 10.48550/ARXIV.2105.07147]
[34]   Autonomous robotic additive manufacturing through distributed model‐free deep reinforcement learning in computational design environments [J].
Benjamin Felbrich ;
Tim Schork ;
Achim Menges .
Construction Robotics, 2022, 6 (1) :15-37
[35]  
FISHER RA, 1954, STAT METHODS RES WOR, DOI [DOI 10.1007/978-1-4612-4380-96, 10.1007/978-1-4612-4380-9_6, DOI 10.1007/978-1-4612-4380-9_6]
[36]  
Frazer J., 1995, An evolutionary architecture
[37]   Artificial neural networks (the multilayer perceptron) - A review of applications in the atmospheric sciences [J].
Gardner, MW ;
Dorling, SR .
ATMOSPHERIC ENVIRONMENT, 1998, 32 (14-15) :2627-2636
[38]  
Gebru T, 2021, Arxiv, DOI [arXiv:1803.09010, DOI 10.48550/ARXIV.1803.09010, 10.1145/3458723]
[39]   Garbage In, Garbage Out? Do Machine Learning Application Papers in Social Computing Report Where Human-Labeled Training Data Comes From? [J].
Geiger, R. Stuart ;
Yu, Kevin ;
Yang, Yanlai ;
Dai, Mindy ;
Qiu, Jie ;
Tang, Rebekah ;
Huang, Jenny .
FAT* '20: PROCEEDINGS OF THE 2020 CONFERENCE ON FAIRNESS, ACCOUNTABILITY, AND TRANSPARENCY, 2020, :325-336
[40]  
Geyer P, 2024, Arxiv, DOI arXiv:2108.13836
12345678910