هوش مصنوعی و نقش آن در تحول آموزش و طراحی معماری پایدار: فرصت‌ها و چالش‌ها

محورهای موضوعی : جغرافیا و معماری

دکتر شبنم اکبری نامدار ¹ , الناز زرگین ²

1 - استادیار گروه معماری وشهرسازی، واحد تبریز، دانشگاه آزاد اسلامی، تبریز، ایران
2 - دانشجوی دکتری معماری، واحد تبریز، دانشگاه آزاد اسلامی، تبریز، ایران

تاریخ دریافت : 1404/02/12 تاریخ پذیرش : 1404/04/31 تاریخ انتشار : 1404/10/01

کلید واژه: هوش مصنوعی, آموزش معماری, طراحی معماری, معماری پایدار, فرصت‌ها و چالش‌ها,

چکیده مقاله :

رشد روزافزون فناوری‌های هوش مصنوعی، زمینه‌ساز تحول بنیادین در آموزش و طراحی معماری شده است. این پژوهش با رویکرد توصیفی - تحلیلی و بهره‌گیری از روش‌های کیفی مانند تحلیل محتوا و تحلیل شبکه‌ای با نرم‌افزار VOSviewer، به بررسی نقش هوش مصنوعی در ارتقای کیفیت آموزش معماری، یادگیری انطباقی و طراحی پایدار پرداخته است. فرضیه پژوهش آن است که پیاده‌سازی دقیق و بومی‌سازی‌شدن فناوری‌های هوش مصنوعی، می‌تواند از طریق تلفیق تحلیل داده‌محور، بازخورد بلادرنگ و تعامل انسان - ماشین، منجر به بهبود فرایندهای آموزشی و خلق طراحی‌های نوآورانه و پایدار شود. با تحلیل محتوای ۱۲۰ مقاله منتخب، مدلی مفهومی سه‌لایه ارائه گردید که شامل: زیرساخت فناورانه (شامل الگوریتم‌های یادگیری و شبیه‌سازی‌ها)، خلاقیت انسانی و تعامل انسان - ماشین، و بومی‌سازی فرهنگی و اقلیمی است. یافته‌ها نشان می‌دهد تحقق این تحول مستلزم تقویت زیرساخت‌های فناورانه، ارتقای سواد دیجیتال، و بازنگری در ساختارهای آموزشی است. این پژوهش با تأکید بر هم‌افزایی میان قوه خلاق انسانی و قابلیت‌های فناورانه، هوش مصنوعی را به‌عنوان عاملی تحول‌آفرین در آموزش و طراحی معماری معرفی می‌کند.

کلمات کلیدی: هوش مصنوعی، آموزش معماری، طراحی معماری، معماری پایدار، فرصت‌ها و چالش‌ها

چکیده مبسوط فارسی

مقدمه  

تحولات پرشتاب فناوری به‌ویژه در حوزه هوش مصنوعی، چشم‌انداز تازه‌ای پیشروی آموزش و طراحی معماری گشوده‌اند؛ حوزه‌ای که ذات میان‌رشته‌ای آن، همواره نیازمند پاسخ‌گویی خلاقانه به چالش‌هایی چون بهینه‌سازی عملکرد، تحقق پایداری و تقویت فرایندهای تصمیم‌گیری بوده است. هوش مصنوعی، با ظرفیت تحلیل داده‌های پیچیده و تولید راهکارهای هوشمند، امکان ارتقای کیفی در آموزش و طراحی را فراهم ساخته است. با این‌ حال، بیشتر پژوهش‌های موجود، نگاهی سطحی به این ظرفیت داشته و از درک عمیق تعامل انسان و ماشین، نقش خلاقیت انسانی و ضرورت بومی‌سازی غافل مانده‌اند. این پژوهش بر آن است تا از منظری انسان‌محور و بومی‌شده، چارچوبی کاربردی برای بهره‌برداری هدفمند از هوش مصنوعی در آموزش و طراحی معماری ارائه دهد؛ چارچوبی که علاوه بر ارتقای کیفیت یادگیری، به پرورش خلاقیت و تسهیل تصمیم‌گیری‌های پایدار نیز بینجامد. در این مسیر، به‌جای تمرکز صرف بر فناوری، بر تعامل خلاق انسان با ماشین و نقش زمینه‌های فرهنگی - اجتماعی در پذیرش فناوری تأکید شده است. براین‌اساس، فرضیه پژوهش بر این اصل استوار است که پیاده‌سازی دقیق، هوشمند و زمینه‌مند فناوری‌های هوش مصنوعی، می‌تواند تحولی بنیادین در آموزش و طراحی معماری رقم زند؛ تحولی که نه جایگزینی انسان، بلکه ارتقای توانمندی‌های انسانی را هدف قرار می‌دهد.

 داده و روش

پژوهش حاضر با رویکردی کاربردی و توصیفی - تحلیلی، بر آن است تا با بهره‌گیری از مرور نظام‌مند منابع علمی دهه اخیر، مدلی مفهومی برای به‌کارگیری هوش مصنوعی در آموزش و طراحی معماری تدوین کند. برای گردآوری داده‌ها، ۱۲۰ مقاله منتخب از پایگاه‌های معتبر نظیر Scopus، Web of Science و Google Scholar با کلیدواژه‌های تخصصی تحلیل شدند. در مرحله تحلیل، داده‌ها به دو شیوه مکمل بررسی شدند. تحلیل کتاب‌سنجی با نرم‌افزار VOSviewer به‌منظور ترسیم شبکه‌های هم‌واژگانی و هم نویسندگی که سه خوشه اصلی مفهومی (فناوری‌های AI، آموزش شخصی‌سازی‌شده، طراحی پایدار و خلاقانه) را شناسایی کرد.

 

  شکل ۱: آموزش طراحی معماری و AI در vos viewer

مأخذ: نگارندگان

تحلیل محتوای کیفی با روش کدگذاری دستی برای استخراج شاخص‌های کلیدی، فرصت‌ها و چالش‌های بومی‌سازی AI در آموزش معماری. در نتیجه این تحلیل‌ها، مدل مفهومی سه‌لایه‌ای با تمرکز بر تعامل میان زیرساخت فناورانه، خلاقیت انسانی و بوم‌گرایی فرهنگی طراحی شد؛ مدلی که ابعاد کلیدی آموزش و طراحی معماری در عصر هوش مصنوعی را به‌صورت تلفیقی بازنمایی می‌کند.

 

شکل ۲: مدل مفهومی سه‌لایه تعامل هوش مصنوعی با آموزش معماری

مأخذ: نگارندگان

همچنین، با تحلیل ساختاری مدل، روابط علی میان سه‌لایه اصلی بررسی و نقشه عملکردی هریک از لایه‌ها در تعامل با دیگری ترسیم شد.

 بحث و یافته ها

تحلیل‌های انجام‌شده نشان‌دهنده آن است که به‌رغم ظرفیت‌های قابل‌توجه هوش مصنوعی در تحول آموزش و طراحی معماری، چالش‌ها و محدودیت‌های متعددی از جمله کمبود زیرساخت‌های فناورانه، نابرابری دسترسی، و ضعف آمادگی تخصصی اساتید، موانع فرهنگی و مقاومت در برابر پذیرش فناوری‌های نوین، و نیز دغدغه‌های اخلاقی و اجتماعی، همچنان سد راه توسعه کامل این فناوری‌ها در این حوزه است. هوش مصنوعی، اگرچه توانایی تحلیل داده‌های پیچیده و بهینه‌سازی فرایندهای طراحی را دارد، اما نمی‌تواند جایگزین خلاقیت، قضاوت و درک زمینه‌ای انسانی شود و باید به‌عنوان ابزاری مکمل و تعاملی در خدمت افزایش دقت، خلاقیت و پایداری طراحی مورد بهره‌برداری قرار گیرد. تحقق موفق این چشم‌انداز نیازمند توسعه زیرساخت‌های فناورانه پیشرفته، آموزش میان‌رشته‌ای تخصصی برای اساتید و دانشجویان، ارتقای سواد دیجیتال، و تدوین چارچوب‌های اخلاقی شفاف است. علاوه بر این، ترکیب هوش مصنوعی با اصول طراحی پایدار و بومی‌سازی فرهنگی می‌تواند فرصت‌های نوینی در بازآفرینی محیط‌های معماری پایدار، به‌ویژه در بافت‌های صنعتی متروکه و نمونه‌های بومی همچون تبریز، ایجاد کند. مدل سه‌لایه مفهومی ارائه‌شده، تعامل هماهنگ میان فناوری، خلاقیت انسانی و زمینه فرهنگی را به‌عنوان کلید موفقیت بومی‌سازی هوش مصنوعی معرفی می‌کند و می‌تواند راهنمای راهبردی برای سیاست‌گذاران، برنامه‌ریزان آموزشی و فعالان حوزه معماری باشد. در نهایت، هوش مصنوعی نه‌تنها ابزاری فناورانه، بلکه محرکی بنیادین در ارتقای کیفیت آموزش، خلاقیت طراحی و تحقق معماری پایدار آینده قلمداد می‌شود.

نتیجه‌گیری

پژوهش حاضر نشان داد که فناوری‌های هوش مصنوعی می‌توانند نقشی کلیدی و تحول‌آفرین در فرایندهای آموزش و طراحی معماری ایفا کنند؛ اما تحقق این تحول، منوط به پیاده‌سازی هدفمند، دقیق و متناسب با بسترهای بومی است. استفاده از فناوری‌هایی نظیر سیستم‌های یادگیری انطباقی، بازخوردهای بلادرنگ و الگوریتم‌های تولید فرم خلاقانه، به طور قابل‌توجهی کیفیت آموزش را ارتقا داده و خلاقیت و پایداری در طراحی معماری را تقویت می‌کند. علاوه بر این، توجه به فرهنگ‌سازمانی، توسعه زیرساخت‌های فناورانه و ارتقای مهارت‌های میان‌رشته‌ای و سواد دیجیتال در میان اساتید و دانشجویان، از مهم‌ترین پیش‌نیازهای موفقیت بهره‌برداری از هوش مصنوعی در محیط‌های آموزشی و حرفه‌ای معماری به شمار می‌روند. یافته‌های تحلیل‌های کتاب‌سنجی و کیفی، نقش‌محوری فناوری‌های یادگیری ماشین، آموزش انطباقی و تولید فرم‌های نوآورانه را در این مسیر تأیید می‌کنند. مدل مفهومی سه‌لایه ارائه شده، با تمرکز بر تعامل هم‌افزا میان زیرساخت فناورانه، خلاقیت انسانی و بومی‌سازی فرهنگی، چارچوبی جامع برای فهم فرصت‌ها و چالش‌های به‌کارگیری هوش مصنوعی در آموزش معماری فراهم آورده است. این مدل می‌تواند راهنمایی مؤثر برای بازنگری در سرفصل‌های درسی، طراحی دوره‌های میان‌رشته‌ای، تقویت زیرساخت‌ها و توانمندسازی نیروی انسانی باشد. در نهایت، هوش مصنوعی فراتر از یک ابزار فناورانه صرف، به‌عنوان عاملی محرک و تحول‌آفرین در ارتقای کیفیت آموزش، خلاقیت طراحی و پایداری معماری آینده مطرح است؛ لذا اتخاذ رویکردی نظام‌مند و آینده‌نگر در توسعه کاربردهای هوش مصنوعی در آموزش و طراحی معماری، به‌ویژه در زمینه‌های بومی، امری ضروری و راهبردی است.

 

منابع ومآخذ

• اکبری نامدار، شبنم، خدائی، هانیه. (۱۴۰۴). بازآفرینی فضای معماری ازیادرفته، طرحی برای توسعه معماری پایدار (نمونه موردی: فضاهای صنعتی در تبریز). اندیشه‌های نو در علوم جغرافیایی،۹(۳)،۱-۱۶.
• کمایی، سپیده، کابلی، دکتر احمدرضا، (۱۴۰۳). ارزیابی معماری ایرانی و تعاملات اجتماعی در فضاهای فرهنگی. اندیشه‌های نو در علوم جغرافیایی،۳(۲)،۴۷-۶۲.
• Almarashdeh, I. (2021). The role of artificial intelligence in enhancing online learning: A study in architecture education. International Journal of Educational Technology, 32(2), 87–103.
• Alsharif, N., Al-Zahrani, A., Al-Mutairi, M., & Baqadir, A. (2020). Integration of AI in VR and AR for architecture education. Journal of Educational Technology & Society, 23(4), 45–58.
• Aluko, R. O., Adenuga, O. A., Kukoyi, P. O., Soyingbe, A. A., & Oyedeji, J. O. (2016). Predicting the academic success of architecture students by pre-enrolment requirement: Using machine-learning techniques. Construction Economics and Building, 16(4), 86–98.
• Aluko, R. O., Daniel, E. I., Oshodi, O., & Aigbavboa, C. (2018). Towards reliable prediction of academic performance of architecture students using data mining techniques. Journal of Engineering, Design and Technology, 16(1), 57–68.
• Azhar, S. (2011). Building information modeling (BIM): Benefits, risks, and challenges. International Journal of Advanced Engineering Technology, 4(3), 79–83.
• Binns, S. (2020). Ethical challenges of artificial intelligence in architectural education. Journal of Architecture and Ethics, 5(2), 113–127.
• Björk, B.-C. (1999). The future of building information modeling. CIB Publication 2.
• Bonnardot, L., Dupuis, M., & Rondeau, J. (2021). Artificial intelligence in architecture design: Challenges and implications for creativity. Journal of Architectural Computing, 32(4), 225–239.
• Borges, A., Pinto, A., & Duarte, P. (2021). Computational intelligence in architectural design: An evolutionary approach. Springer.
• Brynjolfsson, E., & McAfee, A. (2022). The second machine age: Work, progress, and prosperity in a time of brilliant technologies. W. W. Norton & Company.
• Cao, Y., Gao, X., Yin, H., Yu, K., & Zhou, D. (2024). Reimagining tradition: A comparative study of artificial intelligence and virtual reality in sustainable architecture education. Sustainability, 16(24), 11135.
• Chien, C., & Lee, C. (2021). Adaptive learning systems in architectural education: AI for personalizing design education. Architectural Science Review, 64(1), 45–57.
• Chien, S., Lee, S., & Wang, L. (2021). EvoArch: An evolutionary algorithm for architectural layout design. ResearchGate.
• Eastman, C., Teicholz, P., & Sacks, R. (2018). BIM handbook: A guide to building information modeling for owners, designers, engineers, contractors, and fabricators (2nd ed.). Wiley.
• Garcia, R., et al. (2022). Enhancing architectural learning with AI, VR, and AR. Education and Design Journal, 32(2), 78–94.
• Gero, J. S., & Maher, M. L. (2020). Computational models in architecture. Springer.
• Ghaffarianhoseini, A., Ghaffarianhoseini, A., & Alwaer, H. (2021). Artificial intelligence in architecture and building design: A comprehensive review of current applications. Automation in Construction, 123, 103541.
• Goh, A., & Chow, W. (2021). The role of AI in the transformation of architectural education and design practices. Journal of Educational Technology and Design, 25(1), 51–67.
• Günay, H., Aldridge, L., & Ghanbari, M. (2023). Artificial neural networks for sustainable architectural design: Energy efficiency and material selection. Journal of Building Engineering, 61, 105227.
• Hosseini, M., & Nikbakht, A. (2022). Smart platforms in architecture: A review on AI-driven tools in education and design. Architectural Technology Review, 34(4), 289–305.
• Huang, C., & Zhang, J. (2021). Social and ethical considerations in AI applications for architectural education. International Journal of AI & Architecture, 13(2), 118–134.
• Jabareen, H. (2022). Smart design technologies in architecture. Routledge.
• Jha, P., & Sharma, P. (2021). Integrating AI in architectural education: A pathway to innovation. Journal of Architectural Education, 78(3), 152–165.
• Jin, S., Tu, H., Li, J., Fang, Y., Qu, Z., Xu, F., Liu, K., & Lin, Y. (2024). Enhancing architectural education through artificial intelligence: A case study of an AI-assisted architectural programming and design course. Buildings, 14(6), 1613.
• Kim, H., Cho, C. Y., & Hong, S. W. (2023). Impact of agent‑based simulation on novice architects’ workplace design exploration and trade‑offs. Automation in Construction, 145, 104635.
• Kiviniemi, M. (2014). BIM and intelligent systems in architecture. Elsevier.
• Koh, J., Tan, K., & Lee, Y. (2022). Deep learning in architectural form generation: Applications and challenges. Computers, Environment and Urban Systems, 90, 101720.
• Kotsiantis, S. B., Zervas, P. G., & Kalliris, D. (2023). AI in architectural education: Overcoming resistance to new technologies. International Journal of Architectural Education, 47(1), 45–59.
• Koutamanis, A. (2020). Architectural design and artificial intelligence: A review of the role of creativity in design processes. Design Studies, 69(1), 1–17.
• Leung, K., & Chan, M. (2022). AI in learning analytics for architecture education. Education and Technology Journal, 27(4), 430–445.
• Li, B. (2023). Educational challenges and opportunities for integrating AI in architectural design: A global perspective. Journal of Educational Technology, 44(2), 234–250.
• Li, W., Zhang, Y., & Wang, F. (2023). Optimization of energy and cost in building design using genetic algorithms. ScienceDirect.
• Li, X., Xie, Y., & Zhang, M. (2022). Fuzzy logic and evolutionary algorithms in design decision making. Cambridge University Press.
• Liu, J., Tan, Z., & Wang, Q. (2022). AI-based personalization and adaptive learning in architecture: Enhancing learning processes and outcomes. Education and Information Technologies, 27(6), 8607–8625.
• Lu, Y., Wu, W., Geng, X., Liu, Y., Zheng, H., & Hou, M. (2022). Multi-objective optimization of building environmental performance: An integrated parametric design method based on machine learning approaches. Building and Environment, 208, 108629.
• Miao, Y., Wu, J., Zhang, H., & Shen, G. Q. (2020). Understanding the role of artificial intelligence in construction project management. Automation in Construction, 122, 103465.
• Newton, D. (2019). Generative deep learning in architectural design. Technology|Architecture+Design, 3(2), 176–189.
• Nguyen, T., Le, T., & Tran, H. (2022). Artificial intelligence in architectural education: Revolutionizing learning processes. Journal of Architectural Education, 76(4), 123–139.
• Papageorgiou, D., & Nikolaou, M. (2023). AI in architecture education: Automated assessment and student performance analysis. International Journal of Educational Technology in Higher Education, 20(1), 1–19.
• Patel, M., & Lee, J. (2023). Generative design in architecture: Harnessing the power of deep learning. Frontiers of Architectural Research, 12(2), 250–265.
• Perkins, S., et al. (2021). AR and AI in architecture: A new educational approach. Architectural Technology Journal, 19(2), 99–110.
• Ralston, P. A. S., Hoye, J. D., & Rambo-Hernandez, K. E. (2019). Building better engineers: A study of academic and career success in engineering with implications for education and diversity. International Journal of STEM Education, 6(1), 1–12.
• Salem, O. (2021). Financial and infrastructural barriers to AI implementation in architecture education. International Journal of Technology and Education, 29(3), 203–217.
• Schwab, K. (2021). The fourth industrial revolution. Penguin.
• Serban, O., Thies, W., & Roussev, B. (2020). Machine learning in architecture: A review. Automation in Construction, 119, 103339.
• Shahin, A., Farooq, M., & Rehman, A. (2021). Developing AI skills in architecture education: Strategies for faculty development. Journal of Architectural Education, 60(2), 94–110.
• Smith, A., Wang, J., & Brown, C. (2021). AI in architecture: Integrating machine learning with architectural design. Routledge.
• Sun, Y., Zhao, X., & Li, F. (2022). Artificial intelligence in architectural education: Overcoming challenges and enhancing skills. Educational Review, 28(1), 99–113.
• Swan, M., & Lile, B. (2020). Artificial intelligence in architecture: Financial and infrastructure challenges. Journal of Building Education, 35(2), 243–257.
• Tegos, S., Vassiliou, A., & Andreou, D. (2023). The future role of artificial intelligence in architectural and interior design education to improve efficiency, sustainability, and creativity. ResearchGate.
• Törmä, M., Heikkilä, S., & Salo, A. (2020). Advanced data analysis algorithms for architectural design. Journal of Architecture and Urban Planning, 12(2), 233–245.
• Wang, Y., Huang, J., & Zhang, Z. (2022). Machine learning applications in architecture and design. Wiley.
• Wang, Z., Hu, Z., & Fang, D. (2021). Artificial intelligence in architecture: Emerging trends and future prospects. Journal of Architectural and Planning Research, 38(3), 205–220.
• Yang, M., Li, X., & Wang, Y. (2021). Neural networks in architecture: From design to construction. Springer.
• Yuan, W., Li, Z., & Zhao, X. (2021). Using machine learning and genetic algorithms for energy optimization and cost reduction in building design. ScienceDirect.
• Zhang, L., Wu, Y., & Yang, J. (2023). Using machine learning to simulate building behavior and improve design decisions. ScienceDirect.
• Zhao, Y., & Wang, X. (2023). AI-driven smart architecture: The future of building design and construction. Elsevier.
• Zhu, W., Chen, R., Lin, J., & Zhou, H. (2023). Machine learning for architectural design prediction. Journal of Computational Architecture, 17(1), 220–233.
• Zhuang, X., Zhu, P., Yang, A. Y., & Caldas, L. (2025). Machine learning for generative architectural design: Advancements, opportunities, and challenges. Automation in Construction, 174, 106129.

چکیده انگلیسی:

The rapid of development  of artificial intelligence (AI) technologies has laid  a  fundamental evolution in architectural education and design. This research has been implemented  using a descriptive-analytical approach and utilizing qualitative methods such as content analysis and network analysis with VOSviewer software to investigate the role of AI in enhancing the quality of architectural education, adaptive learning processes and sustainable design practices. The research hypothesis assumes that the accurate implementation and localization of AI technologies, through the integration of data-driven analysis, real-time feedback and human-machine interaction can significantly improve educational methodologies and the creation of innovative and sustainable designs. By analyzing the content of 120 selected  papers, this study was presented a three-layer conceptual model including : technological infrastructure (including learning algorithms and simulation tools), human creativity and human-machine interaction and cultural and climatic localization. The findings suggest that realizing this evolution  requires the reinforcement of technological infrastructure, enhancement of digital literacy, and reformation in educational structures. This study  emphasizes   the synergy between human creativity and technological capabilities and it introduces AI as a  transformative factor in education and  architectural design.

Keywords: Artificial Intelligence, Architectural Education, Architectural Design, Sustainable agriculture , Opportunities and Challenges

Extended Abstract

Introduction

The rapid advancement  especially in the field of artificial intelligence (AI) has opened a new perspective for architectural education and design , a field inherently interdisciplinary has always required creative responses to challenges such as performance optimization, , achieving sustainability and creative decision-making . Artificial intelligence (AI)  with its capacity  to analyze complex data and intelligent solution generation has enabled qualitative improvements in education and design. However, existing studies  have  only a superficial view of this capacity and have overlooked a deeper understanding of human-machine interaction, the role of human creativity and the necessity of localization .This research aims to present an applied framework for the purposeful utilization of artificial intelligence in education and architectural design from a human-centered and localized perspective; a framework that  in addition to improving the quality of learning but it also leads   to nurture creativity and facilitate sustainable decision-making.This study has been emphasized  on the creative interaction between human and machine and  the role of cultural and social contexts in the adoption of technology instead of solely focusing on technology. Accordingly ,  the research hypothesis is founded on the principle that implementation of  precise, intelligent and context-aware of artificial intelligence technologies can create a fundamental evolution in education and architectural design; a transformation that does not aim to replace human but rather to promote  human abilities.

 Data and Method

This present study  has a  descriptive-analytical approach and it aims to develop a conceptual model for the application of artificial intelligence in education and architectural design by utilizing a systematic review of scientific sources from the past decade. To collect  data, 120 selected papers from reputable databases such as Scopus, Web of Science and Google Scholar were analyzed using specialized keywords. In the analysis phase, the data were examined using two complementary  methods:

Bibliometric analysis using VOSviewer software was conducted to visualize co-occurrence and co-authorship networks, which identified three main conceptual clusters: AI technologies, personalized education and sustainable and creative design.

Bibliometric Analysis:
Using VOSviewer software, co-word and co-authorship networks were mapped. This analysis identified three major conceptual clusters:
 (1) Core AI technologies,
 (2) Personalized and adaptive learning in architecture,
 (3) Sustainable and creative design processes.

   

Figure 1: Architectural Design Education and AI Visualization in VOSviewer

Qualitative content analysis using manual coding to extract key indicators, opportunitiesand localization challenges of AI in architectural education. As a result of these analyses , a three-layer conceptual model was developed , focusing on  the interaction between technological infrastructure, human creativityand cultural contextualization ; a model that integratively represents the key dimensions of architecture education and design in the age of artificial intelligence.

 

Figure 2: Three-layer conceptual model of the interaction between artificial intelligence and architectural education

Moreover, through structural analysis of the model, causal relationships among the three main layers were examined, and the functional map of each layer in interaction with the others was delineated.

 Results and Discussion

 These analyses indicate that despite the considerable potential of artificial intelligence (AI) to transform architectural education and design, multiple challenges and limitations persist. These include insufficient technological infrastructure, unequal access, inadequate specialized preparedness among faculty, cultural barriers and resistance to adopting modern technologies, as well as ethical and social concerns that continue to hinder the full development of AI applications in this field. Although AI possesses the capability to analyze complex data and optimize design processes, it cannot replace human creativity, judgment, and contextual understanding. Therefore, AI should be employed as a complementary and interactive tool to enhance accuracy, creativity, and sustainability in design. Successful realization of this vision requires the advancement of sophisticated technological infrastructures, interdisciplinary specialized training for both professors  and students, enhancement of digital literacy, and the formulation of clear ethical frameworks. Moreover, integrating AI with principles of sustainable design and cultural localization can create new opportunities for the revitalization of sustainable architectural environments, particularly within industrial brownfields and indigenous contexts such as the city of Tabriz. The proposed three-layer conceptual model highlights the coordinated interaction among technology, human creativity and cultural context as the key to successful localization of  AI. This model can serve as a strategic guide for policymakers, educational planners and architectural professionals.Finally, AI is not merely a technological tool but a fundamental catalyst for improving educational quality, design creativity and achieving sustainable architecture for the future.

 Conclusion

This present study indicated that artificial intelligence technologies can play a key and transformative role in the processes of architectural education and design; however, realizing this evolution depends on purposeful, precise implementation tailored to local contexts. The utilization of technologies such as adaptive learning systems, real-time feedback  and algorithms of creative form generation significantly enhances the quality of education and strengthens creativity and sustainability in architectural design. In addition , attention to organizational culture, development of technological infrastructure and the advancement of interdisciplinary skills and digital literacy among professors and students are the most critical prerequisites for successful utilization of AI in both educational and professional architectural environments. Findings from bibliometric and qualitative analyses confirm the central role of machine learning technologies, adaptive education, and innovative form generation on this path. The presented three-layer conceptual model focusing  the synergistic interaction among technological infrastructure, human creativity and cultural localization provides a comprehensive framework for understanding the opportunities and challenges of applying AI in architectural education. This model can serve as an effective guide for revising curriculam , designing interdisciplinary courses, strengthening infrastructures and empowering human resources. Finally , artificial intelligence transcends being a mere technological tool, positioning itself as a driving and transformative force in enhancing the quality of education, design creativity and the sustainability of future architecture. Therefore, adopting a systematic and forward-looking approach to the development of AI applications in architectural education and design—particularly within local contexts—is essential and strategic.

             

References   

• Akbari Namdar, Shabnam, & Khodaei, Hanieh. (2025). Revitalizing Forgotten Architectural Spaces: A Proposal for Sustainable Architecture Development (Case Study: Industrial Spaces in Tabriz). New Ideas in The Geographical Sciences, 9(3), 1-16. (in Persian)
• Almarashdeh, I. (2021). The role of artificial intelligence in enhancing online learning: A study in architecture education. International Journal of Educational Technology, 32(2), 87–103.
• Alsharif, N., Al-Zahrani, A., Al-Mutairi, M., & Baqadir, A. (2020). Integration of AI in VR and AR for architecture education. Journal of Educational Technology & Society, 23(4), 45–58.
• Aluko, R. O., Adenuga, O. A., Kukoyi, P. O., Soyingbe, A. A., & Oyedeji, J. O. (2016). Predicting the academic success of architecture students by pre-enrolment requirement: Using machine-learning techniques. Construction Economics and Building, 16(4), 86–98.
• Aluko, R. O., Daniel, E. I., Oshodi, O., & Aigbavboa, C. (2018). Towards reliable prediction of academic performance of architecture students using data mining techniques. Journal of Engineering, Design and Technology, 16(1), 57–68.
• Azhar, S. (2011). Building information modeling (BIM): Benefits, risks, and challenges. International Journal of Advanced Engineering Technology, 4(3), 79–83.
• Binns, S. (2020). Ethical challenges of artificial intelligence in architectural education. Journal of Architecture and Ethics, 5(2), 113–127.
• Björk, B.-C. (1999). The future of building information modeling. CIB Publication 2.
• Bonnardot, L., Dupuis, M., & Rondeau, J. (2021). Artificial intelligence in architecture design: Challenges and implications for creativity. Journal of Architectural Computing, 32(4), 225–239.
• Borges, A., Pinto, A., & Duarte, P. (2021). Computational intelligence in architectural design: An evolutionary approach. Springer.
• Brynjolfsson, E., & McAfee, A. (2022). The second machine age: Work, progress, and prosperity in a time of brilliant technologies. W. W. Norton & Company.
• Cao, Y., Gao, X., Yin, H., Yu, K., & Zhou, D. (2024). Reimagining tradition: A comparative study of artificial intelligence and virtual reality in sustainable architecture education. Sustainability, 16(24), 11135.
• Chien, C., & Lee, C. (2021). Adaptive learning systems in architectural education: AI for personalizing design education. Architectural Science Review, 64(1), 45–57.
• Chien, S., Lee, S., & Wang, L. (2021). EvoArch: An evolutionary algorithm for architectural layout design. ResearchGate.
• Eastman, C., Teicholz, P., & Sacks, R. (2018). BIM handbook: A guide to building information modeling for owners, designers, engineers, contractors, and fabricators (2nd ed.). Wiley.
• Garcia, R., et al. (2022). Enhancing architectural learning with AI, VR, and AR. Education and Design Journal, 32(2), 78–94.
• Gero, J. S., & Maher, M. L. (2020). Computational models in architecture. Springer.
• Ghaffarianhoseini, A., Ghaffarianhoseini, A., & Alwaer, H. (2021). Artificial intelligence in architecture and building design: A comprehensive review of current applications. Automation in Construction, 123, 103541.
• Goh, A., & Chow, W. (2021). The role of AI in the transformation of architectural education and design practices. Journal of Educational Technology and Design, 25(1), 51–67.
• Günay, H., Aldridge, L., & Ghanbari, M. (2023). Artificial neural networks for sustainable architectural design: Energy efficiency and material selection. Journal of Building Engineering, 61, 105227.
• Hosseini, M., & Nikbakht, A. (2022). Smart platforms in architecture: A review on AI-driven tools in education and design. Architectural Technology Review, 34(4), 289–305.
• Huang, C., & Zhang, J. (2021). Social and ethical considerations in AI applications for architectural education. International Journal of AI & Architecture, 13(2), 118–134.
• Jabareen, H. (2022). Smart design technologies in architecture. Routledge.
• Jha, P., & Sharma, P. (2021). Integrating AI in architectural education: A pathway to innovation. Journal of Architectural Education, 78(3), 152–165.
• Jin, S., Tu, H., Li, J., Fang, Y., Qu, Z., Xu, F., Liu, K., & Lin, Y. (2024). Enhancing architectural education through artificial intelligence: A case study of an AI-assisted architectural programming and design course. Buildings, 14(6), 1613.
• Kamaei, Sepideh, & Kaboli, Dr. Ahmad Reza. (2024). Evaluation of Iranian Architecture and Social Interactions in Cultural Spaces. New Ideas in The Geographical Sciences, 3(2), 47-62 . (in Persian)
• Kim, H., Cho, C. Y., & Hong, S. W. (2023). Impact of agent‑based simulation on novice architects’ workplace design exploration and trade‑offs. Automation in Construction, 145, 104635.
• Kiviniemi, M. (2014). BIM and intelligent systems in architecture. Elsevier.
• Koh, J., Tan, K., & Lee, Y. (2022). Deep learning in architectural form generation: Applications and challenges. Computers, Environment and Urban Systems, 90, 101720.
• Kotsiantis, S. B., Zervas, P. G., & Kalliris, D. (2023). AI in architectural education: Overcoming resistance to new technologies. International Journal of Architectural Education, 47(1), 45–59.
• Koutamanis, A. (2020). Architectural design and artificial intelligence: A review of the role of creativity in design processes. Design Studies, 69(1), 1–17.
• Leung, K., & Chan, M. (2022). AI in learning analytics for architecture education. Education and Technology Journal, 27(4), 430–445.
• Li, B. (2023). Educational challenges and opportunities for integrating AI in architectural design: A global perspective. Journal of Educational Technology, 44(2), 234–250.
• Li, W., Zhang, Y., & Wang, F. (2023). Optimization of energy and cost in building design using genetic algorithms. ScienceDirect.
• Li, X., Xie, Y., & Zhang, M. (2022). Fuzzy logic and evolutionary algorithms in design decision making. Cambridge University Press.
• Liu, J., Tan, Z., & Wang, Q. (2022). AI-based personalization and adaptive learning in architecture: Enhancing learning processes and outcomes. Education and Information Technologies, 27(6), 8607–8625.
• Lu, Y., Wu, W., Geng, X., Liu, Y., Zheng, H., & Hou, M. (2022). Multi-objective optimization of building environmental performance: An integrated parametric design method based on machine learning approaches. Building and Environment, 208, 108629.
• Miao, Y., Wu, J., Zhang, H., & Shen, G. Q. (2020). Understanding the role of artificial intelligence in construction project management. Automation in Construction, 122, 103465.
• Newton, D. (2019). Generative deep learning in architectural design. Technology|Architecture+Design, 3(2), 176–189.
• Nguyen, T., Le, T., & Tran, H. (2022). Artificial intelligence in architectural education: Revolutionizing learning processes. Journal of Architectural Education, 76(4), 123–139.
• Papageorgiou, D., & Nikolaou, M. (2023). AI in architecture education: Automated assessment and student performance analysis. International Journal of Educational Technology in Higher Education, 20(1), 1–19.
• Patel, M., & Lee, J. (2023). Generative design in architecture: Harnessing the power of deep learning. Frontiers of Architectural Research, 12(2), 250–265.
• Perkins, S., et al. (2021). AR and AI in architecture: A new educational approach. Architectural Technology Journal, 19(2), 99–110.
• Ralston, P. A. S., Hoye, J. D., & Rambo-Hernandez, K. E. (2019). Building better engineers: A study of academic and career success in engineering with implications for education and diversity. International Journal of STEM Education, 6(1), 1–12.
• Salem, O. (2021). Financial and infrastructural barriers to AI implementation in architecture education. International Journal of Technology and Education, 29(3), 203–217.
• Schwab, K. (2021). The fourth industrial revolution. Penguin.
• Serban, O., Thies, W., & Roussev, B. (2020). Machine learning in architecture: A review. Automation in Construction, 119, 103339.
• Shahin, A., Farooq, M., & Rehman, A. (2021). Developing AI skills in architecture education: Strategies for faculty development. Journal of Architectural Education, 60(2), 94–110.
• Smith, A., Wang, J., & Brown, C. (2021). AI in architecture: Integrating machine learning with architectural design. Routledge.
• Sun, Y., Zhao, X., & Li, F. (2022). Artificial intelligence in architectural education: Overcoming challenges and enhancing skills. Educational Review, 28(1), 99–113.
• Swan, M., & Lile, B. (2020). Artificial intelligence in architecture: Financial and infrastructure challenges. Journal of Building Education, 35(2), 243–257.
• Tegos, S., Vassiliou, A., & Andreou, D. (2023). The future role of artificial intelligence in architectural and interior design education to improve efficiency, sustainability, and creativity. ResearchGate.
• Törmä, M., Heikkilä, S., & Salo, A. (2020). Advanced data analysis algorithms for architectural design. Journal of Architecture and Urban Planning, 12(2), 233–245.
• Wang, Y., Huang, J., & Zhang, Z. (2022). Machine learning applications in architecture and design. Wiley.
• Wang, Z., Hu, Z., & Fang, D. (2021). Artificial intelligence in architecture: Emerging trends and future prospects. Journal of Architectural and Planning Research, 38(3), 205–220.
• Yang, M., Li, X., & Wang, Y. (2021). Neural networks in architecture: From design to construction. Springer.
• Yuan, W., Li, Z., & Zhao, X. (2021). Using machine learning and genetic algorithms for energy optimization and cost reduction in building design. ScienceDirect.
• Zhang, L., Wu, Y., & Yang, J. (2023). Using machine learning to simulate building behavior and improve design decisions. ScienceDirect.
• Zhao, Y., & Wang, X. (2023). AI-driven smart architecture: The future of building design and construction. Elsevier.
• Zhu, W., Chen, R., Lin, J., & Zhou, H. (2023). Machine learning for architectural design prediction. Journal of Computational Architecture, 17(1), 220–233.
• Zhuang, X., Zhu, P., Yang, A. Y., & Caldas, L. (2025). Machine learning for generative architectural design: Advancements, opportunities, and challenges. Automation in Construction, 174, 106129.

منابع و مأخذ:


1) اکبری نامدار، شبنم، خدائی، هانیه. (۱۴۰۴). بازآفرینی فضای معماری ازیادرفته، طرحی برای توسعه معماری پایدار (نمونه موردی: فضاهای صنعتی در تبریز). اندیشه‌های نو در علوم جغرافیایی،۹(۳)،۱-۱۶.
2) کمایی، سپیده، کابلی، دکتر احمدرضا، (۱۴۰۳). ارزیابی معماری ایرانی و تعاملات اجتماعی در فضاهای فرهنگی. اندیشه‌های نو در علوم جغرافیایی،۳(۲)،۴۷-۶۲.
3) Almarashdeh, I. (2021). The role of artificial intelligence in enhancing online learning: A study in architecture education. International Journal of Educational Technology, 32(2), 87–103.
4) Alsharif, N., Al-Zahrani, A., Al-Mutairi, M., & Baqadir, A. (2020). Integration of AI in VR and AR for architecture education. Journal of Educational Technology & Society, 23(4), 45–58.
5) Aluko, R. O., Adenuga, O. A., Kukoyi, P. O., Soyingbe, A. A., & Oyedeji, J. O. (2016). Predicting the academic success of architecture students by pre-enrolment requirement: Using machine-learning techniques. Construction Economics and Building, 16(4), 86–98.
6) Aluko, R. O., Daniel, E. I., Oshodi, O., & Aigbavboa, C. (2018). Towards reliable prediction of academic performance of architecture students using data mining techniques. Journal of Engineering, Design and Technology, 16(1), 57–68.
7) Azhar, S. (2011). Building information modeling (BIM): Benefits, risks, and challenges. International Journal of Advanced Engineering Technology, 4(3), 79–83.
8) Binns, S. (2020). Ethical challenges of artificial intelligence in architectural education. Journal of Architecture and Ethics, 5(2), 113–127.
9) Björk, B.-C. (1999). The future of building information modeling. CIB Publication 2.
10) Bonnardot, L., Dupuis, M., & Rondeau, J. (2021). Artificial intelligence in architecture design: Challenges and implications for creativity. Journal of Architectural Computing, 32(4), 225–239.
11) Borges, A., Pinto, A., & Duarte, P. (2021). Computational intelligence in architectural design: An evolutionary approach. Springer.
12) Brynjolfsson, E., & McAfee, A. (2022). The second machine age: Work, progress, and prosperity in a time of brilliant technologies. W. W. Norton & Company.
13) Cao, Y., Gao, X., Yin, H., Yu, K., & Zhou, D. (2024). Reimagining tradition: A comparative study of artificial intelligence and virtual reality in sustainable architecture education. Sustainability, 16(24), 11135.
14) Chien, C., & Lee, C. (2021). Adaptive learning systems in architectural education: AI for personalizing design education. Architectural Science Review, 64(1), 45–57.
15) Chien, S., Lee, S., & Wang, L. (2021). EvoArch: An evolutionary algorithm for architectural layout design. ResearchGate.
16) Eastman, C., Teicholz, P., & Sacks, R. (2018). BIM handbook: A guide to building information modeling for owners, designers, engineers, contractors, and fabricators (2nd ed.). Wiley.
17) Garcia, R., et al. (2022). Enhancing architectural learning with AI, VR, and AR. Education and Design Journal, 32(2), 78–94.
18) Gero, J. S., & Maher, M. L. (2020). Computational models in architecture. Springer.
19) Ghaffarianhoseini, A., Ghaffarianhoseini, A., & Alwaer, H. (2021). Artificial intelligence in architecture and building design: A comprehensive review of current applications. Automation in Construction, 123, 103541.
20) Goh, A., & Chow, W. (2021). The role of AI in the transformation of architectural education and design practices. Journal of Educational Technology and Design, 25(1), 51–67.
21) Günay, H., Aldridge, L., & Ghanbari, M. (2023). Artificial neural networks for sustainable architectural design: Energy efficiency and material selection. Journal of Building Engineering, 61, 105227.
22) Hosseini, M., & Nikbakht, A. (2022). Smart platforms in architecture: A review on AI-driven tools in education and design. Architectural Technology Review, 34(4), 289–305.
23) Huang, C., & Zhang, J. (2021). Social and ethical considerations in AI applications for architectural education. International Journal of AI & Architecture, 13(2), 118–134.
24) Jabareen, H. (2022). Smart design technologies in architecture. Routledge.
25) Jha, P., & Sharma, P. (2021). Integrating AI in architectural education: A pathway to innovation. Journal of Architectural Education, 78(3), 152–165.
26) Jin, S., Tu, H., Li, J., Fang, Y., Qu, Z., Xu, F., Liu, K., & Lin, Y. (2024). Enhancing architectural education through artificial intelligence: A case study of an AI-assisted architectural programming and design course. Buildings, 14(6), 1613.
27) Kim, H., Cho, C. Y., & Hong, S. W. (2023). Impact of agent based simulation on novice architects’ workplace design exploration and trade offs. Automation in Construction, 145, 104635.
28) Kiviniemi, M. (2014). BIM and intelligent systems in architecture. Elsevier.
29) Koh, J., Tan, K., & Lee, Y. (2022). Deep learning in architectural form generation: Applications and challenges. Computers, Environment and Urban Systems, 90, 101720.
30) Kotsiantis, S. B., Zervas, P. G., & Kalliris, D. (2023). AI in architectural education: Overcoming resistance to new technologies. International Journal of Architectural Education, 47(1), 45–59.
31) Koutamanis, A. (2020). Architectural design and artificial intelligence: A review of the role of creativity in design processes. Design Studies, 69(1), 1–17.
32) Leung, K., & Chan, M. (2022). AI in learning analytics for architecture education. Education and Technology Journal, 27(4), 430–445.
33) Li, B. (2023). Educational challenges and opportunities for integrating AI in architectural design: A global perspective. Journal of Educational Technology, 44(2), 234–250.
34) Li, W., Zhang, Y., & Wang, F. (2023). Optimization of energy and cost in building design using genetic algorithms. ScienceDirect.
35) Li, X., Xie, Y., & Zhang, M. (2022). Fuzzy logic and evolutionary algorithms in design decision making. Cambridge University Press.
36) Liu, J., Tan, Z., & Wang, Q. (2022). AI-based personalization and adaptive learning in architecture: Enhancing learning processes and outcomes. Education and Information Technologies, 27(6), 8607–8625.
37) Lu, Y., Wu, W., Geng, X., Liu, Y., Zheng, H., & Hou, M. (2022). Multi-objective optimization of building environmental performance: An integrated parametric design method based on machine learning approaches. Building and Environment, 208, 108629.
38) Miao, Y., Wu, J., Zhang, H., & Shen, G. Q. (2020). Understanding the role of artificial intelligence in construction project management. Automation in Construction, 122, 103465.
39) Newton, D. (2019). Generative deep learning in architectural design. Technology|Architecture+Design, 3(2), 176–189.
40) Nguyen, T., Le, T., & Tran, H. (2022). Artificial intelligence in architectural education: Revolutionizing learning processes. Journal of Architectural Education, 76(4), 123–139.
41) Papageorgiou, D., & Nikolaou, M. (2023). AI in architecture education: Automated assessment and student performance analysis. International Journal of Educational Technology in Higher Education, 20(1), 1–19.
42) Patel, M., & Lee, J. (2023). Generative design in architecture: Harnessing the power of deep learning. Frontiers of Architectural Research, 12(2), 250–265.
43) Perkins, S., et al. (2021). AR and AI in architecture: A new educational approach. Architectural Technology Journal, 19(2), 99–110.
44) Ralston, P. A. S., Hoye, J. D., & Rambo-Hernandez, K. E. (2019). Building better engineers: A study of academic and career success in engineering with implications for education and diversity. International Journal of STEM Education, 6(1), 1–12.
45) Salem, O. (2021). Financial and infrastructural barriers to AI implementation in architecture education. International Journal of Technology and Education, 29(3), 203–217.
46) Schwab, K. (2021). The fourth industrial revolution. Penguin.
47) Serban, O., Thies, W., & Roussev, B. (2020). Machine learning in architecture: A review. Automation in Construction, 119, 103339.
48) Shahin, A., Farooq, M., & Rehman, A. (2021). Developing AI skills in architecture education: Strategies for faculty development. Journal of Architectural Education, 60(2), 94–110.
49) Smith, A., Wang, J., & Brown, C. (2021). AI in architecture: Integrating machine learning with architectural design. Routledge.
50) Sun, Y., Zhao, X., & Li, F. (2022). Artificial intelligence in architectural education: Overcoming challenges and enhancing skills. Educational Review, 28(1), 99–113.
51) Swan, M., & Lile, B. (2020). Artificial intelligence in architecture: Financial and infrastructure challenges. Journal of Building Education, 35(2), 243–257.
52) Tegos, S., Vassiliou, A., & Andreou, D. (2023). The future role of artificial intelligence in architectural and interior design education to improve efficiency, sustainability, and creativity. ResearchGate.
53) Törmä, M., Heikkilä, S., & Salo, A. (2020). Advanced data analysis algorithms for architectural design. Journal of Architecture and Urban Planning, 12(2), 233–245.
54) Wang, Y., Huang, J., & Zhang, Z. (2022). Machine learning applications in architecture and design. Wiley.
55) Wang, Z., Hu, Z., & Fang, D. (2021). Artificial intelligence in architecture: Emerging trends and future prospects. Journal of Architectural and Planning Research, 38(3), 205–220.
56) Yang, M., Li, X., & Wang, Y. (2021). Neural networks in architecture: From design to construction. Springer.
57) Yuan, W., Li, Z., & Zhao, X. (2021). Using machine learning and genetic algorithms for energy optimization and cost reduction in building design. ScienceDirect.
58) Zhang, L., Wu, Y., & Yang, J. (2023). Using machine learning to simulate building behavior and improve design decisions. ScienceDirect.
59) Zhao, Y., & Wang, X. (2023). AI-driven smart architecture: The future of building design and construction. Elsevier.
60) Zhu, W., Chen, R., Lin, J., & Zhou, H. (2023). Machine learning for architectural design prediction. Journal of Computational Architecture, 17(1), 220–233.
61) Zhuang, X., Zhu, P., Yang, A. Y., & Caldas, L. (2025). Machine learning for generative architectural design: Advancements, opportunities, and challenges. Automation in Construction, 174, 106129.