Reproduction of Nature-Inspired Architectural Forms through Artificial Intelligence
DOI:
https://doi.org/10.38027/smart.v2n1-10Keywords:
Artificial Intelligence in Architecture, Generative Design Tools, Architectural Visualization, Structural Similarity Index (SSIM), BiomimicryAbstract
This study aims to evaluate the effectiveness of AI-based visualization tools in reinterpreting biomimetic architectural designs. To this end, three iconic nature-inspired buildings—Eastgate Building, Clyde Auditorium, and the Bahá'í Temple—were selected. For each, visual representations were generated using different AI models: DALL-E, DeepAI, and Midjourney. These AI-generated visuals were compared with the original structures based on architectural criteria, including form similarity, structural feasibility, scale and proportion, environmental integration, and SSIM (Structural Similarity Index Measure) scores.The findings demonstrate that while AI models can interpret and reproduce formal diversity inspired by nature, their architectural realism, scale coherence, and environmental responsiveness vary considerably. Midjourney stood out for its integration with landscape, DALL-E achieved the highest visual similarity scores, and DeepAI produced simplified forms with limited detailing. Overall, AI-generated biomimetic designs show promise in conceptual design phases, but to enhance practical applicability, more integrated approaches with engineering systems are needed.
References
Aykal, D., & Erbaş Özil, M. (2021). Biyofilik tasarımın Diyarbakir geleneksel konutlarında araştırılması. Journal of Architectural Sciences and Applications, 6(1), 45-58. https://doi.org/10.30785/mbud.801022
Bakurov, I., Buzzelli, M., Schettini, R., Castelli, M., & Vanneschi, L. (2022). Structural similarity index (SSIM) revisited: A data-driven approach. Expert Systems with Applications, 189, 116087. https://doi.org/10.1016/j.eswa.2021.116087
Bansal, G., Nawal, A., Chamola, V., & Herencsar, N. (2024). Revolutionizing visuals: The role of generative AI in modern image generation. ACM Transactions on Multimedia Computing, Communications and Applications, 20(11), 1–22. https://doi.org/10.1145/3689641
Benyus, J. (1997). Biomimicry - innovation inspired by nature. Harper Collins.
Chayaamor-Heil, N., & Hannachi-Belkadi, N. (2017). Towards a platform of investigative tools for biomimicry as a new approach for energy-efficient building design. Buildings, 7(1), 19. https://doi.org/10.3390/buildings7010019
Chayaamor-Heil, N., & Vitalis, L. (2021). Biology and architecture: An ongoing hybridization of scientific knowledge and design practice by six architectural offices in France. Frontiers of Architectural Research, 10(2), 240–262. https://doi.org/10.1016/j.foar.2020.10.002
Kaya, H. E., & Taylan Susan, A. (2020). Sürdürülebilir bir kentleşme yaklaşımı olarak, ekolojik planlama ve eko-kentler. İdealkent, 11(30), 909–937. https://doi.org/10.31198/idealkent.533730
Maganga, M. (2023, January 22). The AI image generator: The limits of the algorithm and human biases. ArchDaily. https://www.archdaily.com/992012/the-ai-image-generator-the-limits-of-the-algorithm-and-human-biases
Makram, A., & Abou Ouf, T. (2019, October 14–16). Biomimetic and biophilic design as an approach to innovative sustainable architectural design. [Conference paper]. AR-UP 2019: Architecture & Urbanism. Cairo, Egypt. https://www.researchgate.net/publication/336832615_Biomimetic_and_biophilic_design_as_an_approach_to_the_innovative_sustainable_architectural_design
Oğurlu, İ., & Uç, B. (2024). Biyomimetik mimarlıkta ekomimikri ve orman kurma metaforu. Avrupa Bilim ve Teknoloji Dergisi, (53), 43–57. DOI: 10.5281/zenodo.10623642
Pawlyn, M. (2019). Biomimicry in architecture (2nd ed.). RIBA Publishing. https://doi.org/10.4324/9780429346774
Russell, S., & Norvig, P. (2016). Artificial intelligence: A modern approach (Third edition). Pearson.
Sukkar, A. W., Fareed, M. W., Yahia, M. W., Mushtaha, E., & De Giosa, S. L. (2024). Artificial intelligence Islamic architecture (AIIA): What is Islamic architecture in the age of artificial intelligence? Buildings, 14, 781. https://doi.org/10.3390/buildings14030781
Tiwari, T., Tiwari, T., & Tiwari, S. (2018). How artificial intelligence, machine learning and deep learning are radically different? International Journal of Advanced Research in Computer Science and Software Engineering, 8(1). https://doi.org/10.23956/ijarcsse.v8i2.569
Uç, B. (2023). Ekolojik mimarı tasarımda biyomimikri ve ekomimikri. YDÜ Mimarlık Fakültesi Dergisi, 5(2), 1–20. https://doi.org/10.32955/neujfa202352782
Xia, L. (2025). Transform invariant low rank texture feature extraction and restoration algorithms for architectural decoration surface patterns. Signal, Image and Video Processing, 19(1), 1-13. https://doi.org/10.1007/s11760-024-03626-y
Zhang, S., Qi, Y., & Wu, J. (2025). Applying deep learning for style transfer in digital art: enhancing creative expression through neural networks. Scientific reports, 15(1), 11744. https://doi.org/10.1038/s41598-025-95819-9
Published
Issue
Section
License
Copyright (c) 2025 Gül Şebnem Tutal, Fatma Demet Aykal (Author)

This work is licensed under a Creative Commons Attribution 4.0 International License.






