Research Article

Reconstructing Lost Urban Memory with Generative AI: An Oral-History Prompt-Engineering Framework

Volume: 10 Number: 4 October 16, 2026

Reconstructing Lost Urban Memory with Generative AI: An Oral-History Prompt-Engineering Framework

Abstract

Urban transformation processes not only destroy the physical fabric of historic neighbourhoods but also erode the collective memory and everyday life practices embedded within them. This study addresses this spatial memory loss by employing generative AI to visually reconstruct the lost atmospheres of Cumhuriyet Neighbourhood within the outer walls of Kayseri Castle, Turkey. Drawing on oral history interviews conducted as part of a TÜBİTAK-funded project, narrative data from 5 former residents were transformed into structured seven-category prompts and fed into Google Gemini- Nano Banana 2 pro, OpenAI GPT-Image-1, and XAI Grok. A 30-member residents panel evaluated the outputs. Tool G (Google Gemini) achieved the best overall ranking (M = 1.77). The findings confirm that human curatorial oversight and iterative community feedback remain essential for culturally authentic AI-generated heritage visualisations.

Keywords

Supporting Institution

TÜBİTAK

Project Number

TÜBİTAK / 3501 - KARIYER GELISTIRME PROGRAMI / 224K906

Ethical Statement

This study was conducted in accordance with the Declaration of Helsinki. Ethics committee approval was obtained from Abdullah Gül University Ethics Committee (Approval No. E-23934413-050.04-113716). All participants provided informed written consent before participation.

Thanks

This study was funded by TÜBİTAK; we would like to thank the organisation for its support. We would also like to thank the city residents who took part in the interviews conducted as part of this study, as well as those who completed the questionnaire. The preliminary findings of this study were presented at the 9th International Conference on Current Issues in Architecture and Urban Planning. Our article has been submitted for consideration for publication in your journal; I would like to thank you in advance for your review.

References

  1. Nora, P. (2006). Hafıza mekanları (M. E. Özcan, Çev.). Dost Yayınları.
  2. Taylor, K. (2009). Cultural Landscapes and Asia: Reconciling International and Southeast Asian Regional Values. Landscape Research, 34(1), 7–31. https://doi.org/10.1080/01426390802387513
  3. Halbwachs, M. (1992). The social frameworks of memory. University of Chicago Press.
  4. Connerton, P. (2019). Toplumlar nasıl anımsar? (A. Şenel, Çev.; 3. bs.). Ayrıntı Yayınları.
  5. Nora, P. (1996). Realms of memory. Columbia University Press.
  6. Lowenthal, D. (1975). Past time, present place: Landscape and memory. Geographical Review, 65(1), 1–36. https://doi.org/10.2307/213831
  7. Aplin, G. (2007). World Heritage Cultural Landscapes. International Journal of Heritage Studies, 13(6), 427–446. https://doi.org/10.1080/13527250701570515
  8. Taylor, K., & Lennon, J. (2011). Cultural landscapes: A bridge between culture and nature? International Journal of Heritage Studies, 17(6), 537–554. https://doi.org/10.1080/13527258.2011.618246

Details

Primary Language

English

Subjects

Architectural Engineering

Journal Section

Research Article

Publication Date

October 16, 2026

Submission Date

June 25, 2026

Acceptance Date

July 24, 2026

Published in Issue

Year 2026 Volume: 10 Number: 4

APA
Kevseroğlu, Ö., Yaşar, İ., & Yıldırım, V. (2026). Reconstructing Lost Urban Memory with Generative AI: An Oral-History Prompt-Engineering Framework. Turkish Journal of Engineering, 10(4), 1667-1676. https://doi.org/10.31127/tuje.1967989
AMA
1.Kevseroğlu Ö, Yaşar İ, Yıldırım V. Reconstructing Lost Urban Memory with Generative AI: An Oral-History Prompt-Engineering Framework. TUJE. 2026;10(4):1667-1676. doi:10.31127/tuje.1967989
Chicago
Kevseroğlu, Özlem, İrem Yaşar, and Vildan Yıldırım. 2026. “Reconstructing Lost Urban Memory With Generative AI: An Oral-History Prompt-Engineering Framework”. Turkish Journal of Engineering 10 (4): 1667-76. https://doi.org/10.31127/tuje.1967989.
EndNote
Kevseroğlu Ö, Yaşar İ, Yıldırım V (October 1, 2026) Reconstructing Lost Urban Memory with Generative AI: An Oral-History Prompt-Engineering Framework. Turkish Journal of Engineering 10 4 1667–1676.
IEEE
[1]Ö. Kevseroğlu, İ. Yaşar, and V. Yıldırım, “Reconstructing Lost Urban Memory with Generative AI: An Oral-History Prompt-Engineering Framework”, TUJE, vol. 10, no. 4, pp. 1667–1676, Oct. 2026, doi: 10.31127/tuje.1967989.
ISNAD
Kevseroğlu, Özlem - Yaşar, İrem - Yıldırım, Vildan. “Reconstructing Lost Urban Memory With Generative AI: An Oral-History Prompt-Engineering Framework”. Turkish Journal of Engineering 10/4 (October 1, 2026): 1667-1676. https://doi.org/10.31127/tuje.1967989.
JAMA
1.Kevseroğlu Ö, Yaşar İ, Yıldırım V. Reconstructing Lost Urban Memory with Generative AI: An Oral-History Prompt-Engineering Framework. TUJE. 2026;10:1667–1676.
MLA
Kevseroğlu, Özlem, et al. “Reconstructing Lost Urban Memory With Generative AI: An Oral-History Prompt-Engineering Framework”. Turkish Journal of Engineering, vol. 10, no. 4, Oct. 2026, pp. 1667-76, doi:10.31127/tuje.1967989.
Vancouver
1.Özlem Kevseroğlu, İrem Yaşar, Vildan Yıldırım. Reconstructing Lost Urban Memory with Generative AI: An Oral-History Prompt-Engineering Framework. TUJE. 2026 Oct. 1;10(4):1667-76. doi:10.31127/tuje.1967989
Flag Counter