A Conceptual Design Study of AI-Driven Architectural Heritage Conservation: The Case of Taj Mahal in India

doi:10.22716/sckt.2026.14.2.008

All Issue

2026 Vol.14, Issue 2 Preview Page Next Page

Research Article

A Conceptual Design Study of AI-Driven Architectural Heritage Conservation: The Case of Taj Mahal in India AI를 활용한 건축문화유산 보존을 위한 개념 설계 연구: 인도 타지마할 사례를 중심으로: ¹Choonho Lee
¹이춘호; ¹HK Professor, Institute of Indian Studies, Hankuk University of Foreign Studies

¹한국외국어대학교 인도연구소 HK교수

30 June 2026. pp. 89-101

PDF

Abstract

기후변화의 심화와 인공지능 기술의 급속한 발전은 비서구 건축문화유산 보존에 새로운 전기를 마련했다. 본 논문은 AI 보존 시스템의 성능 실증보다는, 그 설계 구조와 적용 방안을 개념적으로 정리하는 데 초점을 둔다. 인도 타지마할을 사례로 삼아, 데이터 수집·분석·의사결정의 3단계 구조를 제안하였다. 수집 단계에서는 위성, 드론(UAV), 사물인터넷(IoT) 자료를 통합 활용한다. 분석 단계에서는 U-Net, YOLO, Mask R-CNN 등 다양한 딥러닝 모델을 적용한다. 의사결정 단계는 디지털 트윈을 기반으로 한다. 이와 함께 복합 위협 매트릭스, 무갈·이슬람·인도 건축 맥락을 반영한 설계 사례, 탈식민주의 관점의 AI 편향 완화 전략도 제시한다. 그리고 현장 연구로 이어지는 5단계 검증 로드맵도 함께 수록한다.

The intensification of climate change and the rapid advancement of artificial intelligence (AI) technologies have created new opportunities for the preservation of non-Western architectural heritage. Rather than empirically validating the performance of AI-based conservation systems, this study focuses on conceptually organizing their design framework and potential applications. Using the Taj Mahal in India as a case study, the paper proposes a three-stage architecture consisting of data collection, analysis, and decision-making. In the data collection stage, satellite imagery, unmanned aerial vehicles (UAVs), and Internet of Things (IoT) data are integrated. In the analysis stage, various deep learning models, including U-Net, YOLO, and Mask R-CNN, are employed to detect and assess heritage deterioration. The decision-making stage is built upon a digital twin framework that supports predictive conservation and management. In addition, the study presents a multi-threat matrix, design scenarios that reflect the Mughal, Islamic, and Indian architectural context, and AI bias mitigation strategies informed by postcolonial perspectives. Finally, a five-stage validation roadmap is proposed to facilitate future field-based research and practical implementation.

Keywords

AI conservation

Taj Mahal

conceptual design

geomatics

digital twin

Mughal architecture

References

M. Casillo, F. Colace, R. Gaeta, A. Lorusso, and M. Pellegrino, “Artificial intelligence in archaeological site conservation: Trends, challenges, and future directions”, Journal of Computer Applications in Archaeology, Vol. 8, No. 1, pp. 224-241, 2025. DOI: 10.5334/jcaa.207
10.5334/jcaa.207
M. Paolanti, E. Frontoni, and R. Pierdicca, “Towards trustworthy AI in cultural heritage”, npj Heritage Science, Vol. 14, Article no. 131, 2026. DOI: 10.1038/s40494-026-02403-z
10.1038/s40494-026-02403-z
V. Barrile, C. Gattuso, and E. Genovese, “Review of geomatics solutions for protecting cultural heritage in response to climate change”, Heritage, Vol. 7, No. 12, pp. 7031-7049, 2024. DOI:10.3390/heritage7120325
10.3390/heritage7120325
Archaeological Survey of India (ASI), Conservation and Preservation of Taj Mahal: Annual Report 2022-2023, Ministry of Culture, Government of India, 2023. https://www.indiaculture.gov.in/sites/default/files/annual-reports/Final_Min_of_Culture_Eng_AR_for_Net_14-09-23_18092023.pdf
UNESCO World Heritage Committee, “State of conservation reports: Taj Mahal (India),” World Heritage List No. 252. https://whc.unesco.org/en/soc/
I. Karadag, “Machine learning for conservation of architectural heritage”, Open House International, Vol. 48, No. 4, pp. 23-37, 2022. DOI:10.1108/OHI-05-2022-0124
10.1108/OHI-05-2022-0124
R. Sizyakin, J. Cornelis, L. Meeus, and L. Platisa, “Crack detection in paintings using convolutional neural networks”, IEEE Access, Vol. 8, pp. 74535-74552, 2020. DOI: 10.1109/ACCESS.2020.2988856
10.1109/ACCESS.2020.2988856
C. Koch, K. Georgieva, V. Kasireddy, B. Akinci, and P. Fieguth, “A review on computer vision based defect detection and condition assessment of concrete and asphalt civil infrastructure”, Advanced Engineering Informatics, Vol. 29, No. 2, pp. 196-210, 2015. DOI: 10.1016/j.aei.2015.01.008
10.1016/j.aei.2015.01.008
A. R. Hevner, S. T. March, J. Park, and S. Ram, “Design Science in Information Systems Research”, MIS Quarterly, Vol. 28, No. 1, pp. 75-105, 2004. DOI: 10.2307/25148625
10.2307/25148625
M.T. Ribeiro, S. Singh, and C. Guestrin, “Why should I trust you?: Explaining the predictions of any classifier”, Proc. ACM SIGKDD, pp. 1135-1144, 2016. DOI: 10.1145/2939672.2939778
10.1145/2939672.2939778
A. Jobin, M. Ienca, and E. Vayena, “The global landscape of AI ethics guidelines”, Nature Machine Intelligence, Vol. 1, pp. 389-399, 2019. DOI: 10.1038/s42256-019-0088-2
10.1038/s42256-019-0088-2
Y. Zhang, C. Li, F. Chen, and Y. Cen, “Crack segmentation on earthen heritage site surfaces” , Applied Sciences, Vol. 12, No. 24, p. 12830, 2022. DOI: 10.3390/app122412830
10.3390/app122412830
H. Richards-Rissetto, D. Newton, and A. Al Zadjali, “A 3D point cloud deep learning approach using LiDAR to identify ancient Maya archaeological sites”, ISPRS Annals, Vol. VIII-M-1-2021, pp. 133-139, 2021. DOI: 10.5194/isprs-annals-VIII-M-1-2021-133-2021
10.5194/isprs-annals-VIII-M-1-2021-133-2021
O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional networks for biomedical image segmentation”, Proc. MICCAI 2015, LNCS 9351, pp. 234-241, 2015. DOI: 10.48550/arXiv.1505.04597
10.48550/arXiv.1505.04597
K. He, G. Gkioxari, P. Dollár, and R. Girshick, “Mask R-CNN,” Proc. ICCV, pp. 2961-2969, 2017. DOI: 10.1109/ICCV.2017.322
10.1109/ICCV.2017.322
Z. Q. Wu, and L. Fuxin, “PointConv: Deep convolutional networks on 3D point clouds”, Proc. CVPR, pp. 9621-9630, 2019. DOI: 10.1109/CVPR.2019.00985
10.1109/CVPR.2019.00985
J. Redmon, and I. Farhadi, “YOLOv3: An incremental improvement”, Proc. ICCV, pp. 1-12, 2018. DOI: 10.48550/arXiv.1804.02767
10.48550/arXiv.1804.02767
G. Jocher, A. Chaurasia, and J. Qiu, YOLOv5 by Ultralytics (Version 7.0) [Software], Zenodo, 2022. DOI: 10.5281/zenodo.7347926
10.5281/zenodo.7347926
M. Mishra, T. Barman, and G. V. Ramana, “Artificial intelligence-based visual inspection system for structural health monitoring of cultural heritage”, Journal of Civil Structural Health Monitoring, Vol. 14, pp. 103-120, 2024. DOI:10.1007/s13349-022-00643-8
10.1007/s13349-022-00643-8
G. Imen, M. Hamdi, M. Zoubeida, and B. Fouad, “Utilizing the MaxEnt machine learning model to forecast urban heritage sites in the desert regions of southwestern Algeria”, Archaeological Prospection, Vol. 31, No. 1, pp. 23-35, 2024. DOI: 10.1002/arp.1923
10.1002/arp.1923
N. Masini, M. Biscione, M. Ciminale, and R. Lasaponara, “Revealing the structural behaviour of Brunelleschi’s Dome with machine learning techniques”, Data Mining and Knowledge Discovery, Vol. 38, pp. 1440-1465, 2024. DOI: 10.1007/s10618-024-01004-3
10.1007/s10618-024-01004-3
M. Altaweel, Khelifi, and M. M. Shana’ah, “Monitoring Looting at Cultural Heritage Sites: Applying Deep Learning on Optical Unmanned Aerial Vehicles Data as a Solution”, Social Science Computer Review, Vol. 42, No. 2, pp. 480-495, 2023. DOI: 10.1177/08944393231188471
10.1177/08944393231188471

Information

Publisher :The Society of Convergence Knowledge
Publisher(Ko) :융복합지식학회
Journal Title :The Society of Convergence Knowledge Transactions
Journal Title(Ko) :융복합지식학회논문지
Volume : 14
No :2
Pages :89-101
DOI :https://doi.org/10.22716/sckt.2026.14.2.008

[1] M. Casillo, F. Colace, R. Gaeta, A. Lorusso, and M. Pellegrino, “Artificial intelligence in archaeological site conservation: Trends, challenges, and future directions”, Journal of Computer Applications in Archaeology, Vol. 8, No. 1, pp. 224-241, 2025. DOI: 10.5334/jcaa.207
10.5334/jcaa.207

[2] M. Paolanti, E. Frontoni, and R. Pierdicca, “Towards trustworthy AI in cultural heritage”, npj Heritage Science, Vol. 14, Article no. 131, 2026. DOI: 10.1038/s40494-026-02403-z
10.1038/s40494-026-02403-z

[3] V. Barrile, C. Gattuso, and E. Genovese, “Review of geomatics solutions for protecting cultural heritage in response to climate change”, Heritage, Vol. 7, No. 12, pp. 7031-7049, 2024. DOI:10.3390/heritage7120325
10.3390/heritage7120325

[4] Archaeological Survey of India (ASI), Conservation and Preservation of Taj Mahal: Annual Report 2022-2023, Ministry of Culture, Government of India, 2023. https://www.indiaculture.gov.in/sites/default/files/annual-reports/Final_Min_of_Culture_Eng_AR_for_Net_14-09-23_18092023.pdf

[5] UNESCO World Heritage Committee, “State of conservation reports: Taj Mahal (India),” World Heritage List No. 252. https://whc.unesco.org/en/soc/

[6] I. Karadag, “Machine learning for conservation of architectural heritage”, Open House International, Vol. 48, No. 4, pp. 23-37, 2022. DOI:10.1108/OHI-05-2022-0124
10.1108/OHI-05-2022-0124

[7] R. Sizyakin, J. Cornelis, L. Meeus, and L. Platisa, “Crack detection in paintings using convolutional neural networks”, IEEE Access, Vol. 8, pp. 74535-74552, 2020. DOI: 10.1109/ACCESS.2020.2988856
10.1109/ACCESS.2020.2988856

[8] C. Koch, K. Georgieva, V. Kasireddy, B. Akinci, and P. Fieguth, “A review on computer vision based defect detection and condition assessment of concrete and asphalt civil infrastructure”, Advanced Engineering Informatics, Vol. 29, No. 2, pp. 196-210, 2015. DOI: 10.1016/j.aei.2015.01.008
10.1016/j.aei.2015.01.008

[9] A. R. Hevner, S. T. March, J. Park, and S. Ram, “Design Science in Information Systems Research”, MIS Quarterly, Vol. 28, No. 1, pp. 75-105, 2004. DOI: 10.2307/25148625
10.2307/25148625

[10] M.T. Ribeiro, S. Singh, and C. Guestrin, “Why should I trust you?: Explaining the predictions of any classifier”, Proc. ACM SIGKDD, pp. 1135-1144, 2016. DOI: 10.1145/2939672.2939778
10.1145/2939672.2939778

[11] A. Jobin, M. Ienca, and E. Vayena, “The global landscape of AI ethics guidelines”, Nature Machine Intelligence, Vol. 1, pp. 389-399, 2019. DOI: 10.1038/s42256-019-0088-2
10.1038/s42256-019-0088-2

[12] Y. Zhang, C. Li, F. Chen, and Y. Cen, “Crack segmentation on earthen heritage site surfaces” , Applied Sciences, Vol. 12, No. 24, p. 12830, 2022. DOI: 10.3390/app122412830
10.3390/app122412830

[13] H. Richards-Rissetto, D. Newton, and A. Al Zadjali, “A 3D point cloud deep learning approach using LiDAR to identify ancient Maya archaeological sites”, ISPRS Annals, Vol. VIII-M-1-2021, pp. 133-139, 2021. DOI: 10.5194/isprs-annals-VIII-M-1-2021-133-2021
10.5194/isprs-annals-VIII-M-1-2021-133-2021

[14] O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional networks for biomedical image segmentation”, Proc. MICCAI 2015, LNCS 9351, pp. 234-241, 2015. DOI: 10.48550/arXiv.1505.04597
10.48550/arXiv.1505.04597

[15] K. He, G. Gkioxari, P. Dollár, and R. Girshick, “Mask R-CNN,” Proc. ICCV, pp. 2961-2969, 2017. DOI: 10.1109/ICCV.2017.322
10.1109/ICCV.2017.322

[16] Z. Q. Wu, and L. Fuxin, “PointConv: Deep convolutional networks on 3D point clouds”, Proc. CVPR, pp. 9621-9630, 2019. DOI: 10.1109/CVPR.2019.00985
10.1109/CVPR.2019.00985

[17] J. Redmon, and I. Farhadi, “YOLOv3: An incremental improvement”, Proc. ICCV, pp. 1-12, 2018. DOI: 10.48550/arXiv.1804.02767
10.48550/arXiv.1804.02767

[18] G. Jocher, A. Chaurasia, and J. Qiu, YOLOv5 by Ultralytics (Version 7.0) [Software], Zenodo, 2022. DOI: 10.5281/zenodo.7347926
10.5281/zenodo.7347926

[19] M. Mishra, T. Barman, and G. V. Ramana, “Artificial intelligence-based visual inspection system for structural health monitoring of cultural heritage”, Journal of Civil Structural Health Monitoring, Vol. 14, pp. 103-120, 2024. DOI:10.1007/s13349-022-00643-8
10.1007/s13349-022-00643-8

[20] G. Imen, M. Hamdi, M. Zoubeida, and B. Fouad, “Utilizing the MaxEnt machine learning model to forecast urban heritage sites in the desert regions of southwestern Algeria”, Archaeological Prospection, Vol. 31, No. 1, pp. 23-35, 2024. DOI: 10.1002/arp.1923
10.1002/arp.1923

[21] N. Masini, M. Biscione, M. Ciminale, and R. Lasaponara, “Revealing the structural behaviour of Brunelleschi’s Dome with machine learning techniques”, Data Mining and Knowledge Discovery, Vol. 38, pp. 1440-1465, 2024. DOI: 10.1007/s10618-024-01004-3
10.1007/s10618-024-01004-3

[22] M. Altaweel, Khelifi, and M. M. Shana’ah, “Monitoring Looting at Cultural Heritage Sites: Applying Deep Learning on Optical Unmanned Aerial Vehicles Data as a Solution”, Social Science Computer Review, Vol. 42, No. 2, pp. 480-495, 2023. DOI: 10.1177/08944393231188471
10.1177/08944393231188471

The Society of Convergence Knowledge Transactions ISSN:2287-8920(Print) 융복합지식학회논문지

All Issue