Documentation and Classification of Heritage Buildings’ Styles through Machine Learning
Dohuk’s City Center as a Case Study
DOI:
https://doi.org/10.14500/aro.12227Keywords:
Architectural styles, Classification, Documentation, Heritage site, Machine learningAbstract
Duhok, a city in Kurdistan Region of Iraq, has important historical and cultural evident in its archaeological sites. The city center contains many neglected heritage buildings that necessitate documenting as a crucial preliminary step for their preservation, facilitating a comprehensive understanding of their architectural, historical, and social significance. Consequently, the study aims to document buildings in the study region employing several documentation methods and looking at various aspects, such as architectural, historical, social, and cultural dimensions. The second goal of the study is to build an automated model utilizing advanced machine learning techniques, such as convolutional neural networks, transfer learning, and neural architectural search, to create a robust model for identifying and classifying architectural styles across various regions of the Kurdistan Region. The initials result of the study shows the unique attributes of Islamic, vernacular, modern, and postmodern architectural styles within Duhok’s legacy. The machine learning categorization of the model is very accurate, highlighting its potential as a reliable analytical tool for identifying and classifying architectural styles in Duhok city and across Kurdistan Region.
Downloads
References
ARS Progetti Spa, 2014. Master Planning Project for Duhok City Center. Available from: https://arsprogetti.org/project.asp?idproject=649 [Last accessed on 2026 Apr 13].
Cantemir, E., and Kandemir, O., 2023. Use of artificial neural networks in architecture: Determining the architectural style of a building with a convolutional neural network. Neural Computing and Applications, 36, pp.6195-6207.
Chen, Y, Wu, Y., Sun, X., Ali, N., and Zhou, Q., 2023. Digital documentation and conservation of architectural heritage information: An application in modern Chinese architecture. Sustainability, 15(9), p.7276.
Barbaro, C.C., Moscone, D., Iamoni, M., Morandi Bonacossi, D., and Qasim, H.A., 2019. The prehistory and protohistory of the Northwestern region of Iraqi Kurdistan: Preliminary results from the first survey campaigns. Paléorient, 45(2), pp.207-229.
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., and Fei L.F., 2009. Imagenet: A Large-Scale Hierarchical Image Database. In: IEEE Conference on Computer Vision and Pattern Recognition. pp.248-255.
Elgammal, A, Mazzone, M., Liu, B., Kim, D., and Elhoseiny, M., 2018. The Shape of Art History in the Eyes of the Machine. In: The Thirty-Second Aaai Conference on Artificial Intelligence (Aaai-18). Vol. 32, p.2183.
Available from : https://arxiv.org/abs/1801.07729 [Last accessed on 2026 Apr 13]. Fritz., 2023. AutoML: The Next Wave of Machine Learning. Available from: https://fritz.ai/automl-the-next-wave-of-machine-learning/ [Last accessed on 2026 Apr 13].
Google, 2024. AutoML Vision Beginner’s Guide, AutoML Beginner’s Guide, Vertex AI. Google Cloud, California. Google, 2025. Compute Engine Machine Types. Available from: https://docs. cloud.google.com/compute/docs/machine-resource [Last accessed on 2026 Apr 13].
Han, P, Hu, S., and Xu, R., 2025. Formal feature identification of vernacular architecture based on deep learning-a case study of Jiangsu province, China. Sustainability, 17(4), p.1760.
Harori, N., 2001. Commercial Structure of Dohuk City: A Study in Urban Geography. University of Duhok, Duhok, Iraq, p.57.
He, K, Zhang, X., Ren, S., and Sun, J., 2015. Delving Deep into Rectifiers: Surpassing Human-Level Performance on Imagenet Classification. In: Proceedings of the IEEE International Conference on Computer Vision. pp.1026-1034.
He, K, Zhang, X., Ren, S., and Sun, J., 2016. Deep Residual Learning for Image Recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp.770-778.
Khalil, A, Stravoravdis, S., and Backes, D., 2020. Categorisation of building data in the digital documentation of heritage buildings. Applied Geomatics, 13(1), p.29-54.
Kurdistan Regional Government, 2020. Cultural Heritage of Kurdistan Region, Ministry of Municipalities and Tourism. Available from: https://www.iraq-jccme. jp/pdf/archives/krg_2020_english.pdf [Last accessed on 2026 Apr 13].
Llamas, J., Lerones, P.M., Medina, R., Zalama, E., and Gómez-García Bermejo, J., 2017. Classification of architectural heritage images using deep learning techniques, Applied Sciences, 7(10), p.992.
Miao, S., Zhang, C., Piao, Y., and Miao, Y., 2024. Classification and model explanation of traditional dwellings based on improved swin transformer. Buildings, 14(6), p.1540.
Mohammed, J.A., 2010. Community Design and Development Report. Kurdistan, City of Duhok, p.5. Available from: https://www.academia.edu/18741300/ City_of_Dohuk_Kurdistan_Community_Design_and_Development_Report [Last accessed on 2026 Apr 13].
Muhammad, S., 2013. Documentation and Monitoring of Built heritage in Abu Dhabi, UAE. In: ISI Conference Proceedings International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XL-5/W2 [XXIV International CIPA Symposium]. p.437.
Nair, V., and Hinton, G.E., 2010. Rectified Linear Units Improve Restricted Boltzmann Machines. In: Proceedings of the 27th International Conference on Machine Learning. pp.807-814.
Available from: https://www.researchgate. net/publication/221345737_Rectified_Linear_Units_Improve_Restricted_ Boltzmann_Machines [Last accessed on 2026 Apr 13].
Pham, H., Guan, M.Y., Zoph, B., Le, Q.V., and Dean, J., 2018. Efficient Neural Architecture Search Via Parameter Sharing. In: 35th International Conference on Machine Learning. vol. 80, pp.4095-4104.
Sołtysiak A, Wiercińska, A., and Kozłowski S.K., 2015, Human remains from Nemrik, Iraq. An insight into living conditions and burial customs in a Pre-Pottery Neolithic village. Paléorient, 41(2), pp.101-114.
Srivastava N, Hinton, G., Krizhevsky, A., Sutskever, I., and Salakhutdinov, R., 2014. Dropout: A simple way to prevent neural networks from overfitting. Journal of Machine Learning Research, 15(1), pp.1929-1958.
Sun, H., Xu, H., and Wei, Q., 2022. The classification method of Urban architectural styles based on deep learning and street view imagery. In: Hydraulic and Civil Engineering Technology VII. Vol. 31. IOS Press, Amsterdam, Netherlands, p.824.
Tan, G., Zhu, J., and Chen, Z., 2023. Deep learning based identification and interpretability research of traditional village heritage value elements: A case study in Hubei Province. Heritage Science, 12, p.200.
Tan, M., Chen, B., Pang, R., Vasudevan, V., Sandler, M., Howard, A., and Le, Q.V., 2019. MnasNet: Platform-Aware Neural Architecture Search for Mobile. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp.2820-2828.
Yoshimura Y, Cai, B., Wang, Z., and Ratti, C., 2018. Deep Learning architect: Classification for architectural design through the eye of artificial intelligence. In: Advances in Informatics and Computing in Civil and Construction Engineering. Cornell University, United States, p.3. Available from : https://senseable.mit.edu/ papers/pdf/20190510_Yoshimura-etal_DeepLearning_ICCUPUM.pdf.
Xia, B, Lin, X., Shi, H., Chen, S., and Chen, J., 2020. Style classification and prediction of residential buildings based on machine learning. Journal of Asian Architecture and Building Engineering, 19(6), pp.714-730.
Zoph, B., and Le, Q.V., 2016. Neural Architecture Search with Reinforcement Learning. Cornell University, New York.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Cebar J. Sadiq
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Authors who choose to publish their work with Aro agree to the following terms:
-
Authors retain the copyright to their work and grant the journal the right of first publication. The work is simultaneously licensed under a Creative Commons Attribution License [CC BY-NC-SA 4.0]. This license allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
-
Authors have the freedom to enter into separate agreements for the non-exclusive distribution of the journal's published version of the work. This includes options such as posting it to an institutional repository or publishing it in a book, as long as proper acknowledgement is given to its initial publication in this journal.
-
Authors are encouraged to share and post their work online, including in institutional repositories or on their personal websites, both prior to and during the submission process. This practice can lead to productive exchanges and increase the visibility and citation of the published work.
By agreeing to these terms, authors acknowledge the importance of open access and the benefits it brings to the scholarly community.
Accepted 2026-02-13
Published 2026-04-28
ARO Journal is a scientific, peer-reviewed, periodical, and diamond OAJ that has no APC or ASC.