Machine Learning in Predicting Section Drawings Case of Anatolian Seljuk Kümbets

Güzelci O. Z.

40th Conference on Education and Research in Computer Aided Architectural Design in Europe, eCAADe 2022, Ghent, Belgium, 13 - 16 September 2022, vol.2, pp.169-176 identifier

  • Publication Type: Conference Paper / Full Text
  • Volume: 2
  • City: Ghent
  • Country: Belgium
  • Page Numbers: pp.169-176
  • Keywords: Anatolian Seljuk Architecture, Kümbet, Machine Learning, Pix2Pix, Section
  • Istanbul Technical University Affiliated: Yes

Abstract

© 2022, Education and research in Computer Aided Architectural Design in Europe. All rights reserved.Funerary structures called kümbet emerged as a unique typology during the Anatolian Seljuk period (1077-1307). This study introduces a machine learning (ML) based model to predict sections of kümbets to complete their missing parts. The proposed ML-based model employs the Pix2Pix method, which is a subset of conditional Generative Adversarial Networks (cGAN).The model is trained over a coupled dataset (interior space and exterior shell) of section drawings. Then, the model is validated by predicting overall shape (exterior shell) for a given input (interior space). The outcomes of the validation phase are evaluated objectively by using structural similarity method (SSIM). Initial findings of the implementation show that the proposed ML-based model has the potential to be used as a design decision support tool for further restitution and renovation works.