Using deep learning for enrichment of heritage BIM: Al Radwan house in historic Jeddah as a case study

A novel deep learning approach enhances the digitization of historic building geometry, addressing key challenges in heritage Building Information Modeling (BIM). By integrating laser scanner and unmanned aerial vehicle imagery data, researchers developed a scan-to-HBIM workflow that significantly improves the interpretation of spatial weathering forms and façade degradation. This method reduces subjective decision-making and resource demands while creating an HBIM library for Saudi Hijazi architectural elements. Applied to Al Radwan house in historic Jeddah—a UNESCO World Heritage site—this study provides stakeholders with a tool to identify, monitor, and analyze the types and extent of façade degradation, offering valuable insights for conservation efforts.

Miky, Y., Alshawabkeh, Y., & Baik, A. (2024). Using deep learning for enrichment of heritage BIM: Al Radwan house in historic Jeddah as a case study. Heritage Science, 12(1). https://doi.org/10.1186/s40494-024-01382-3