Reading Urban Heritage Through Roofscapes: A Machine Learning Approach for Tirilye

Historic towns often lack thorough records, complicating the study of long-term material changes in the built environment. This study develops RoofChronoNet, a machine learning workflow that extracts roof covering classes from grayscale imagery and quantifies roofscape change over time. Applied to Tirilye (Bursa, Turkey), historical aerial photographs from 1970 and 1984 are colourised using a pix2pix generative adversarial network trained on 2022 imagery. A YOLOv11m-seg model then detects roof surfaces and classifies them into three roof covering categories: red, white, and dark grey, producing diachronic roofscape maps for 1970–2022. Bounding box detection reached mask mAP@0.50 of 0.81 (2022), ≈0.71 (1984), and 0.76 (1970, single class), while class-averaged mask mAP@0.50 was lower due to pixel-level delineation complexity. Results indicate the persistence of red-tiled roof regimes within the historic core alongside a growing presence of white and dark-grey roof coverings in peripheral areas, consistent with renovation-driven material diffusion after the 1980s. Methodologically, the study contributes a reproducible framework that operationalises chromatic differentiation as a measurable variable for mapping roof covering regimes in planning history research using monochrome historical aerial imagery. RoofChronoNet supports heritage-oriented and planning history interpretations of material regime shifts in data-scarce contexts; however, colourised outputs are synthetic and probabilistic, and spatial inferences should be corroborated with archival or field-based evidence where feasible.