This study focuses on the nameplate of Vila D. Bosco, a modern building in Macau from the time of Portuguese rule, and looks at the types of metal materials and surface coatings used, as well as how they corrode due to the tropical marine climate affecting the building’s metal parts. The study uses different techniques, such as X-ray fluorescence spectroscopy (XRF), scanning electron microscopy/energy dispersive spectroscopy (SEM-EDS), X-ray diffraction (XRD), attenuated total internal reflectance Fourier transform infrared spectroscopy (ATR-FTIR), and cross-sectional microscopic analysis, to carefully look at the metal, corrosion products, and coating of the nameplate. The results show that (1) the nameplate matrix is a resulfurized steel with a high sulfur content (Fe up to 97.3% and S up to 1.98%), and the sulfur element is evenly distributed inside, which is one of the internal factors that induce corrosion. (2) Rust is composed of polycrystalline iron oxides such as goethite (α-FeOOH), hematite (α-Fe₂O₃), and magnetite (Fe₃O₄) and has typical characteristics of atmospheric oxidation. (3) The white and yellow-green coatings on the nameplate are oil-modified alkyd resin paints, and the color pigments are TiO₂, PbCrO₄, etc. The surface layer of the letters is protected by a polyvinyl alcohol layer. The paint application process leads to differences in the thickness of the paint in different regions, which directly affects the anti-rust performance. The study reveals the deterioration mechanism of resulfurized steel components in a subtropical polluted environment and puts forward repair suggestions that consider both material compatibility and reversibility, providing a reference for the protection practice of modern and contemporary architectural metal heritage in Macau and even in similar geographical environments.

In computer artificial intelligence, there is great potential in research on the protection of Suzhou's traditional gardens, a world cultural heritage site. As a special material in Suzhou's traditional garden architecture, shedthin tile is widely used in roof base laying and is one of the important materials for building roofs. However, professionals need to reach the roof and spend much time and effort assessing the damage before repairing it. Therefore, the main goals of this study are to investigate a machine learning-based method for finding targets and determining the type of surface damage on a shedthin tile using the YOLOv4 model trained in this study. Using 500 shedthin tile on-site photos as training samples, the model was trained for 750 epochs. The main results of this study are as follows: (1) An object detection method based on machine learning can efficiently and accurately identify damage content, overcoming the manpower and time–cost limitations of traditional assessment methods. (2) The detection model in this study has an accuracy of 85.89% for water stain recognition of shedthin tiles, 93.29% for surface scaling, 87.37% for color aberration, and 96.15% for too wide a gap. The comprehensive accuracy is 90.20%, which meets the basic testing requirements. (3) The model demonstrated its robustness and reliability in complex environments in application tests in actual scenarios, providing a methodological reference for computer vision and target detection technology in cultural heritage protection.

With the rapid development of machine learning technology, it has become possible to automatically identify cultural heritage elements in traditional buildings. This research aimed to develop a machine learning model based on the YOLOv4 architecture to identify the traditional Chinese porcelain inlay pattern in the Lingnan region. The researchers collected and annotated a large quantity of Lingnan Chinese porcelain inlay image data and then used these data to train the studied model. The research results show that (1) the model in this study was specifically adjusted to effectively identify a variety of Chinese porcelain inlay pattern types, including traditional patterns such as plum blossoms and camellias. (2) In the 116th epoch, the model showed excellent generalization ability, and the verification loss reached the lowest value of 0.88. The lowest training loss in the 195th epoch was 0.99, indicating that the model reached an optimal balance point for both recognition accuracy and processing speed. (3) By comparing different models for detecting Chinese porcelain inlay images across 581 pictures, our YOLOv4 model demonstrated greater accuracy in most classification tasks than did the YOLOv8 model, especially in the classification of chrysanthemums, where it achieved an accuracy rate of 87.5%, significantly outperforming YOLOv8 by 58.82%. However, the study also revealed that under certain conditions, such as detecting apples and pears in low-light environments, YOLOv8 showed a lower missing data rate, highlighting the limitations of our model in dealing with complex detection conditions.

With the rapid growth of global urbanization and the rising demand for sustainable development, it is essential to study the performance and durability of building materials. As a traditional and widely employed building material, Chinese clay tiles play a significant role in traditional Chinese architecture. However, traditional methods for assessing structural surface damage necessitate the time-consuming and labor-intensive assessment and judgment of trained professionals. Consequently, it is crucial to employ machine learning techniques for automatic damage type identification. This study identifies the types of damage to Chinese clay tiles in Macau by employing machine learning techniques and the YOLOv4 object detection model. A total of 363 photographs of on-site Chinese clay tiles were used as training samples, and 200 epochs of the model training were performed. The primary findings of this study are as follows: (1) The machine learning method, based on the YOLOv4 model, provides an effective and precise solution for the automatic identification of Chinese clay tiles damage types, overcoming the human and time-cost constraints of conventional evaluation methods. (2) The detection accuracy of the detection model in this study is 95.42% for the detection of Chinese clay tiles cracks, 80.91% for the detection of stains, and 89.34% for the detection of surface wear, with an overall accuracy of 88.98%, which meets the basic detection requirements. (3) The experimental results demonstrate the viability and efficacy of the proposed method for identifying clay tile damage types and provide a method reference for the preservation and sustainable development of historical buildings.

The historical Lingnan gray brick buildings in Macau, a World Heritage Site, are facing severe deterioration due to prolonged disrepair, manifesting as cracks, breakages, moss adhesion, and other types of surface damage. These issues threaten not only the structural stability of the buildings but also the conservation of cultural heritage. To address the inefficiencies and low accuracy of traditional manual inspections, this study proposes an automated recognition and quantitative detection method for wall surface damage based on the YOLOv8 deep learning object detection model. A dataset comprising 375 annotated images collected from 162 gray brick historical buildings in Macau was constructed, covering eight damage categories: crack, damage, missing, vandalism, moss, stain, plant, and intact. The model was trained and validated using a stratified sampling approach to maintain a balanced class distribution, and its performance was comprehensively evaluated through metrics such as the mean average precision (mAP), F1 score, and confusion matrices. The results indicate that the best-performing model (Model 3 at the 297th epoch) achieved a mAP of 61.51% and an F1 score up to 0.74 on the test set, with superior detection accuracy and stability. Heatmap analysis demonstrated the model’s ability to accurately focus on damaged regions in close-range images, while damage quantification tests showed high consistency with manual assessments, confirming the model’s practical viability. Furthermore, a portable, integrated device embedding the trained YOLOv8 model was developed and successfully deployed in real-world scenarios, enabling real-time damage detection and reporting. This study highlights the potential of deep learning technology for enhancing the efficiency and reliability of architectural heritage protection and provides a foundation for future research involving larger datasets and more refined classification strategies.