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.

Historical cultural heritage sites are valuable for all of mankind, as they reflect the material and spiritual wealth of by nations, countries, or specific groups during the development of human civilization. The types and functions of microorganisms that form biofilms on the surfaces of architectural heritage sites influence measures to preserve and protect these sites. These microorganisms contribute to the biocorrosion of architectural heritage structures through the cycling of chemical elements. The ancient city wall of Shou County is a famous architectural and cultural heritage site from China’s Song Dynasty, and the protection and study of this site have substantial historical and cultural significance. In this study, we used metagenomics to study the microbial diversity and taxonomic composition of the Song Dynasty city wall in Shou County, a tangible example of Chinese cultural heritage. The study covered three main topics: (1) examining the distribution of bacteria in the biofilm on the surfaces of the Song Dynasty city wall in Shou County; (2) predicting the influence of bacteria involved in the C, N, and S cycles on the corrosion of the city wall via functional gene analysis; and (3) discussing cultural heritage site protection measures for biocorrosion-related bacteria to investigate the impact of biocorrosion on the Song Dynasty city wall in Shou County, a tangible example of Chinese cultural heritage. The study revealed that (1) the biofilm bacteria mainly belonged to Proteobacteria, Actinobacteria, Cyanobacteria, Bacteroidetes, and Firmicutes, which accounted for more than 70% of the total bacteria in the biofilms. The proportion of fungi in the microbial community of the well-preserved city wall was greater than that in the damaged city wall. The proportion of archaea was low—less than 1%. (2) According to the Shannon diversity index, the well-preserved portion of the ancient city wall had the highest diversity of bacteria, fungi, and archaea, and bacterial diversity on the good city wall was greater than that on the corroded city wall. (3) Bray–Curtis distances revealed that the genomes of the two good city walls were similar and that the genomes of the corroded city wall portions were similar. Researchers also detected human intestine-related bacteria in four locations on the city walls, with the proportion of these bacteria in the microbial community being greater on good city walls than on bad city walls. (4) KEGG functional analysis revealed that the energy metabolism and inorganic ion transport activities of the bacterial community on the corroded city wall were greater than those of the good city wall. (5) In the carbon cycle, the absence of active glycolysis, the ED pathway, and the TCA cycle played significant roles in the collapse of the east city wall. (6) The nitrogen cycling processes involved ammonia oxidation and nitrite reduction to nitrate. (7) In the sulfur cycle, researchers discovered a crucial differential functional gene, SoxY, which facilitates the conversion of thiosulfate to sulfate. This study suggests that, in the future, biological approaches can be used to help cultural heritage site protectors achieve targeted and precise protection of cultural relics through the use of microbial growth inhibition technology. The results of this study serve as a guide for the protection of cultural heritage sites in other parts of China and provide a useful supplement to research on the protection of world cultural heritage or architectural heritage sites.

Microbial corrosion poses a significant threat to architectural heritage worldwide. This study used metagenomics to investigate microbial diversity and taxonomic groups present in the door walls of the Ji family’s residential houses, as well as their biological functions and chemical cycles. Taxonomic annotation revealed the predominant microbial taxa associated with wall corrosion, shedding light on their potential impact on structural integrity. Moreover, analyzing the metabolites and pathways present in these microbial communities allows for a thorough understanding of their functional capabilities. Our results revealed that areas with significant damage (dwelling bad door (DBD) and dwelling bad wall (DBW)) exhibited a higher microbial diversity compared to undamaged areas (dwelling good door (DGD) and dwelling good wall (DGW)), with variations in the occurrence of archaeal and bacterial species. The presence of bacteria was found to be connected with impaired function in DBW, whereas changes in the community patterns of Sphingobium and Sphingomonas, as well as a decrease in Cercospora proportion and an increase in Fusarium proportion, were correlated with damage in DBD. Both the Entner–Doudoroff (ED) route and sulfide oxidation processes were observed in both damaged locations (DBD and DBW). However, significant nitrogen-cycling mechanisms, including dissimilatory nitrate reduction to ammonium, were only found in DBW. Furthermore, DBD specifically detected the shift from methyl mercaptan (MMPA) to methyl mercaptan (MeSH). This research highlights the intricate interplay between microbial communities and the physical deterioration of residential structures, emphasizing the importance of understanding microbial ecology in mitigating such issues.

Characterizing material variation is relevant to the conservation of historic city walls. This study examined five masonry fragments from the East Gate of the Shouxian County City Wall using petrographic microscopy, X-ray diffraction (XRD), and scanning electron microscopy–energy-dispersive spectroscopy (SEM–EDS). Six thin sections showed fine-grained continuous matrices in Samples A and C, abundant coarse grains in B and E, and contrasting optical characteristics between the two sections of D. Calcite and quartz were identified in all five XRD patterns. Local EDS analyses recorded mixed elemental distributions and regions with prominent Fe, Ca, or C and O signals. SEM revealed blocky, platy, and granular particles, together with filamentous, tubular, and folded film-like features. Material heterogeneity here refers to contrasting matrix–grain textures and local elemental distributions within a sample set sharing calcite and quartz. These differences may reflect variation in materials used during construction or repair, without identifying specific historical phases. They support recording individual masonry units and their interfaces before conservation interventions.