The past few decades have witnessed unprecedented global urbanisation, with direct or indirect impacts on global cultural heritage sites. Research on the spatial relationship between cultural heritage sites and urban areas has provided a new perspective for understanding the impact processes between them, which have previously been discussed at the regional scale. In this article, we analyse the spatial relationship between world cultural heritage sites and neighbouring towns through systematic observations at the global scale and attempt to model change processes and identify impact mechanisms. We adopt spatial analysis and spatial statistics to analyse the changing characteristics of the spatial relationship between world cultural heritage sites and neighbouring towns from 1990 to 2018 and to analyse the impact processes at different spatial and temporal scales by combining indicators, such as income levels and urbanisation rates, at the national scale. The results show that 8.52% of world cultural heritage sites have been incorporated into urban areas over the aforementioned 28 years, with a certain aggregation in the spatial distribution of these sites, and that the growth rate can be divided into three phases, including two periods of rapid growth. The spatial relationship between towns and the 523 world cultural heritage sites that were previously located outside towns has not yet changed substantially, but the distances between most of the towns and these sites have been decreasing, with 81% of the world cultural heritage sites having a variation in distance from the corresponding town of 7.60 km or less. We also analysed the variation in distance between cultural heritage sites and neighbouring towns and found a relationship with indicators, such as the income level and urbanisation rate of the country to which a site belongs. Among the indicators, variation in national urbanisation rates most greatly affected the distance between heritage sites and towns. This study shows that world cultural heritage sites are affected by urbanisation and that particular attention should be given to the relationship between cultural heritage sites and neighbouring towns, especially in countries undergoing rapid urbanisation, so that the authenticity and integrity of cultural heritage are not compromised. This article provides a basis for development plans and policies in urban design, especially those that are sensitive to cultural heritage, and may also provide ideas and references for heritage conservation against the background of urbanisation.
World heritage sites are monuments and natural landscapes recognised by all humanity as being of outstanding significance and universal value. Spatial technology provides new ideas for the conservation and sustainable development of world heritage sites. Using a bibliometric analysis, this study extracted 401 relevant documents from the Web of Science database from 1990–2022. Meta information, such as abstracts, keywords of the papers were extracted and cleaned using bibliometric package and analysed the applications, partnerships and development trends of existing spatial technologies for world heritage sites. The results of the study show the “4D” characteristics of space technology in world heritage sites: (1) Development: Spatial applications in world heritage sites have gradually developed with an annual growth rate of 10.22% during the period 1990–2022. (2) Discrepancy: More than 70 per cent of countries have not been able to fully apply space technology on the ground at world heritage sites. (3) Desirability: Shared exchanges between research institutions are rare, and more cooperation and exchanges are expected, especially between transnationals. (4) Diversity: The future outlook for technology will be multidisciplinary, multi-method integrated research.
Scientific cognition and assessment of threats to cultural heritage and surrounding landscapes are prerequisites for targeted management and protection of cultural heritage. This study took 530 city sites in the Central Plains of China as the research object. Based on the survey information of city sites in the third national cultural heritage survey in China, a combination of high resolution google images and land use/land cover data products and city sites survey data enables a comprehensive evaluation of landscape elements impacts on city sites. With spatial statistical method, we divided city site landscape types, and constructed a landscape element risk assessment model and an urbanization intensity index to analyze the threats of each landscape element to city site protection. The results indicated that 40.64% of the sites are in farmland landscapes, where agricultural cultivation, irrigation, and other production activities may affect the surface and subsurface remains of the sites. The sites (16.82%) in urban landscapes are affected by activities such as building houses and roads. Only six sites belong to the water landscape area, which may be affected by water erosion. Other sites (2.84%) are mainly affected by plant root growth in forest landscapes. The city sites distributed in urban areas such as Zhengzhou or the urban–rural junction were significantly affected by urban expansion and got the greatest protection pressure. City sites in agricultural landscapes have the second highest conservation risk. Plant erosion and flooding mainly affected the city sites in the northwest-southwest mountainous areas or near the water area of the study area, and the risks were relatively small. It can be seen that landscape types such as urban and farmland, which are closely related to human activities, bring the most pressure to the protection of city sites, and it is necessary to focus on the impact of human activities such as urban construction on city sites and the surrounding environment in the future, while paying attention to the protection and rational use of city sites with high assessment risk in urban planning and management for the protection of the city site proper and landscape scenery.
This paper addresses the challenges of sample scarcity and class imbalance in remote sensing image semantic segmentation by proposing a decoupled synthetic sample generation framework based on a latent diffusion model. The method consists of two stages. In the label generation stage, we fine-tune a pretrained latent diffusion model with LoRA to generate semantic label masks from textual descriptions. A novel proportion-aware loss function explicitly penalizes deviations from the desired class distribution in the generated mask. In the image generation stage, we use ControlNet to train a multi-condition image generation network that takes the synthesized mask, along with its text description, as input and produces a realistic remote sensing image. The base Stable Diffusion model’s weights remain frozen during this process, with the trainable ControlNet ensuring that outputs are structurally and semantically aligned with the input labels. This two-stage approach yields coherent image–mask pairs that are well-suited for training segmentation models. Experiments show that models trained on the synthetic samples produced by the proposed method achieve high visual quality and semantic consistency. The proportion-aware loss effectively mitigates the impact of minority classes, boosting segmentation performance on under-represented categories. Results also reveal that adding a suitable proportion of synthetic sample improves segmentation accuracy, whereas an excessive share can cause over-fitting or misclassification. Comparative tests across multiple models confirm the generality and robustness of the approach.
The Shuanghuaishu (SHS) site in China is one of the 100 most important archaeological discoveries over the past 100 years; its historical heritage can be traced directly back 5300 years. Understanding the early landscape of the site would provide important information about the origin of Chinese civilization. The SHS site is buried and surface traces are difficult to see; therefore, we attempted to reconstruct the early landscape of the site based on a current surface landscape model and environmental archaeological analysis. We created a modern three-dimensional (3D) landscape model of the study area from high spatial resolution unmanned aerial vehicle (UAV) aerial photographs and analysed the distance change between the Yellow River and SHS site in the past 60 years from CORONA and Landsat images. By combining environmental archaeological survey results, archaeological excavation data, relevant papers, and field measurements, we reconstructed the paleotopography of the SHS site during the Yangshao period (7000–5000 aBP). On this basis, 3D natural and human landscapes during the Yangshao period were rebuilt. The results show that (1) Satellite images acquired at different resolutions can provide multiscale spatial information about the site, and high-precision models of current conditions can be quickly generated from UAV aerial photography. (2) From 1960 to 2020, the shortest distance between the SHS site and the Yellow River was approximately 512 m. The location of bedrock on Mang Mountain can be used to infer the early extent of the northern terrace at the site. (3) Environmental archaeology provided information about the palaeoenvironment of the site area. By incorporating spatial information technology and 3D visualization, we can better restore the early landscape of the SHS site. Our work integrates environmental archaeology, field archaeology, and spatial technology, enabling data and modelling support for the visual interpretation of the SHS site.
Escalating armed conflict threatens World Cultural Heritage sites with irreversible damage. This study develops an integrated risk assessment framework that combines physical monitoring and public perception analysis for heritage sites in conflict zones. The framework uses multi-modal data, including remote sensing imagery for building damage detection, open-source intelligence for armed conflict events, and social media texts for public attention analysis. We construct three indicators: Building Damage Intensity Index (BDII), Conflict Intensity Index (CII), and Public Attention Volume (PAV). The framework is applied to 16 UNESCO World Heritage Sites in Israel/Palestine and Ukraine during 2018–2024. Results show that spatial encroachment on heritage buffer zones, rather than the absolute intensity of damage or conflict, is the main trigger of global public attention. This finding suggests that threats closer to heritage boundaries amplify international concern. The framework offers evidence-based support for heritage risk identification and intervention prioritization.