The classification of architectural style for Chinese traditional settlements (CTSs) has become a crucial task for developing and preserving settlements. Traditionally, the classification of CTSs ...primarily relies on manual work, which is inefficient and time consuming. Inspired by the tremendous success of deep learning (DL), some recent studies attempted to apply DL networks such as convolution neural networks (CNNs) to achieve automated classification of the architecture styles. However, these studies suffer overfitting problems of the CNNs, leading to inferior classification performance. Moreover, most of the studies apply the CNNs as a black box providing limited interpretability. To address these limitations, a new DL classification framework is proposed in this study to overcome the overfitting problem by transfer learning and learning-based data augmentation technique (i.e., AutoAugment). Furthermore, we also employ class activation map (CAM) visualization technique to help understand how the CNN classifiers work to abstract patterns from the input. Specifically, due to a lack of architectural style datasets for the CTSs, a new annotated dataset is first established with six representative classes. Second, several representative CNNs are leveraged to benchmark the new dataset. Third, to address the overfitting problem of the CNNs, a new DL framework is proposed which combines transfer learning and AutoAugment to improve the classification performance. Extensive experiments are conducted on the new dataset to demonstrate the effectiveness of our framework. The proposed framework achieves much better performance than baselines, greatly mitigating the overfitting problem. Additionally, the CAM visualization technique is harnessed to explain what and how the CNN classifiers implicitly learn for recognizing a specified architectural style.
This study constructs a directed weighted network among traditional village buildings based on directional similarity and utilizes social network analysis to identify influential buildings affecting ...spatial order. Key findings include: 1) Centrality Measures; Weighted degree, eigenvector, and betweenness centrality quantify the influence of building nodes in terms of quantity, quality, and importance, respectively. 2) Influential Buildings; High centrality buildings are not necessarily ‘star buildings’. Their impact is implicit and local, contrasting with the explicit and holistic influence of ‘star buildings’. 3) Community Structure; The village forms seven sub-communities with a modularity of 0.681, reflecting ideal community division. Community consistency is influenced by factors like size, the presence of ancient buildings, and morphology. 4) Spatial Order; Centrality distribution among nodes varies between communities. Communities rich in ancient buildings show a complex, organic order, suggesting self-organization, while those with modern buildings exhibit a more rigid layout, indicating imposed order. This research offers methodological insights for traditional village spatial morphology and provides guidance for conservation and planning.
Satellite precipitation products (SPPs) have emerged as an important information source of precipitation with high spatio-temporal resolutions, with great potential to improve catchment water ...resource management and hydrologic modelling, especially in data-sparse regions. As an indirect precipitation measurement, satellite-derived precipitation accuracy is of major concern. There have been numerous evaluation/validation studies worldwide. However, a convincing systematic evaluation/validation of satellite precipitation remains unrealized. In particular, there are still only a limited number of hydrologic evaluations/validations with a long temporal period. Here we present a systematic evaluation of eight popular SPPs (CHIRPS, CMORPH, GPCP, GPM, GSMaP, MSWEP, PERSIANN, and SM2RAIN). The evaluation area used, using daily data from 2007 to 2020, is the Xiangjiang River basin, a mountainous catchment with a humid sub-tropical monsoon climate situated in south China. The evaluation was conducted at various spatial scales (both grid-gauge scale and watershed scale) and temporal scales (annual and seasonal scales). The evaluation paid particular attention to precipitation intensity and especially its impact on hydrologic modelling. In the evaluation of the results, the overall statistical metrics show that GSMaP and MSWEP rank as the two best-performing SPPs, with KGEGrid ≥ 0.48 and KGEWatershed ≥ 0.67, while CHIRPS and SM2RAIN were the two worst-performing SPPs with KGEGrid ≤ 0.25 and KGEWatershed ≤ 0.42. GSMaP gave the closest agreement with the observations. The GSMaP-driven model also was superior in depicting the rainfall-runoff relationship compared to the hydrologic models driven by other SPPs. This study further demonstrated that satellite remote sensing still has difficulty accurately estimating precipitation over a mountainous region. This study provides helpful information to optimize the generation of algorithms for satellite precipitation products, and valuable guidance for local communities to select suitable alternative precipitation datasets.
Ice, Cloud, and land Elevation Satellite-2 (ICESat-2) provides effective photon-counting light detection and ranging (LiDAR) data for estimating forest height across extensive geographical areas. ...Although prior studies have illustrated canopy conditions during leaf-on and leaf-off phases may influence ICESat-2 derived forest heights, a comprehensive understanding of this effect remains incomplete. This study seeks to comprehensively assess how varying canopy conditions (leaf-on/leaf-off) affect ICESat-2 forest height retrieval and modelling. First, the accuracies of ICESat-2 terrain and canopy heights under leaf-on and leaf-off conditions were validated. Second, random forest algorithm was utilized to model forest height by integrating ICESat-2, Sentinel-2, and other ancillary datasets. Finally, we evaluated the influence of leaf-on and leaf-off conditions on forest height retrieval and modelling. Results reveal higher consistency between ICESat-2 and airborne LiDAR-derived terrain heights compared to the agreement between two canopy height datasets. Accuracies of ICESat-2 terrain and canopy heights are higher under leaf-off conditions in contrast to leaf-on conditions. Notably, the accuracies of ICESat-2 terrain and canopy heights under various conditions are closely linked to canopy cover. Furthermore, the accuracy of forest height modelling can be enhanced by combining ICESat-2 data collected during both leaf-on and leaf-off seasons with further eliminating low-quality samples.
Geoparks are home to unique and precious geological sites and have a rich historical and cultural heritage. Most studies have focused on their tourism value and/or educational significance. However, ...far too little attention has been paid to the impact of geopark construction on the local ecological environment. The Xiangxi UNESCO Global Geopark (XXGG) was used as a case study to explore the impact of global geopark construction on local ecological quality. Three ecological indices, including an ecological quality index based on productive, residential, and ecological land use, an improved remote-sensing ecological index (RSEI-2), and net primary productivity (NPP), were adopted to evaluate the ecological quality of XXGG during two periods: before construction (from 2015 to 2017) and during construction of XXGG (from 2018 to 2020). The results show that: (1) in general, all ecological quality indicators showed a downtrend (from 2015 to 2017) followed by an uptrend (from 2018 to 2020), indicating that construction and development of XXGG has had a significant positive effect on local ecological quality. This occurred because a series of environmental protection measures were taken after application to the United Nations Educational, Scientific, and Cultural Organization (UNESCO) Global Geoparks (UGGPs) for membership at the end of 2017. (2) The areas of XXGG with excellent and improved ecological quality are mainly distributed in the northern and southeastern portions, which are located in the protected area with high coverage rates of forest and other vegetation. Poor ecological quality in the east and south is closely related with human activities, such as ethnic tourism development. The results explore the relationship between regional construction of the geopark and ecological effects and provide a scientific reference for sustainable development of global geoparks.
•Impact of a global geopark construction on ecological quality is assessed.•Construction of XXGG has an overall positive effect on local ecological quality.•Human activities such as ethnic tourism negatively affect ecological quality.
Vegetation plays a crucial role in nature, with intricate interactions between it and the geographical environment. The Yangtze River Basin (YRB) refers to the third largest river basin globally and ...an essential ecological security barrier in China. Monitoring vegetation dynamics in the basin is of profound significance for addressing climate change, soil erosion, and biodiversity loss in the basin's ecosystems. Here, we investigate the spatiotemporal variations of vegetation at both the basin and land cover scales in the YRB from 2000 to 2020. We elucidate the determinants driving the changes and explore future normalized difference vegetation index (NDVI) trends. The results indicate that NDVI in the YRB increased at a rate of 0.0032 year−1 (p < 0.01) over the past 21 years, and it is anticipated to maintain an upward trend in the future. Regions in the upper and middle reaches of the YRB demonstrated higher NDVI, whereas regions in the headwater area and the lower reaches showed lower NDVI. Significant vegetation improvement was primarily concentrated in the central part of the basin, while noticeable vegetation degradation was observed in the eastern region. Temperature and wind speed were identified as the primary controlling factors affecting vegetation greenness. Global‐scale climate oscillations played a significant role in driving periodic variations in NDVI, with La Niña events tending to increase NDVI, while El Niño events hindered its rise. Land cover types were influenced by long‐term interactions between natural factors and human activities, although short‐term vegetation variations might be more affected by the latter. Our findings provide valuable insights into the mechanisms behind vegetation variability driven by multiple variables, and the strong vegetation carbon sink capacity advances the conservation and development of ecosystems.
Traditional Chinese buildings serve as a carrier for the inheritance of traditional culture and national characteristics. In the context of rural revitalization, achieving the 3D reconstruction of ...traditional village buildings is a crucial technical approach to promoting rural planning, improving living environments, and establishing digital villages. However, traditional algorithms primarily target urban buildings, exhibiting limited adaptability and less ideal feature extraction performance for traditional residential buildings. As a result, guaranteeing the accuracy and reliability of 3D models for different types of traditional buildings remains challenging. In this paper, taking Jingping Village in Western Hunan as an example, we propose a method that combines multiple algorithms based on the slope segmentation of the roof to extract feature lines. Firstly, the VDVI and CSF algorithms are used to extract the building and roof point clouds based on the MVS point cloud. Secondly, according to roof features, village buildings are classified, and a 3D roof point cloud is projected into 2D regular grid data. Finally, the roof slope is segmented via slope direction, and internal and external feature lines are obtained after refinement through Canny edge detection and Hough straight line detection. The results indicate that the CSF algorithm can effectively extract the roofs of I-shaped, L-shaped, and U-shaped traditional buildings. The accuracy of roof surface segmentation based on slope exceeds 99.6%, which is significantly better than the RANSAC algorithm and the region segmentation algorithm. This method is capable of efficiently extracting the characteristic lines of roofs in low-rise buildings within traditional villages. It provides a reference method for achieving the high-precision modeling of traditional village architecture at a low cost and with high efficiency.
Traditional residences are among the most important tangible cultural heritage. This paper evaluates and explores the quality of individual traditional residences and the heritage value of a complex ...of traditional residences in Western Hunan in China. The former indicates how well the external characteristics of the building are preserved, whilst the latter refers to the integration of use values, ecology principles and cultural features. Based on the survey of the selected 7 traditional villages, the authors have built a spatial database of these villages on the strength of GIS, RS and GPS techniques, and employed an architectural evaluation method to grade the exterior quality of individual traditional residences, followed by the construction of an evaluation indicator system and the use of entropy weight method to score the value of traditional residences, thereby systematically unveiling how indicators influence the value of traditional residences. The results reveal that well-preserved and prime-quality traditional residences are quite rare. Average-quality individual traditional residences outnumber other quality levels in all selected traditional villages. These villages differ in the value of their traditional residences, which is susceptible to both natural and cultural factors. Architectural elements play a dominant role, and the change in architectural form serves as an important criterion for determining whether the traditional residence in question has been transformed into a modern building. The value of traditional rural residences is mainly reflected in the authenticity of the architectural form and the building material, which are crucial to the intact pass-down of their unique architectural styles.
•Traditional residences were systematically investigated based on GIS, RS and GPS.•The quality of individual traditional rural residences was quantified and analyzed.•Well-preserved and prime-quality traditional residences are quite rare.•The entropy weight method was used to estimate the value of traditional residences.•The influencing factors of the value of traditional residences were unveiled.
...there has been no report on network attention to traditional villages. Since the Ministry of Housing and Urban-Rural Development, the Ministry of Culture, and the Ministry of Finance announced the ...first batch of Chinese traditional villages in December 2012, China has announced four batches of 4,153 traditional villages. In these areas, the traffic conditions are good, the overall household income of the residents is high, the education level is relatively good, and the popularity of the Internet is high, so the travel rate of residents is high. 4Strategies for promoting tourism development in Hunan Provincial traditional villages based on network attention 4.1Strengthening propaganda on the Internet platform to enhance the visibility of traditional villages The number of Internet users in China is growing, and the rise of online social media, such as blog, Weibo, and WeChat provides new channels for the promotion and propaganda of tourism in traditional villages. With the characteristic buildings of traditional villages and tourist peripheral products as the carrier, innovation and development will be conducted continuously to drive the development of related tourism products and promote the social and economic development of the region. 4.3 Strengthening the integration of tourism resources in traditional villages and developing practical cooperation mechanisms The cities of different regions can carry out the integration and classification of resources according to the characteristics of traditional villages in the domain. Through the development of practical tourism cooperation mechanisms, cooperation and win-win situation brought by cross-regional sharing, as well as sustainable development will be achieved. 5 Conclusions With Sina Travel Blog as the research platform, 283 Sina travel notes about the traditional villages in Hunan Province were collected using the Octoparse collector, and then the network attention to the traditional villages in Hunan Province was analyzed from the aspects of time and space.