With the implementation of China’s rural revitalization strategy, the sustainable preservation of traditional dwellings has become a research priority. Moreover, with the aging population in the countryside increasing, the limited mobility of the elderly may result in them receiving daily corneal illuminance too low for a healthy circadian stimulus. This work aims to explore the relationship between circadian and daylighting design parameters inside traditional dwellings and to develop easy-to-use methods for guiding indoor circadian design in traditional dwellings in western Hunan. Additionally, it seeks to promote the digitalization and informatization of traditional dwellings in western Hunan for preservation purposes, aiming to integrate these efforts with sustainable tourism and community development, which supports the local economy while preserving cultural heritage. The main contributions are as follows: (i) Systematic evaluation of the indoor lighting and circadian status of traditional Miao dwellings in western Hunan. (ii) Simplification and application of the CS and corneal illuminance fitting model for guiding circadian design, especially suitable for indirect indoor circadian aspects of lighting in daylight scenarios. The simplified model provides quick circadian design feedback and promotes healthy circadian concepts. Its accuracy has been verified by fitting it with simulation data from Climate Studio daylighting software. (iii) Exploration of daylighting conditions using simulation software, focusing on ρ′ (the area-weighted average of room surface reflectance), ρ (the reflectance of the surface where the first reflection occurs), and the WWR (Window-to-wall ratio) in two different types of traditional dwellings. This also includes defining the dwelling parameter intervals necessary for an appropriate circadian stimulus in traditional Miao dwellings in western Hunan. (iv) The analysis suggests that enhancing ρ′ has a greater effect on circadian lighting than WWR, indicating that increasing ρ′ should be the preferred method for achieving high-quality and efficient circadian lighting.

The digital recognition and preservation of historical architectural heritage has become a critical challenge in cultural inheritance and sustainable urban development. While deep learning methods show promise in architectural classification, existing models often struggle to achieve ideal results due to the complexity and uniqueness of historical buildings, particularly the limited data availability in remote areas. Focusing on the study of Chinese historical architecture, this research proposes an innovative architectural recognition framework that integrates the Swin Transformer backbone with a custom-designed Global Channel and Spatial Attention (GCSA) mechanism, thereby substantially enhancing the model’s capability to extract architectural details and comprehend global contextual information. Through extensive experiments on a constructed historical building dataset, our model achieves an outstanding performance of over 97.8% in key metrics including accuracy, precision, recall, and F1 score (harmonic mean of the precision and recall), surpassing traditional CNN (convolutional neural network) architectures and contemporary deep learning models. To gain deeper insights into the model’s decision-making process, we employed comprehensive interpretability methods including t-SNE (t-distributed Stochastic Neighbor Embedding), Grad-CAM (gradient-weighted class activation mapping), and multi-layer feature map analysis, revealing the model’s systematic feature extraction process from structural elements to material textures. This study offers substantial technical support for the digital modeling and recognition of architectural heritage in historical buildings, establishing a foundation for heritage damage assessment. It contributes to the formulation of precise restoration strategies and provides a scientific basis for governments and cultural heritage institutions to develop region-specific policies for conservation efforts.

Although traditional Chinese wooden residential buildings have historically adapted to their respective regions, they face challenges in meeting modern living standards, particularly with regard to insufficient indoor natural lighting. This study focuses on three representative Tujia residences: the “L-shaped” dwellings, the “U-shaped” dwellings, and the courtyard residences, with the aim of improving their indoor lighting performance. Using Ecotect 2011 software for computer simulations, the study investigates the impact of altering the geometric shapes of courtyards in traditional wooden residential buildings on the lighting of the central room. The results indicate that, for the “L-shaped” dwellings, the geometric dimensions of the courtyard have little impact on the lighting of the central room. For the “U-shaped” dwellings, the optimal courtyard geometry is achieved with a well index (WI) of 1, balancing residential functionality, economic considerations, and indoor lighting performance. Regarding the courtyard residences, the best results are obtained by minimizing the building height while maximizing the well depth index to 1. Additionally, the study shows that a square layout of 90° ∗ 90° is most favorable for courtyards, effectively balancing lighting performance, functionality, and aesthetics. These findings provide valuable insights for the renovation of existing traditional residences and the design of new buildings, aiming to enhance overall indoor lighting effectiveness.

This study employed unsupervised machine learning clustering algorithms to systematically analyze the spatial layout characteristics of residential buildings in villages along the Miao Frontier Wall and Miao Frontier Corridor in Western Hunan. The results indicated significant differences between the two regions in terms of the number of building clusters, distribution patterns, and compactness. A comparative analysis of the K-means and DBSCAN algorithms revealed that K-means is more effective in uncovering the internal spatial layout characteristics of settlements. Further analysis showed that villages along the Miao Frontier Wall exhibited greater diversity and complexity, whereas those along the Miao Frontier Corridor demonstrated higher clustering efficiency and denser internal building distribution. These differences can be attributed to variations in historical functions, geographical environments, planning concepts, and social structures. This research uncovers the spatial layout patterns of traditional settlements and proposes a machine learning-based approach to cultural heritage preservation, providing a theoretical foundation for future heritage conservation and spatial optimization, thereby promoting the sustainable development and protection of traditional cultural heritage.