This study employs cultural landscape gene theory to deconstruct traditional village landscapes into five key gene units and examines their interactions through field surveys, GIS mapping, and multivariate analysis (PCA and AHP). Four gene types are identified: primary, additional, mixed, and variant. Each type fulfills distinct roles: primary genes (e.g., religious beliefs) define the core cultural identity; additional genes (architectural and artistic elements) reinforce spatial and structural stability; mixed genes (linguistic and festive traditions) reflect adaptive intercultural blending; and variant genes (e.g., evolving settlement patterns) respond to socio-environmental dynamics. The synergistic functioning of these genes contributes to the resilience and continuity of cultural landscapes. This research proposes a systematic framework for interpreting the complexity of ethnic heritage spaces. It provides theoretical insights and empirical references for sustainable ethno-rural planning and preserving cultural identity and diversity.

This study takes the landscape space of traditional Tibetan villages in western Sichuan as the research object, and three national-level traditional villages of different Tibetan clans in Gyatso, Amdo and Baima Tibet were selected as samples. Using the fractal theory, combined with counting-box dimension measurement and spatial analysis methods, it comparatively analyzes the fractal characteristics of their landscape space and their influencing factors. The study finds that the landscape space of these villages has certain fractal characteristics, which are characterized by self-similarity and irregularity. The fractal characteristics of different villages are influenced by various factors such as geographic location, natural conditions, religious beliefs, folk costumes, etc., showing differences and diversity. There is a certain correlation between the fractal dimension and the distribution of landscape elements and spatial patterns, which can be used to describe the complexity and diversity of landscape space pattern. The article believes that the fractal theory provides a new perspective and method for analyzing the landscape space of traditional Tibetan villages, which helps to reveal its intrinsic formation mechanism and cultural connotation and provides new insights for the protection of traditional village heritage and the maintenance of cultural traditions. Meanwhile, the study also points out the limitations and shortcomings of the fractal theory in the study of traditional villages and puts forward directions and suggestions for future research.

This study employs an artificial neural network optimization algorithm, enhanced with a Genetic Algorithm-Back Propagation (GA-BP) network, to assess the service quality of urban water bodies and green spaces, aiming to promote healthy urban environments. From an initial set of 95 variables, 29 key variables were selected, including 17 input variables, such as water and green space area, population size, and urbanization rate, six hidden layer neurons, such as patch number, patch density, and average patch size, and one output variable for the comprehensive value of blue-green landscape quality. The results indicate that the GA-BP network achieves an average relative error of 0.94772%, which is superior to the 1.5988% of the traditional BP network. Moreover, it boasts a prediction accuracy of 90% for the comprehensive value of landscape quality from 2015 to 2022, significantly outperforming the BP network’s approximate 70% accuracy. This method enhances the accuracy of landscape quality assessment but also aids in identifying crucial factors influencing quality. It provides scientific and objective guidance for future urban landscape structure and layout, contributing to high-quality urban development and the creation of exemplary living areas.

The article examines the spatial distribution characteristics and influencing factors of traditional Tibetan “Bengke” residential architecture in Luhuo County, Ganzi Tibetan Autonomous Prefecture, Sichuan Province. The study utilizes spatial statistical methods, including Average Nearest Neighbor Analysis, Getis-Ord Gi*, and Kernel Density Estimation, to identify significant clustering patterns of Bengke architecture. Spatial autocorrelation was tested using Moran’s Index, with results indicating no significant spatial autocorrelation, suggesting that the distribution mechanisms are complex and influenced by multiple factors. Additionally, exploratory data analysis (EDA), the Analytic Hierarchy Process (AHP), and regression methods such as Lasso and Elastic Net were used to identify and validate key factors influencing the distribution of these buildings. The analysis reveals that road density, population density, economic development quality, and industrial structure are the most significant factors. The study also highlights that these factors vary in impact between high-density and low-density areas, depending on the regional environment. These findings offer a comprehensive understanding of the spatial patterns of Bengke architecture and provide valuable insights for the preservation and sustainable development of this cultural heritage.

With the improvement of remote sensing image resolution, remote sensing image scene classification has become a major difficulty in the research of remote sensing Urban green space spatial layout and site selection. Complex data and network structure affect the processing effect of the traditional Convolutional neural network model, so it is particularly important to design a more efficient Convolutional neural network. This research will first expand the convolution design of the Convolutional neural network to improve the scope of model recognition, then select two methods of structural pruning and separable knowledge distillation for lightweight processing of the model, and finally introduce relevant models for comparative experiments to verify the lightweight effect of the model. The experimental results show that the global average accuracy of the lightweight model based on structural pruning is 95.5%, and the Kappa coefficient value is 0.947; The global classification accuracy of the lightweight model based on knowledge distillation reaches 95.60%, with a Kappa coefficient value of 0.939. It only uses 38.419MB of storage space to recognize a remote sensing image, 4698352 model parameters, and 1397527639 floating-point operations per second. The results show that the expansion convolution and network pruning methods improve the classification performance of the Convolutional neural network, improve the accuracy of the model, and the knowledge distillation method has a better effect in reducing the complexity and making up for the loss of the classification performance of the network model.

This study employs an integrated analytical framework combining the Social-Ecological System (SES) and Driver-Pressure-State-Impact-Response (DPSIR) models, supplemented by quantitative methodologies including the Entropy Weight Method (EWM), Generalized Additive Model (GAM), Lasso regression, and shallow neural networks, to conduct a systematic resilience assessment of six representative Tibetan villages in western Sichuan based on longitudinal data from 2015 to 2022. The analysis reveals significant differences in resilience levels among the villages, primarily influenced by multiple factors. Disposable income and employment are key positive drivers that enhance adaptive capacity and resilience. Conversely, excessive reliance on policy interventions may constrain local self-organization and adaptive governance. The study highlights the complexity of balancing ecological sustainability with economic growth, underscoring the need for flexible and inclusive policy frameworks. Furthermore, the findings indicate that integrating top-down policies with community-based governance can effectively mitigate external pressures. Key recommendations involve promoting economic diversification via agroecology and cultural tourism, enhancing local governance capacity, and adopting adaptive environmental policies. These strategies are crucial for reducing dependence on traditional agriculture and alleviating resource pressures. The insights gained from this study deepen the understanding of restoration mechanisms in ecologically fragile areas and contribute to the development of effective strategies for sustainable management.