Siwei Yu

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.

This study examines the spatiotemporal evolution of Tibetan villages in western Sichuan through state transition models and predictive simulations to understand their complex dynamics and key driving factors. Using a combination of multivariate time-series analysis and chaotic attractor identification, the research identifies forest cover, economic growth, employment rates, road density, and communication network coverage as critical determinants of village trajectories. For instance, Molo Village recovers rapidly with a 10% increase in regional economic growth, while Xisuo Village becomes unstable with employment rate fluctuations above 2%. Shenzuo Village benefits from improved road density, and Minzu Village’s stability depends on forest cover. Jiangba Village relies on the growth of irrigated farmland and communication network coverage, whereas Kegeyi Village exhibits periodic dynamics and high sensitivity to employment variations. The findings underscore the inherent complexity and nonlinearity of rural systems, revealed through chaotic attractor analysis, which highlights the system’s sensitivity to initial conditions and external shocks. The article provides actionable insights into resilience mechanisms and offers practical recommendations for the sustainable development of culturally and ecologically sensitive regions. Emphasis on tailored management strategies is essential to meet the challenges faced by these unique systems in the face of modernization and environmental change.

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.

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.