Rural tourism is a new driving force for achieving rural revitalization and development, promoting rural economic prosperity, and serving as a new industrial approach to achieving the transformation and upgrading of farmers’ livelihoods. This paper focuses on Manas County as the research subject and employs farmer questionnaire interviews and participatory rural appraisal methods to categorize villages into four types: “scenic area-dependent” villages, “industry-dependent” villages, “folklore-dependent” villages, and “suburban-dependent” villages. Based on the sustainable livelihood analysis framework proposed by the Department for International Development, we developed a sustainable livelihood framework for farm households in Manas County and analyzed the effects of rural tourism on farm households’ livelihood capital and livelihood strategies as the watershed of the rural tourism takes shape, taking livelihood capital and livelihood strategies as the entry point. The factors influencing the livelihood capital and livelihood options of farm households in the context of rural tourism are analyzed. The results show that: (1) The overall livelihood capital of farmers engaging in rural tourism is significantly greater than that of farmers not participating in rural tourism. Additionally, variations exist in the livelihood capital of different types of rural tourism within villages. (2) Participation in rural tourism significantly influences farmers’ choices of livelihood strategies. Compared with individuals who do not engage in rural tourism, those involved in rural tourism are more likely to opt for self-management livelihood strategies. The proportion of self-managed farmers in villages based around scenic areas is the highest. (3) The effect of rural tourism on farm households in Manas County is generally positive, and various types of villages yield different impact effects. (4) Participation in rural tourism significantly increases the possibility of farmers choosing self-management livelihood strategies, while it reduces the possibility of farmers choosing agriculture-oriented livelihood strategies. In all villages, except those dependent on industry, the decision to engage in rural tourism significantly impacts farmers’ selection of self-management livelihood strategies.

Rapid social development has led to serious air pollution problems in cities, and air pollutants, including gaseous pollutants and particulate matter, have an important impact on climate, the environment, and human health. This study analyzed the characteristics, potential sources, and causes of air pollution in the Wu-Chang-Shi urban cluster. The results showed that NO₂, CO, SO₂, PM₁₀, and PM_2.5 had a tendency to decrease, while O₃ showed an increasing trend. The concentrations of SO₂, NO₂, CO, PM_2.5, and PM₁₀ showed the highest values in winter and the lowest values in summer, with similar seasonal variations. However, the concentration of O₃ was highest in the summer and lowest in the winter. Compared with the pollutant concentrations in other Chinese cities, PM_2.5, PM₁₀, and NO₂ are more polluted in the Wu-Chang-Shi urban. Meteorological factors have a greater impact on pollutant concentrations, with higher concentrations of major pollutants observed when wind speeds are low and specific wind directions are observed, and higher secondary pollutant O₃ concentrations observed when wind speeds are low and specific wind directions are observed. The backward trajectory and concentration weighting analysis show that the particulate pollutants in the Wu-Chang-Shi urban in winter mainly come from Central Asia and surrounding cities. O₃ showed an increasing trend before and after the novel coronavirus outbreak, which may be related to changes in NO_X, volatile organic compounds, and solar radiation intensity, and the concentrations of SO₂, NO₂, CO, PM₁₀, and PM_2.5 showed an overall decreasing trend after the outbreak and was smaller than before the outbreak, which is related to the reduction of industrial and anthropogenic source emissions during the outbreak.

Feature selection (FS) constitutes a critical stage within the realms of machine learning and data mining, with the objective of eliminating irrelevant features while guaranteeing model accuracy. Nevertheless, in datasets featuring a multitude of features, choosing the optimal feature poses a significant challenge. This study presents an enhanced Sand Cat Swarm Optimization algorithm (MSCSO) to improve the feature selection process, augmenting the algorithm’s global search capacity and convergence rate via multiple innovative strategies. Specifically, this study devised logistic chaotic mapping and lens imaging reverse learning approaches for population initialization to enhance population diversity; balanced global exploration and local development capabilities through nonlinear parameter processing; and introduced a Weibull flight strategy and triangular parade strategy to optimize individual position updates. Additionally, the Gaussian–Cauchy mutation strategy was employed to improve the algorithm’s ability to overcome local optima. The experimental results demonstrate that MSCSO performs well on 65.2% of the test functions in the CEC2005 benchmark test; on the 15 datasets of UCI, MSCSO achieved the best average fitness in 93.3% of the datasets and achieved the fewest feature selections in 86.7% of the datasets while attaining the best average accuracy across 100% of the datasets, significantly outperforming other comparative algorithms.

Accurate prediction of PM_2.5 concentration is important for pollution control, public health, and ecological protection. However, due to the nonlinear nature of PM_2.5 data, the accuracy of existing methods suffers and performs poorly in both short-term and long-term predictions. In this study, a deep learning hybrid prediction model based on clustering and quadratic decomposition is proposed. The model utilizes the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) to decompose the PM_2.5 sequences into multiple intrinsic modal function components (IMFs), and clusters and re-fuses the subsequences with similar complexity by permutation entropy (PE) and K-means clustering. For the fused high-frequency sequences, a secondary decomposition is performed using the whale optimization algorithm (WOA) optimized variational modal decomposition (VMD). Finally, the nonlinear and temporal features are captured for prediction using the long- and short-term memory neural network (LSTM). Experiments show that this proposed model exhibits good stability and generalization ability. It does not only make accurate predictions in the short term, but also captures the trends in the long-term prediction. There is a significant performance improvement over the baseline models. Further comparisons with existing models outperform the current state-of-the-art models.

The fundamental component of the ecological compensation system, as well as the crucial basis for its efficient functioning, is calculating the ecological compensation amount and establishing the ecological compensation standard. This study integrates the ecological footprint with natural capital monetization and other methods by introducing a natural capital accounting system. From the standpoint of natural capital supply and demand, it also builds an accounting framework for ecological compensation standards that is standardized, dynamic, and regionally differentiated while taking local socioeconomic aspects into account. We determined the amount of ecological compensation by using Xinjiang as the research object and calculating and analyzing the features of regional and temporal changes in the monetary and physical quantities of natural capital in Xinjiang from 2010 to 2020. The findings show that from 2010 to 2020, Xinjiang’s ecological footprint increased by 1.26 times in physical terms and 1.21 times in monetary terms and that its ecological carrying capacity increased by 4.13% in physical terms and 9.42% in monetary terms. The ecological deficit continues to grow in physical and monetary terms, with a per capita ecological deficit in 2020 of 19.92 s-nha/cap and 70,100 CNY/cap in physical and monetary terms, respectively. The amount of ecological compensation required to be paid in Xinjiang increased from CNY 5659 million to CNY 10,259 million, and the per capita ecological compensation payment standard increased from 259.42 CNY/cap/yr to 396.11 CNY/cap/yr. In summary, Xinjiang’s natural capital supply is insufficient to meet the demand for consumption, and the ecological deficit is growing with time, necessitating the payment of ecological compensation. The study’s results lay the foundation for formulating and implementing ecological compensation policies in Xinjiang and provide theoretical support for constructing ecological civilization in Xinjiang. In addition, the ecological compensation accounting framework constructed in this study organically integrates natural capital theory, ecosystem services, and socioeconomic influencing factors, which enriches the methodology of accounting for ecological compensation standards, and, at the same time, can be used as a paradigm of a dynamic and equitable ecological compensation accounting framework to further promote its use at different scales and regions.