The accuracy of Seismic Landslide Susceptibility Maps (SLSMs) is imperative for the prevention of seismic landslide disasters. This study enhances the precision of SLSMs by integrating nine distinct machine learning methodologies with the GeoDetector version 0.0.4 tool to filter both numerical and physical factors contributing to landslide susceptibility. The dataset comprises 2317 landslide instances triggered by the 2013 Minxian Ms = 6.6 earthquake, from which redundant factors were pruned using the Recursive Feature Elimination technique. Subsequent evaluations of the optimized factors, both individually and in combination, were conducted through Frequency Ratio analysis and Factor Interaction assessment. The study juxtaposes the Area Under the Receiver Operating Characteristic Curve (AUC) and the accuracy of nine machine learning models before and after factor optimization. The findings indicate an increase in AUC from a maximum of 0.989 to 0.992 in the Random Forest model, and an 8.37% increase in AUC for the SVM model, signifying a notable enhancement in the stability across all models. The establishment of the SLSM notably elevated the frequency ratio in high-risk zones from 50.40 to 85.14, underscoring the efficacy of combining machine learning and detector optimization techniques in sustainable practices. This research proposes a universal framework aimed at eliminating redundancy and noise in SLSMs and hazard risk assessments, thereby facilitating sustainable geological disaster risk management.

The proliferation of developmental projects exerts a profound impact on biodiversity and environmental degradation. In pursuit of assessing ecosystem services, this study introduces an innovative combination optimization methodology that melds direct market assessment with mathematical fuzzy analysis. This approach is designed to elucidate the authentic economic repercussions of land utilization endeavors, facilitating a nuanced exploration of the cost-benefit dynamics across projects of varying magnitudes. This research posits that when ecosystem services are factored into the equation, environmental costs augment the conventional cost structures.Employing a combination optimization model, the research delineates the distinct characteristics of assorted environmental costs. The model integrates direct market valuation, conceptualizing environmental remediation expenses as financial detriments ensuing from environmental contamination. Concurrently, it employs mathematical fuzzy algorithms for the appraisal of potential environmental costs. Subsequently, a synthesis of comprehensive evaluation scores across different project phases is conducted.This investigation selected a residential community and a thermal power station to represent small-scale community initiatives and large-scale national projects, respectively. Cost-benefit analyses were executed based on the ratios derived from the combination optimization model. The MATLAB software was utilized to assess the ecological milieu at various temporal junctures. Findings indicate that the cost-benefit ratio for the small-scale community project stood at 1.051, whereas the large-scale national project yielded a ratio of 24.979. In sum, the combination optimization model demonstrated its efficacy in accurately quantifying the cost-benefits associated with the ecological environment, thereby furnishing comprehensive evaluative outcomes.

With the development of internationalization, the distribution of languages and the office addresses of multinational companies are changing constantly. This paper makes the following research and exploration on this phenomenon: impact on the development of languages around the world. This paper studies the changes of native and second-language users and uses the historical data to predict the development trend by using the gray number series prediction model. Get the types of factors that affect the second language. Then, use fuzzy analytic hierarchy process to calculate the score of each factor. Finally, the global language trend equation is simulated: predictions for the development of language. In this paper, radiation propagation is calculated, and the method of CNN neural network is used to train big data, and the language trend positioning equation is drawn. Finally, the optimal language is obtained by using wavelet analysis and linear programming at different addresses. About model checking, according to the models internal prediction ability and the significance of internal parameters, it is concluded that the model has high practicability, sensitivity, and stability.