The purpose of the present study is to predict and draw up non-grain cultivated land (NCL) susceptibility map based on optimized Extreme Gradient Boosting (XGBoost) model using the Particle Swarm Optimization (PSO) metaheuristic algorithm. In order to, a total of 184 NCL areas were identified based on historical records, and a total of 16 NCL susceptibility conditioning factors (NCLSCFs) were considered, based on both a systematic literature survey and local environmental conditions. The results showed that the XGBoost model optimized by PSO performed well in comparison to other machine learning algorithms; the values of sensitivity, specificity, PPV, NPV, and AUC are 0.93, 0.89, 0.88, 0.93, and 0.96, respectively. Slope, rainfall, fault density, distance from fault and drainage density are most important variables. According to the results of this study, the use of meta-innovative algorithms such as PSO can greatly enhance the ability of machine learning models.
21 January 2023 in Advances in Mathematical Physics
Based on the Hirota bilinear method, using the heuristic function method and mathematical symbolic computation system, various exact solutions of the ( )- dimensional Boiti–Leon–Manna–Pempinelli equation including the block kink wave solution, block soliton solution, periodic block solution, and new composite solution are obtained. Upon selection of the appropriate parameters, three-dimensional and contour diagrams of the exact solution were generated to illustrate their properties.
Groundwater assessment has several technical deficiencies, especially because the decision-making platform for basic data collection, analysis, and evaluation has not been established. Based on the computer architecture theory and business processing logic, we designed a set of groundwater resource overload evaluation systems using the ArcGIS platform and Python language based on the comprehensive analysis of many research schemes. According to the pressure–state–response (PSR) theoretical programming model, the system pre-sets the evaluation index from three aspects: overexploitation, bearing capacity, and overload. The entropy weight method was used to determine the factor weight. The system was used to evaluate and analyze the groundwater overload in Xi’an, and the performance and accuracy of the system were also verified. The results showed that the serious overload area of groundwater in Xi’an was located in the alluvial fan area of Yanliang District, Gaoling District, and Huyi District, and the alluvial fan area of Lintong District, City Six Districts, and Zhouzhi County. The general overload area was located in the alluvial plain area of City Six Districts, Chang’an District, the flood plain and the first terrace of Huyi District, the loess tableland area of Zhouzhi County, and the alluvial fan area of Lantian County. The remaining areas were not overloaded. The evaluation results matched the study, which confirmed that the evaluation system was stable and that the results were reliable.