Ecosystem service values of gardens in the Yellow River Basin,China

Studies on the ecosystem service value(ESV)of gardens are critical for informing evidence-based land management practices based on an understanding of the local ecosystem.By analyzing equivalent value factors(EVFs),this paper evaluated the values of 11 ecosystem services of gardens in the Yellow River Basin of China in 2019.High-precision land use survey data were used to improve the accuracy of the land use classification,garden areas,and spatial distribution of the ESVs of gardens.The results showed that garden ecosystem generally had high ESVs,especially in terms of the ESV of food production,which is worthy of further research and application to the practice of land use planning and management.Specifically,the value of one standard EVF of ecosystem services in 2019 was 3587.04 CNY/(hm^(2)·a),and the ESV of food production of gardens was much higher than that of croplands.Garden ecosystem provided an ESV of 1348.66×10^(8)CNY/a in the Yellow River Basin.The areas with the most concentrated ESVs of gardens were located in four regions:downstream in the Shandong-Henan zone along the Yellow River,mid-stream in the Shanxi-Shaanxi zone along the Yellow River,the Weihe River Basin,and upstream in the Qinghai-Gansu-Ningxia-Inner Mongolia zone along the Yellow River.The spatial correlation of the ESVs in the basin was significant(global spatial autocorrelation index Moran's I=0.464),which implied that the characteristics of high ESVs adjacent to high ESVs and low ESVs adjacent to low ESVs are prominent.In the Yellow River Basin,the contribution of the ESVs of gardens to the local environment and economy varied across regions.We also put forward some suggestions for promoting the construction of ecological civilization in the Yellow River Basin.The findings of this study provide important contributions to the research of ecosystem service evaluation in the Yellow River Basin.

Factor value determination and applicability evaluation of universal soil loss equation in granite gneiss region

Six types of runoff plots were set up and an experimental study was carried out to examine natural rate of soil and water loss in the granite gneiss region of northern Jiangsu Province in China. Through correlation analysis of runoff and soil loss during 364 rainfall events, a simplified and convenient mathematical formula suitable for calculating the rainfall erosivity factor （R） for the local region was established. Other factors of the universal soil loss equation （USLE model） were also determined. Relative error analysis of the soil loss of various plots calculated by the USLE model on the basis of the observed values showed that the relative error ranged from -3.5% to 9.9% and the confidence level was more than 90%. In addition, the relative error was 5.64% for the terraced field and 12.36% for the sloping field in the practical application. Thus, the confidence level was above 87.64%. These results provide a scientific basis for forecasting and monitoring soil and water loss, for comprehensive management of small watersheds, and for soil and water conservation planning in the region.

Evaluation of Yarn Quality and Optimization of Cotton Spinning Parameter Based on Factors Analysis

In this paper, the spinning parameters are optimized by using the method of factor analysis. The yarns obtained from four different spinning parameters are evaluated by this method. Two common factors, fineness unevenness and tenacity level, are extracted from the seven yarn-quality indexes. The accumulative contribution percentage of the two factors is up to 91.813%,and much information in the yarn-quality indexes is reflected by the two factors. Then the score of each factor is calculated to evaluate the quality of yarn. Based on that, the techniques are optimized. The result is well in line with spinning practices, so it is testified feasibly to use this method to optimize spinning parameter.

A novel OFS–TLBO–SVR hybrid model for optimal budget allocation of government schemes to maximize GVA at factor cost

Support Vector Regression (SVR) has already been proved to be one of the mostreferred and used machine learning technique in various fields. In this study, wehave addressed a predictive-cum-prescriptive analysis for finalizing fundallocations by the Government at center to the schemes under Central Plan andto the schemes under States and Union Territories Plan, with a goal to maximizeGross Value Added (GVA) at factor cost. Here, we have proposed a hybridmachine learning model comprising of OFS (Orthogonal Forward Selection),TLBO (Teaching Learning Based Optimization) and SVR for the prediction ofGVA at factor cost. In this model, referred as OFS–TLBO–SVR hybrid model,SVR is at the core of prediction mechanism, OFS is for identifying the relevantfeatures, and TLBO is to support in optimizing the free parameters of SVR andagain TLBO is used for optimizing the governable attributes of data.