Evaluation of Ecological Environment Competitiveness of Hunan Province Based on Prefecture Level Cities

Based on the data of 13 eco-environmental indicators of 14 prefecture level cities in Hunan Province from 2014 to 2018,this paper quantitatively evaluated the eco-environmental competitiveness and its advantages and disadvantages by principal component analysis(PCA).The results showed that:(1)the overall ecoenvironmental competitiveness of Hunan Province was relatively high,whereas the competitiveness level of each city and prefecture was quite different.The comprehensive score of eco-environmental competitiveness of Changsha City was 2.96,ranking the first,and Zhangjiajie city ranking the last with a score of-1.60,which indicated that there was an obvious difference in the level of eco-environmental competitiveness among different regions.(2)The overall eco-environmental competitiveness of cities and prefectures in Western Hunan Province was weak.Among the 14 prefectures and cities in Hunan Province,the comprehensive scores of eco-environmental competitiveness of 6 prefectures and cities were negative,whereas the scores of Zhangjiajie,Xiangxi and Huaihua in Western Hunan were all lower than the others.In the face of increasingly serious environmental problems,cities and prefectures should adjust measures according to local conditions and put forward specific measures to enhance environmental competitiveness.In particular,cities and prefectures in Western Hunan should give full play to their advantages in ecological resources,take the path of green development,enhance the competitiveness of ecological environment,and provide support for local economic development.

Evaluationof eco-environmental competitiveness in south China hilly region

South China is located in the subtropical zone,with excellent hydrothermal conditions and abundant species.Compared with other regions in China,the environment and natural resources have obvious innate advantages.The crisscross of hills and small plains are the most typical topographic and geomorphic features in South China.Its evaluation of eco-environmental competitiveness is different from other regions in China in terms of index selection and evaluation process.Based on the literature results,combining with the particularity of the southern hilly region and according to certain principles,we construct an evaluation model of ecological environment in southern hilly region,which includes five first-level indicators of ecological resources,environmental status,enconomic society,management response and environmental potential and fifteen second-level index sperated from the first-level,such as forest coverage rate and ambient air quality composite index and so on.Taking Hunan Province,a tipical region of southern hills,as an empirical example to analyse,the conclusion has been verified by other scholars and the new model is more operable than the existing models and methods,which indicates that the model constructed is practical and feasible.

Water quality prediction of copper-molybdenum miningbeneficiation wastewater based on the PSO-SVR model

The mining-beneficiation wastewater treatment is highly complex and nonlinear.Various factors like influent quality,flow rate,pH and chemical dose,tend to restrict the effluent effectiveness of miningbeneficiation wastewater treatment.Chemical oxygen demand(COD)is a crucial indicator to measure the quality of mining-beneficiation wastewater.Predicting COD concentration accurately of miningbeneficiation wastewater after treatment is essential for achieving stable and compliant discharge.This reduces environmental risk and significantly improves the discharge quality of wastewater.This paper presents a novel AI algorithm PSO-SVR,to predict water quality.Hyperparameter optimization of our proposed model PSO-SVR,uses particle swarm optimization to improve support vector regression for COD prediction.The generalization capacity tested on out-of-distribution(OOD)data for our PSOSVR model is strong,with the following performance metrics of root means square error(RMSE)is 1.51,mean absolute error(MAE)is 1.26,and the coefficient of determination(R2)is 0.85.We compare the performance of PSO-SVR model with back propagation neural network(BPNN)and radial basis function neural network(RBFNN)and shows it edges over in terms of the performance metrics of RMSE,MAE and R2,and is the best model for COD prediction of mining-beneficiation wastewater.This is because of the less overfitting tendency of PSO-SVR compared with neural network architectures.Our proposed PSO-SVR model is optimum for the prediction of COD in copper-molybdenum mining-beneficiation wastewater treatment.In addition,PSO-SVR can be used to predict COD on a wide variety of wastewater through the process of transfer learning.