Evaluation Of Water Resources Sustainable Utilization Based On Probabilistic Neural Network

The evaluation of sustainable utilization of water resources can provide a reliable basis for the future rational utilization of water resources and scientific management.At the same time,it is also of great significance to the coordinated development of regional social economy,ecological environment and water resources.The research idea is usually to use certain methods or models to describe the complex relationship between the evaluation index and the standard,and then to achieve the sustainable use of water resources in time and space on the classification or sorting.The evaluation of sustainable use of water resources is a major method for the sustainable use of water resources.The results of the evaluation can be divided into two parts: comprehensive index and grade classification.The essence of the grade evaluation is a classification problem,and the evaluation object is divided into different grades.Probabilistic Neural Network(PNN)is a neural network model which can maximize the use of prior knowledge to obtain the optimal solution under Bayes criterion and has better pattern classification.In the course of learning,PNN is used to estimate the conditional probability density of the class by Parzen window function,and Bayes theorem and Bayes decision rule based on minimum risk are used to classify the sample.Therefore,according to the strong PNN classification function,it is applied to the evaluation of sustainable utilization of water resources.In this paper,Chengdu City,Sichuan Province as the study area,to the sustainable use of water resources in Chengdu as the evaluation objectives.From the point of view of sustainability,the key influence is analyzed,and the evaluation index system is initialized.Based on the correlation analysis and Rough Set(RS)theory,14 representative indexes are selected to determine the The final indicator system.Secondly,combined with the PNN classification principle,the PNN water resources sustainable utilization evaluation model is constructed,and the actual data of Chengdu City is estimated from 2013 to 2015,and the evaluation result is calculated by using the established evaluation model.Finally,in order to verify the rationality of the PNN evaluation model and compare with the results of the traditional BP neural network model,it can be seen from the application results that PNN has a certain feasibility and scientificity in the evaluation of water resources sustainable utilization ability,and And achieved a better application effect.