Intelligent Recommendation Method For Site Pollution Risk Control And Remediation Mode

In recent years,with the rapid development of urbanization in China,a large number of "polluted plots" have appeared in lots of cities and their surrounding areas.Site pollution has brought huge adjustments to soil pollution risk control and remediation work and economic development in China,and also brought significant potential risks to the surrounding environment and public health.With the increasing application of big data intelligence technologies in the environmental field and the increasing amount of environmental mass data,it is still unclear how to use big data intelligence technologies to deeply integrate site environmental management to improve the intelligence,precision and efficiency of site pollution risk control.In view of this,based on the big data platform,through structured hierarchical storage and search technology,using case-based reasoning(CBR)and machine learning methods,the site pollution risk control and remediation mode intelligent recommendation research were carried out,and drew the following conclusions:(1)The case representation method and the numerical model of case selection similarity calculation were determined.Referring to the closed and relocated enterprise plot information survey form in the Ministry of Ecology and Environment Office Soil Letter [2017] No.67 "Notice on Printing and Issuing a Series of Technical Documents for Enterprise Land Investigation in Key Industries" and relevant content of site pollution risk control and remediation cases that have been collected,the basic framework of site pollution risk control and remediation case base was determined.And through literature research,a numerical model for calculating the similarity of case selection was determined.(2)The case selection indicator system of site pollution risk control and remediation mode was established.According to the numerical model of similarity between cases,the indicator types were divided into logical indicator and numerical indicator,and determined the value of each indicator and the rules and levels of each indicator.The weight of each indicator was determined by analytic hierarchy process(AHP),and the consistency test was carried out.The random consistency index met the consistency requirements.By consulting the opinions and suggestions of relevant experts in the industry,the preset threshold value of this research was set to 0.8,and the 20 th case was selected for case selection method verification.The results indicated that the case selection method of this research was available.(3)The method of site pollution risk control and remediation scheme recommendation system was determined,which realized fast search to find matching source cases.By studying the way and content of case base,the structure design and system development of the scheme recommendation system were carried out,and the case retrieval query page based on Web technology was established.Similar cases were retrieved in the case database by using a k-nearest neighbor(KNN)algorithm and an analytic hierarchy process,and the scheme recommendation function was realized.