Improvement Of Gene Expression Programming And Its Application In Haze Concentration Prediction

The rapid expansion of industrialization and urbanization has led to serious urban haze pollution.PM2.5 is an important component of haze,and its prediction is the crux to haze prevention.In this paper,an improved gene expression programming algorithm is used to predict PM2.5 concentration.The main work in this paper is as follows:(1)Research on the current status of PM2.5 concentration prediction.In view of the lack of interpretation and inability to know the occurrence mechanism of PM2.5concentration in solving PM2.5 concentration prediction problems in most existing artificial intelligence algorithms,the gene expression programming algorithm is used to predict PM2.5 concentration,and the function relationship between PM2.5 concentration and various influencing factors can be obtained,and the internal mechanism of PM2.5concentration and various influencing factors can be revealed.(2)A Knowledge-guided and Human Intervention-based Gene Expression Programming algorithm is proposed.Knowledge guidance and human intervention are introduced into the traditional gene expression programming algorithm.Knowledge guidance is realized based on the knowledge base.A prior knowledge base is established by mining previous research results in PM2.5 concentration to determine the decision variables of the algorithm.Artificial intervention consists of individual intervention and population intervention to improve the optimization ability of the algorithm.(3)Application of the Knowledge-guided and Human Intervention-based Gene Expression Programming algorithm.KHI-GEP algorithm was used to predict the PM2.5concentration in Xi ’an in the short term.Finally,the explicit expression of PM2.5concentration prediction was obtained,and the comparative experiments with the related prediction algorithms in the literature were carried out,which proved the effectiveness of KHI-GEP algorithm.Finally,the PM2.5 concentration prediction verification software is developed.The study of this paper shows that the KHI-GEP algorithm can not only predict the PM2.5 concentration in Xi ’an with high accuracy,but also obtain the explicit expression of PM2.5 concentration prediction.The obtained expression reveals the relationship between PM2.5 concentration and various influencing factors.The prediction model is of guiding significance for the prevention and control of haze in Xi ’an.At the same time,it also has reference value to the prevention and control of PM2.5 and haze in other areas.