Air Quality Prediction Based on Wavelet Analysis and Machine Learning

Abstract

This thesis takes the historical weather time series of Chongqing as experimental samples. Firstly, this thesis uses wavelet transform to organize the data, and then divides the sample data into training and test sets to verify the accuracy of the evaluation of the Naive Bayes Model. Secondly, the Naive Bayes Model is compared with currently used machine learning models such as SVM, XGBoost, bagging, and random forest. Finally, the results show that the Naive Bayes Model has high stability and accuracy for the air quality assessment of Chongqing, and it can be applied to the evaluation of urban ambient air quality.