Prediction of Comprehensive Pollution Index in Shandong Province Based on LSTM Neural Network

Abstract

Economic growth is an important factor affecting environmental pollution. It is of great significance to effectively control and prevent environmental pollution by using a variety of economic factor indicators in a certain area to predict the local pollution level. In this paper, a comprehensive pollution index prediction model based on deep learning method is proposed and verified by using the relevant data of Shandong Province over the years. Firstly, the entropy weight method is used to construct the comprehensive pollution index, and the nonlinear processing ability of LSTM neural network to multivariable time series data is used to construct the prediction model to realize the prediction of the comprehensive pollution index. Compared with the traditional cyclic neural network model and BP neural network model, the results show that the LSTM neural network model has the best prediction effect, and with the passage of time, the LSTM model can effectively learn the time series information in the time series, reflecting the advantages of the model in predicting the comprehensive pollution index.