Open AccessResearch of Air Pollutant Concentration Forecasting Based on Deep Learning Algorithms
Author(s) -
Yongming Pan,
Yajie Wang,
Mingzhao Lai
Publication year - 2019
Publication title -
iop conference series. earth and environmental science
Language(s) - English
Resource type - Journals
eISSN - 1755-1307
pISSN - 1755-1315
DOI - 10.1088/1755-1315/300/3/032090
Subject(s) - pollutant , air pollutants , wavelet transform , artificial intelligence , computer science , wavelet , meteorology , data set , series (stratigraphy) , set (abstract data type) , environmental science , algorithm , machine learning , data mining , air pollution , geology , geography , chemistry , paleontology , organic chemistry , programming language
In order to accurately predict the concentration of air pollutants in Shanghai, a prediction model of the concentration of air pollutants in Shanghai based on Wavelet Transform and Long Short-Term Memory (LSTM) was established to predict the concentration of six air pollutants in Shanghai. Firstly, the historical time series of daily air pollutant concentration is decomposed into different frequencies by wavelet decomposition transform and recombined into a set of high-dimensional training data. Secondly, LSTM prediction model is trained with high-dimensional data sets, and parameters are adjusted repeatedly to obtain the optimal prediction model. The results show that the combined model is more accurate than the traditional LSTM model in predicting pollutant concentration.