The Forecasting of PM2.5 Using a Hybrid Model Based on Wavelet Transform and an Improved Deep Learning Algorithm

Abstract

In recent years, the haze has caused serious troubles to people's lives, with the continuous increase of PM2.5 emissions. The accurate prediction of PM2.5 is very crucial for policy makers to make predictive measures. Due to the nonlinearity of the PM2.5 time series, it is difficult to predict accurately. Despite some studies about PM2.5 being proposed, the problem of the LSTM (long short-term memory) gradient disappearance and random selection of wavelet orders and layers isn't still solved. In this study, a novel model based on WT (wavelet transform)-SAE (stacked autoencoder)-LSTM is proposed. Firstly, six study sites from China are taken as examples and WT is used to decompose PM2.5 time series into several low-and high-frequency components based on different samples. Secondly, the decomposed components are predicted based on SAE-LSTM. Finally, the predicted results are reconstructed in view of all low-and highfrequency components and the predicted results are obtained. The results imply that: (1) the forecasting performance of SAE-LSTM is better than that of other models (e.g., BP (back propagation)) used for comparison; (2) for six different PM 2.5 samples, four orders five layers, five orders six layers, five orders seven layers, three orders six layers, five orders seven layers, and five orders six layers are the most appropriate. The conclusion that such a novel model may help to enhance the accuracy of PM 2.5 prediction can be drawn.INDEX TERMS PM 2.5 time series, wavelet transform, stacked autoencoder, long short-term memory, prediction.

Microscopic Pore Structure of Surrounding Rock for Underground Strategic Petroleum Reserve (SPR) Caverns in Bedded Rock Salt

“…The dynamic development of the world economy means that the demand for energy is increasing from year to year in virtually all sectors of this economy [1,2]. Energy is closely related to economy, environment, and social development [3][4][5]. Especially with the fast development of the economy and the resulting rapid growth of energy consumption [6][7][8][9][10][11][12][13], the need for energy is increasingly growing, especially for fossil energy such as crude oil, leading to the increasing dependence on foreign oil every year [14].…”

Numerical simulation and simplified calculation method for heat exchange performance of dry air cooler in natural gas pipeline compressor station

“…A detached eddy simulation algorithm is developed for stratified turbulent flows with low or moderate Reynolds numbers on unstructured meshes. 23 In recent years, many scholars [24][25][26][27] have studied pipeline operation and optimization by using mathematical model prediction method, which provides a new way idea for us to solve the calculation problem of natural temperature drop.…”

Spatial assessment of landslide risk using two novel integrations of neuro-fuzzy system and metaheuristic approaches; Ardabil Province, Iran

“…The computational deficiencies (e.g. local minima (Akkurt et al 2003;Qiao, Tian, et al 2019;Qiao and Yang 2019c) and dimension dangers ) associated with conventional intelligent models have driven the engineers to employ metaheuristic algorithms to remedy them. Two well-tried notions of these techniques are GA and PSO, which have shown high efficiency in earlier researches for optimizing predictor models.…”