Research on PM2.5 Concentration Prediction Based on the CE-AGA-LSTM Model

Abstract

The PM2.5 index is an important basis for measuring the degree of air pollution. The accurate prediction of PM2.5 concentration has an important guiding role in air pollution prevention and control. The Pearson Correlation Coefficient (PCC) is a common index used to mine the correlation between meteorological factors and other air pollutants. However, this index cannot be used to mine non-linear correlations, nor can it quantitatively analyze the weight of each related attribute. In order to accurately explore the correlation between meteorological factors and other air pollutants and to achieve an accurate prediction of PM2.5 concentration, this paper proposes a short- and long-time memory (LSTM) network prediction model based on Copula entropy (CE) and the adaptive genetic algorithm (AGA). By calculating CE, the correlation between multiple meteorological factors and various atmospheric pollutants and PM2.5 was analyzed. The correlation of influencing factors was sorted according to the size of the correlation coefficients. The contribution rate of meteorological factors and atmospheric pollutants to PM2.5 concentration was determined, used as the weight of each influencing factor and predicted as the input data of the prediction model. In this paper, a long- and short-term memory network (LSTM) suitable for time series data was selected as the prediction model, while the selection of model parameters was taken into account, and the relevant parameters were sought by an adaptive genetic algorithm (AGA). The air pollutant data and meteorological data of Beijing from 1 January 2016 to 31 December 2016 were selected, and MAE and RMSE were used as evaluation indexes. By comparing the experimental results of the CE-AGA-LSTM with those of other eight prediction models (LR, SVM, RF, ARMA, ST-LSTM, LSTM, CE-LSTM and CE-RNN), we found that among the models, the CE-AGA-LSTM model provided the lowest MAE and RMSE values, i.e., 14.5 and 21.88, respectively. At the same time, the loss rate and accuracy of the CE-AGA-LSTM model were evaluated, and the experimental results verified the validity of the model.

Deep-learning architecture for PM2.5 concentration prediction: A review

“…Wu et al. [ 69 ] proposed a novel DL model that combined an attention-based GRU and a convolutional encoder with adaptive gated activation (CE-AGA) for air quality prediction. Transfer learning was used in some papers to leverage pre-trained models for related tasks and improve the performance of air quality prediction models.…”

“…[ 63 ] 2022 Beijing, China Conv1D-LSTM H/S/T+1 20.76 11.20 - 0.96 Wu et al. [ 69 ] 2022 Beijing, China CE-AGA-LSTM H/S/T+1 21.88 14.49 - 0.95 Waseem et al. [ 49 ] 2022 Lahore/Karachi/Islamabda, Pakistan LSTM H/S/T+1 - - 11.70/7.40/9.50 - D/S/T+1 - - 28.2/42.1/15.1 - Gul et al.…”

Prediction of Pollutant Concentration Based on Spatial–Temporal Attention, ResNet and ConvLSTM

“…At this stage, the research methods are divided into two categories according to the characteristics of the research methods [8]: numerical model-based prediction methods and data-driven model-based prediction methods. The first is the prediction method of numerical modeling that simulates the process of emission, diffusion, transformation, and removal of air pollutants through meteorological principles and statistical methods so as to achieve the prediction of pollutant concentrations [9]; the second is the prediction method based on data-driven modeling, which is based on making predictions by learning and analyzing pollutant historical data [10].…”

Long-Term Prediction of Particulate Matter2.5 Concentration with Modal Autoformer Based on Fusion Modal Decomposition Algorithm

“…With the development of computer technology, deep learning models can provide higher numerical prediction accuracy due to their nonlinear mapping and adaptive advantages; among them, recurrent neural networks are widely used for air pollutant concentration prediction because of their ability to save and learn information from existing time data. Many scholars have used long short-term memory network (LSTM), gated neural unit (GRU), and other models to perform short-term prediction of PM 2.5 in various places [3][4][5][6][7][8][9][10][11][12]. For instance, Zhao Yanming constructed an LSTM model with spatiotemporal correlation to predict PM 2.5 concentration for 36 h in the Beijing-Tianjin-Hebei region [5].…”