A new ensemble spatio-temporal PM2.5 prediction method based on graph attention recursive networks and reinforcement learning. (September 2022)

• Record Type: Journal Article
• Authors: Tan, Jing; Liu, Hui; Li, Yanfei; Yin, Shi; Yu, Chengqing
• Is Part Of: Chaos, solitons and fractals. Volume 162(2022)
• Publication Date: 2022-09
• Subjects: AI artificial intelligence -- ARIMA autoregressive integrated moving average -- CNN convolutional neural network -- CO carbon monoxide -- CPSOGSA chaotic particle swarm optimization method combined with the gravitation search algorithm -- DBN deep belief network -- ELM extreme learning machine -- ENN error encoding network -- ESN echo state network -- GA genetic algorithm -- GAT graph attention network -- GCN graph convolutional neural -- GRU gated recursive unit -- GWO grey wolf optimizer -- ICA independent component analysis -- LSTM long and short-term memory -- MAE mean absolute error -- MAPE mean absolute percentage error -- MLP multilayer perceptron -- NO nitric oxide -- NO2 nitrogen dioxide -- O3 ozone -- PM particulate matter -- PM2.5 inhalable particulate matter with a diameter of less than 2.5 μm -- PM10 inhalable particulate matter with a diameter of less than 10 μm -- SO2 sulfur dioxide -- PSO particle swarm optimizer -- RBF radial basis function -- RL reinforcement learning -- RMSE root mean square error -- RNN recurrent neural network -- SAE sacked autoencoder -- SVM support vector machine -- TCN temporal convolutional network; Multi-data-driven modeling -- Graph attention network -- Sarsa -- Spatio-temporal pollutant prediction; Chaotic behavior in systems -- Periodicals; Solitons -- Periodicals; Fractals -- Periodicals; Chaotic behavior in systems; Fractals; Solitons; Periodicals; 003.7
• DOI: 10.1016/j.chaos.2022.112405
• Languages: English
• ISSNs: 0960-0779

Abstract

Abstract: Inhalable particulate matter with a diameter of less than 2.5 μm spatio-temporal prediction technology is an important tool for environmental governance in urban traffic congestion areas. A new Ensemble Graph Attention Reinforcement Learning Recursive Network is proposed to create a multi-data-driven spatio-temporal prediction method with excellent application value. The modeling process includes three basic steps. In step I, the graph attention network is used to effectively aggregate the spatio-temporal correlation characteristics of the original air pollutant data. In step II, the features extracted from the graph attention network are transferred to the long short-term memory network and the temporal convolutional network and the prediction models are constructed respectively. In step III, the reinforcement learning algorithm effectively analyzes the adaptability of the two different models to the data sets and realizes ensemble based on continuous optimization of weights. By comparing the experimental results of the listed cases, the following points can be summarized: (a) the graph attention network can effectively aggregate the spatio-temporal correlation characteristics of the original data and optimize the performance of the predictor. (b) The reinforcement learning algorithm effectively realizes the integration of several neural networks and improves the comprehensive adaptability and generalization capabilities of the model. (c) The proposed model in this paper has great application potential and value in spatial and temporal prediction and has achieved better performance than the other 25 benchmark models. Highlights: A new multi-index driven spatio-temporal PM2.5 prediction model is proposed. GAT is applied to study the spatio-temporal correlation between different sites. The Sarsa algorithm is used to build the ensemble learning model with the strongest ability to adapt to different data.