Prediction and cause investigation of ozone based on a double-stage attention mechanism recurrent neural network  

作　　者：Yuanxin Zhang Fei Li Chaoqiong Ni Song Gao Shuwei Zhang Jin Xue Zhukai Ning Chuanming Wei Fang Fang Yongyou Nie Zheng Jiao 

机构地区：[1]School of Environmental and Chemical Engineering,Shanghai University,Shanghai 200444,China [2]Shanghai Jinshan Environmental Monitoring Station,Shanghai 201500,China [3]School of Economics,Shanghai University,Shanghai 200237,China

出　　处：《Frontiers of Environmental Science & Engineering》2023年第2期83-95,共13页环境科学与工程前沿（英文）

基　　金：the simulation of the WRF-CMAQ model,Key Research and Development Projects of the Shanghai Science and Technology Commission(No.20dz1204000).

摘　　要：Ozone is becoming a significant air pollutant in some regions,and VOCs are essential for ozone prediction as necessary ozone precursors.In this study,we proposed a recurrent neural network based on a double-stage attention mechanism model to predict ozone,selected an appropriate time series for prediction through the input attention and temporal attention mechanisms,and analyzed the cause of ozone generation according to the contribution of feature parameters.The experimental data show that our model had an RMSE of 7.71μg/m3 and a mean absolute error of 5.97μg/m3 for 1-h predictions.The DA-RNN model predicted ozone closer to observations than the other models.Based on the importance of the characteristics,we found that the ozone pollution in the Jinshan Industrial Zone mainly comes from the emissions of petrochemical enterprises,and the good generalization performance of the model is proved through testing multiple stations.Our experimental results demonstrate the validity and promising application of the DA-RNN model in predicting atmospheric pollutants and investigating their causes.

关 键 词：Ozone prediction Deep learning Time series ATTENTION Volatile organic compounds 

分 类 号：X70[环境科学与工程—环境工程]