Prediction of PM2.5 Daily Concentration of Guangzhoubased on Neural Network Algorithms

1. School of Atmospheric Sciences, Sun Yat-sen University, Zhuhai 519082; 2. Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai), Zhuhai 519082; 3. School of Marine Sciences, Guangxi University, Nanning 530004; † Corresponding author, E-

Abstract Autoregressive integrated moving average (ARIMA) model, back propagation (BP) neutral network and long short-term memory (LSTM) are used to predict the daily concentration of PM2.5 in 2019 in Guangzhou city of China from 2015 to 2019. The effect of ensemble empirical mode decomposition (EEMD), temporal resolution on model prediction is explored in this paper. The results show that EEMD is able to improve significantly the prediction ability of the model on the low-frequency part of PM2.5 sequence. Increased temporal resolution can improve the prediction accuracy, with more input data. Since PM2.5 (t−1) is used as the input data, the model can only predict PM2.5 for 1 day in advance. To increase the prediction time window, we adopt a rolling forecast method, using PM2.5 (t) prediction value as the input data for PM2.5 (t+1). The result shows that the rolling forecast method allows the model to forecast PM2.5 (t+n) with a comparable MAE compared to the experiment without the rolling forecast method. In this paper, the ARIMA model (the time accuracy of input data is 6 hours) has the best prediction accuracy, and the minimum MAE value can reach 6.478. Key words Guangzhou city; PM2.5; autoregressive integrated moving average model (ARIMA); back propagation (BP); long short-term memory networks (LSTM); ensemble empirical mode decomposition (EEMD)

[1] Lelieveld J, Evans J S, Fnais M, et al. The contribution of outdoor air pollution sources to premature mortality on a global scale. Nature, 2015, 525: 367– 371 [2] Li Jin, Liu Huan, Lv Zhaofeng, et al. Estimation of PM2.5 mortality burden in China with new exposure estimation and local concentration-response function. Environmental Pollution, 2018, 243: 1710–1718

[3] Baker K R, Foley K M. A nonlinear regression model estimating single source concentrations of primary and secondarily formed PM2.5. Atmospheric Environment,2011,45(22): 3758–3767 [4] 周广强, 谢英, 吴剑斌, 等. 基于 WRF-CHEM 模式的华东区域 PM2.5 预报及偏差原因. 中国环境科学, 2016, 36(8): 2251–2259 [5] 王茜, 吴剑斌, 林燕芬. CMAQ模式及其修正技术在上海市 PM2.5预报中的应用检验. 环境科学学报, 2015, 35(6): 1651–1656 [6] 任晓晨, 邹思琳, 唐娴, 等. 基于集合经验模态分解和BP神经网络的北京市PM2.5预报研究. 北京大学学报(自然科学版), 2019, 55(4): 615–625 [7] 郑毅, 朱成璋. 基于深度信念网络的 PM2.5 预测. 山东大学学报(工学版), 2014, 44(6): 19–25 [8] 戴李杰, 张长江, 马雷鸣. 基于机器学习的 PM2.5短期浓度动态预报模型. 计算机应用, 2017, 37(11): 3057–3063 [9] 曲悦, 钱旭, 宋洪庆, 等. 基于机器学习的北京市PM2.5浓度预测模型及模拟分析. 工程科学学报, 2019, 41(3): 401–407 [10] Lu Xingcheng, Lin Changqing, Li Ying, et al. Assessment of health burden caused by particulate matter in southern China using high-resolution satellite observation. Environment International, 2017, 98: 160–170 [11] Huang N E, Shen Z, Long S R, et al. The empirical mode decomposition and the hilbert spectrum for nonlinear and non-stationary time series analysis. Proceedings Mathematical Physical & Engineering Sciences, 1998, 454: 903–995 [12] Wu Z H, Huang N E. Ensemble empirical mode decomposition: a noise-assisted data analysis method. Advances in Adaptive Data Analysis, 2009, 1(1): 1– 41 [13] Hochreiter S, Schmidhuber J. Long short-term memory. Neural computation, 1997, 9(8): 1735–1780 [14] 李建东, 铁学熙, 曹军骥. 城市地区 PM2.5周末效应的初步研究. 地球环境学报, 2015, 6(4): 224–230 [15] 张雪梅. 广州某区 PM2.5和气态污染物质量浓度的日变化特征及其相关性分析. 广州环境科学, 2017, 32(1): 8–11 [16] 薛同来, 赵冬晖, 韩菲. 基于 BP 神经网络的北京市PM2.5 浓度预测. 新型工业化, 2019, 9(8): 88‒91 [17] 张立, 王腾军, 刘帅令, 等. 基于 CPSO-BP 神经网络的 PM2.5 浓度预测模型. 甘肃科学学报, 2020, 32(2): 47‒50 [18] 蒋奇峰, 杜景林, 周芸, 等. 一种基于 QPSO-RBF模型预测 PM2.5浓度值的方法研究及应用. 计算机应用与软件, 2020, 37(9): 202‒208