Research on PCA-PSO-SVM ozone prediction considering spatial-temporal features
DONG Hong-zhao1, WANG Le-heng1, TANG Wei2, YANG Qiang3, SHE Yi-ni1
1. Intelligent Traffic System Joint Research Institute, Zhejiang University of Technology, Hangzhou 310014, China; 2. Hangzhou Institute of Environment Sciences, Hangzhou 310014, China; 3. Hangzhou Huanyan Technology Co., Ltd. Hangzhou 310014, China
Abstract：The current ozone predicting method usually lacks the effect of the spatial covering of ozone pollution coupled with its strong self-correlation within a certain period. To compensate such a deficiency, a PCA-PSO-SVM based model of ozone combining prediction considering spatial-temporal features was proposed. Using wavelet analysis and system clustering, the fluctuation characteristics in time series and spatial distributing similarity of the ozone was extracted, and the maximum daily 8-hour average concentration of the ozone was predicted resorting to PCA-PSO-SVM model which composes of the principal component analysis (PCA) and particle swarm optimization based support vector machine (PSO-SVM). The model was verified by the experiment with the historical data of atmospheric pollutants and meteorological situation from 2016 to 2018 in urban Hangzhou. The results showed that the ozone predicting accuracy by the PCA-PSO-SVM model considering spatial-temporal features was significantly improved. Compared with the PCA-PSO-SVM model without spatial-temporal features, the predicting accuracy was raised 19%. The experiment also proved that the temperature exerts the largest influence among all the meteorological factors on the ozone prediction. The proposed model was showed its robustness to obtain high predicting accuracy even in case of the weak weather forecast.
[2019] 53号.Ministry of ecology and environment.Notice on printing and Distributing "comprehensive treatment plan for volatile organic compounds in key industries"[N]. 2019, Huan Da Qi
[2019] No.53.
[2]
蒋璐璐,钱燕珍,杜坤,等.宁波市近地层臭氧浓度变化及预测[J]. 气象与环境学报, 2016,32(1):53-59.Jiang L L, Qian Y Z, Du K, et al. Variation of ozone concentration and prediction in surface layer in Ningbo[J]. Journal of Meteorology and Environment, 2016,32(1):53-59.
[3]
董红召,许慧鹏,卢滨,等.城市交通道路氮氧化物浓度的CART回归树预测研究[J]. 环境科学学报, 2019,39(4):1086-1094.Dong H Z, Xu H P, Lu B, et al. A CART-based approach to predict nitrogen oxide concentration along urban traffic roads[J]. Acta Scientiae Circumstantiae, 2019,39(4):1086-1094.
[4]
李昕,安俊琳,王跃思,等.北京气象塔夏季大气臭氧观测研究[J]. 中国环境科学, 2003,23(4):18-22.Li X, An J L, Wang Y S, et al. Studies on the measurement of atmospheric ozone in summer with Beijing meteorological tower[J]. China Environmental Science, 2003,23(4):18-22.
[5]
王占山,李云婷,陈添,等.北京城区臭氧日变化特征及与前体物的相关性分析[J]. 中国环境科学, 2014,34(12):3001-3008.Wang Z S, Li Y T, Chen T, et al. Analysis on diurnal variation characteristics of ozone and correlations with its precursors in urban atmosphere of Beijing[J]. China Environmental Science, 2014,34(12):3001-3008.
[6]
Liu S K, Cai S, Chen Y, et al. The effect of pollutional haze on pulmonary function[J]. Journal of Thoracic Disease, 2016,8(1):41-56.
[7]
Chen K, Zhou L, Chen X D, et al. Acute effect of ozone exposure on daily mortality in seven cities of Jiangsu Province, China:No clear evidence for threshold[J]. Environmental Research, 2017,155:235-241.
[8]
Hu H, Ha S, Xu X H. Ozone and hypertensive disorders of pregnancy in Florida:Identifying critical windows of exposure[J]. Environmental Research, 2017,153:120-125.
[9]
郭晓雷.城市空气质量预报方法研究综述[J]. 科技传播, 2011, (15):14-19.Guo X L. Review of urban air quality prediction methods[J]. Science and Technology Communication, 2011,(15):14-19.
[10]
邓涛,吴兑,邓雪娇,等.珠江三角洲一次典型复合型污染过程的模拟研究[J]. 中国环境科学, 2012,32(2):193-199.Deng T, Wu D, Deng X J, et al. Simulation of a typical complex pollution process over Pearl River Delta area[J]. China Environmental Science, 2012,32(2):193-199.
[11]
HJ2.2-2018环境影响评价技术导则[S].HJ2.2-2018 Technical guidelines for environmental impact assessment[S].
[12]
申倩倩.上海地区臭氧数值模拟研究[D]. 上海:华东师范大学, 2011.Shen Q Q. Numerical Simulation of Ozone in Shanghai[D]. Shang hai:East China Normal University, 2011.
[13]
苏筱倩,安俊琳,张玉欣.基于支持向量机回归和小波变换的O3预报方法[J]. 中国环境科学, 2019,39(9):3719-3726.Su Y Q, An J L, Zhang Y X. Support vector machine regression forecasting of O3 concentrations based on wavelet transformation[J]. China Environmental Science, 2019,39(9):3719-3726.
[14]
Wang H W, Li X B, Wang D S, et al. Regional prediction of ground-level ozone using a hybrid sequence-to-sequence deep learning approach[J]. Journal of Cleaner Production, 2020,253.
[15]
Zhu S L, Lian X Y, Haixia Hu L J, et al. Daily air quality index forecasting with hybrid models:A case in China[J]. Environmental Pollution, 2017,231.
[16]
吴春霖,李琦,侯俊雄,等.卷积神经网络的PM2.5预报模型[J]. 测绘科学, 2018,43(8):68-75.Wu C L, Li Q, Hou J X, et al. PM2.5 concentration prediction using convolutional neural networks[J]. Science of Surveying and Mapping, 2018,43(8):68-75.
[17]
丁愫,陈报章,王瑾,等.基于决策树的统计预测模型在臭氧浓度时空分布预测中的应用研究[J]. 环境科学学报, 2018,38(8):3229-3242.Ding S, Chen B Z, Wang J, et al. An applied research of decision-tree based statistical model in forecasting the spatial-temporal distribution of O3[J]. Acta Scientiae Circumstantiae, 2018,38(8):3229-3242.
[18]
邹思琳,任晓晨,王成功,等.时间精度与空间信息对神经网络模型预测PM2.5浓度的影响[J/OL]. 北京大学学报(自然科学版), 2020:1-11.Zou S L, Ren X C, Wang C G, et al. Impacts of Temporal Resolution and Spatial Information on Neural-Network-Based PM2.5 Prediction Model[J/OL]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2020:1-11.
[19]
苏筱倩,安俊琳,张玉欣,等.支持向量机回归在臭氧预报中的应用[J]. 环境科学, 2019,40(4):1697-1704.Su Y Q, An J L, Zhang Y X, et al. Application of Support Vector Machine Regression in Ozone Forecasting[J]. Environmental Science, 2019,40(4):1697-1704.
[20]
梁卓然,顾婷婷,杨续超,等.基于环流分型法的地面臭氧预测模型[J]. 中国环境科学, 2017,37(12):4469-4479.Liang Z R, Gu T T, Yang X C, et al. Study on circulation classification based surface ozone concentration prediction model, China Environmental Science, 2017,37(12):4469-4479.
[21]
Gao M, Yin L T, Ning J C. Artificial neural network model for ozone concentration estimation and Monte Carlo analysis[J]. Atmospheric Environment, 2018,184.
[22]
吴锴,康平,于雷,等. 2015~2016年中国城市臭氧浓度时空变化规律研究[J]. 环境科学学报, 2018,38(6):2179-2190.Wu K, Kang P, Yu L, et al. Pollution status and spatio-temporal variations of ozone in China during 2015~2016[J]. Acta Scientiae Circumstantiae, 2018,38(6):2179-2190.
[23]
曾贤刚,阮芳芳,姜艺婧.中国臭氧污染的空间分布和健康效应[J]. 中国环境科学, 2019,39(9):4025-4032.Zeng X G, Ruan F F, Jiang Y J. Spatial distribution and health effects of ozone pollution in China[J]. China Environmental Science, 2019, 39(9):4025-4032.
[24]
H. Oliver Gao. Day of week effects on diurnal ozone/NOx cycles and transportation emissions in Southern California[J]. Transportation Research Part D, 2007,12(4).
[25]
Salazar L, Nicolis O, Ruggeri F, et al. Predicting hourly ozone concentrations using wavelets and ARIMAmodels[J]. Neural Comput & Applic, 2019,31:4331-4340.
[26]
罗恢泓,袁自冰,郑君瑜,等.上海夏季臭氧生成机制时空变化特征及其影响因素研究[J]. 环境科学学报, 2019,39(1):154-168.Luo H H, Yuan Z B, Zheng J Y, et al. Spatio-temporal variation of summertime ozone formation mechanism in Shanghai and its impact factors[J]. Acta Scientiae Circumstantiae, 2019,39(1):154-168.
[27]
Jan B, Yousufzai M A K, Afridi F A K, et al. Study the stratospheric ozone irregularity over Pakistan atmospheric region in perspectives of wavelet analysis[J]. Arab J. Geosci., 2019,12:603.
[28]
耿红,宣莹莹,蔡夏童,等.太原市2014年春节期间常规大气污染物浓度变化及聚类分析[J]. 环境科学学报, 2015,35(4):965-974.Geng H, Xuan Y Y, Cai X T, et al. Mass concentration variation and cluster analysis of urban air pollutants in Taiyuan, Shanxi Province during Chinese New Year of 2014[J]. Acta Scientiae Circumstantiae, 2015,35(4):965-974.
[29]
He H D, Li M, Wang W L, et al. Prediction of PM2.5 concentration based on the similarity in air quality monitoring network[J]. Building and Environment, 2018,137.
[30]
Iizuka A, Shirato S, Mizukoshi A, et al. A Cluster Analysis of Constant Ambient Air Monitoring Data from the Kanto Region of Japan[J]. Int. J. Environ. Res. Public Health 2014,11:6844-6855.
[31]
Huang Y S, Shen L, Liu H. Grey relational analysis, principal component analysis and forecasting of carbon emissions based on long short-term memory in China[J]. Journal of Cleaner Production, 2019,209.
[32]
林升梁,刘志.基于RBF核函数的支持向量机参数选择[J]. 浙江工业大学学报, 2007,(2):163-167.Lin S L, Liu Z. Parameter selection in SVM with RBF kernel function[J]. Journal of Zhejiang University of Technology, 2007,(2):163-167.
[33]
齐冰,牛彧文,杜荣光,等.杭州市近地面大气臭氧浓度变化特征分析[J]. 中国环境科学, 2017,37(2):443-451.Qi B, Niu Y W, Du R G, et al. Characteristics of surface ozone concentration in urban site of Hangzhou[J]. China Environmental Science, 2017,37(2):443-451.
[34]
刘建,吴兑,范绍佳,等.前体物与气象因子对珠江三角洲臭氧污染的影响[J]. 中国环境科学, 2017,37(3):813-820.Liu J, Wu D, Fang S J, et al. Impacts of precursors and meteorological factors on ozone pollution in Pearl River Delta[J]. China Environmental Science, 2017,37(3):813-820.
[35]
齐艳杰,于世杰,杨健,等.河南省臭氧污染特征与气象因子影响分析[J]. 环境科学, 2020,41(2):587-599.Qi Y J, Yu S J, Yang J, et al. Analysis of characteristics and meteorological influence factors of ozone pollution in Henan Province[J]. Environmental Science, 2020,41(2):587-599.
[36]
易睿,王亚林,张殷俊,等.长江三角洲地区城市臭氧污染特征与影响因素分析[J]. 环境科学学报, 2015,35(8):2370-2377.Yi R, Wang Y L, Zhang Y J, et al. Pollution characteristics and influence factors of ozone in Yangtze River Delta[J]. Acta Scientiae Circumstantiae, 2015,35(8):2370-2377.
[37]
卢滨,黄成,卢清,等.杭州市工业源VOCs排放清单及排放特征[J]. 环境科学, 2018,39(2):533-542.Lu B, Huang C, Lu Q, et al. Emission inventory and pollution characteristics of industrial VOCs in Hangzhou, China[J]. Environmental Science, 2018,39(2):533-542.
[38]
周广强,耿福海,许建明,等.上海地区臭氧数值预报[J]. 中国环境科学, 2015,35(6):1601-1609.Zhou G Q, Geng F H, Xu J M, et al. Numerical ozone forecasting over shanghai[J]. China Environmental Science, 2015,35(6):1601-1609.
[39]
GB3095-2012环境空气质量标准[S].
[40]
王玫,郑有飞,柳艳菊,等.京津冀臭氧变化特征及与气象要素的关系[J]. 中国环境科学, 2019,39(7):2689-2698.Wang M, Zheng Y F, Liu Y J, et al. Characteristics of ozone and its relationship with meteorological factors in Beijing-Tianjin-Hebei Region[J]. China Environmental Science, 2019,39(7):2689-2698.
[41]
王黎明,吴香华,赵天良,等.基于距离相关系数和支持向量机回归的PM2.5浓度滚动统计预报方案[J]. 环境科学学报, 2017,37(4):1268-1276.Wang L M, Wu X H, Zhao T L, et al. A scheme for rolling statistical forecasting of PM2.5 concentrations based on distance correlation coefficient and support vector regression[J]. Acta Scientiae Circumstantiae, 2017,37(4):1268-1276.
[42]
宋国君,国潇丹,杨啸,等.沈阳市PM2.5浓度ARIMA-SVM组合预测研究[J]. 中国环境科学, 2018,38(11):4031-4039.Song G J, Guo X D, Yang X, et al. ARIMA-SVM combination prediction of PM2.5 concentration in Shenyang[J]. China Environmental Science, 2018,38(11):4031-4039.
[43]
李梓铭,赵秀娟,孙兆彬,等.基于相似集合预报技术的臭氧预报释用研究[J]. 中国环境科学, 2020,40(2):475-484.Li Z M, Zhao X J, Sun Z B, et al. Research on the interpretation and correction of numerical ozone forecast based on Analog Ensemble[J]. China Environmental Science, 2020,40(2):475-484.
[44]
Manolis A, Kostas L, Vassiliki K, et al. Correcting temperature and humidity forecasts using Kalman filtering:potential for agricultural protection in Northern Greece[J]. Atmospheric Research, 2004,71(3).
[45]
Kong X B, Liu X J, Shi R F, et al. Wind speed prediction using reduced support vector machines with feature selection[J]. Neurocomputing, 2015,169.
[46]
智协飞,黄闻.基于卡尔曼滤波的中国区域气温和降水的多模式集成预报[J]. 大气科学学报, 2019,42(2):197-206.Zhi X F, Huang W. Multimodel ensemble forecasts of surface air temperature and precipitation over China by using Kalman filter[J]. Transactions of Atmospheric Sciences, 2019,42(2):197-206.
