Machine-learning-based model and simulation analysis of PM2.5 concentration prediction in Beijing
-
摘要: 對北京市周邊8個點多個壓力高度的溫度、濕度和風速數據, 以及北京市PM2.5污染數據進行了分析和歸一化處理, 建立了反向傳播神經網絡(back propagation, BP)、卷積神經網絡(convolutional neural network, CNN) 和長短期記憶模型(long short-term memory, LSTM) 對上述氣象數據和污染數據進行訓練, 訓練結果表明: 反向傳播神經網絡模型和卷積神經網絡模型對未來1 h的PM2.5污染等級的預測準確率較低, 而長短期記憶模型的準確率較高.使用長短期記憶模型預測未來1 h的PM2.5污染值與實際值十分接近, 表明北京市的PM2.5污染與其周邊地區的氣象條件關系密切.通過利用長短期記憶模型對不同壓力高度的氣象數據進行訓練和對比, 得出在利用氣象數據預測污染時, 僅使用近地面氣象數據比使用多個高度上的氣象數據更加準確.Abstract: In recent years, the air quality in China has become a matter of serious concern. Among the available indicators for evaluating air quality, PM2.5 is one of the most important. It comprises a complex mixture of extremely small particles and liquid droplets emitted into the air, whose diameters are no more than 2.5 μm. Environments with a high PM2.5 index are extremely harmful to human health. Once inhaled, these particles can affect the heart and lungs and cause serious health problems. Air pollution is closely related to meteorological conditions such as wind speed, wind direction, atmospheric stability, temperature, and air humidity. With the development of various machine learning methods, deep learning models based on neural networks are increasingly applied in air pollution research. In this study, the temperature, humidity, wind velocity data at different pressure altitudes from 8 locations around Beijing and average of PM2.5 data in Beijing were analyzed and normalized. Multi-dimensional data was ideal for research applications using machine learning methods. and three neural network models were built, including the back propagation (BP), convolutional neural network (CNN), and long short-term memory (LSTM) models, and trained them using the meteorological and PM2.5 data.The results indicate that the accuracies of the back propagation and convolutional neural network models in predicting the PM2.5 pollution level in the next hour is much lower than that of the long short-term memory model. The PM2.5 pollution index predicted for the next hour by the long short-term memory model is very close to the actual value. This result reveals the strong relationship between the PM2.5 pollution index of Beijing and the local meteorological conditions. The long short-term memory model is trained using meteorological data from different pressure altitudes, and found it to be more accurate in predicting pollution levels when using near-surface meteorological data than that obtained from multiple altitudes.
-
Key words:
- machine learning /
- PM2.5 /
- meteorological condition /
- neural networks /
- long short-term memory /
- pollution prediction
-
圖 2 2013~2016年PM2.5日均值. (a) 2013年; (b) 2014年; (c) 2015年; (d) 2016年
Figure 2. Daily average PM2.5 values from 2013 to 2016: (a) 2013; (b) 2014; (c) 2015; (d) 2016
圖 7 長短期記憶模型對2016年12月PM2.5數值的預測曲線
Figure 7. PM2.5 prediction curve using LSTM model in December 2016
圖 8 基于一個壓力高度數據的LSTM模型對2016年12月PM2.5數值的預測曲線
Figure 8. PM2.5 prediction curve using LSTM model based on data from one pressure altitude in December 2016
中文字幕在线观看表 1 空氣質量指數級別與PM2.5對應值
Table 1. Air quality index level and PM2.5 values
空氣質量指數等級 空氣質量指數類別 PM2.5/(mg·m-3) 一級 優 0~50 二級 良 51~100 三級 輕度污染 101~150 四級 中度污染 151~200 五級 重度污染 201~300 六級 嚴重污染 ＞300 
下載: 導出CSV
-
參考文獻
[1] Tai A P K, Mickley L J, Jacob D J. Correlations between fine particulate matter (PM2.5) and meteorological variables in the United States: implications for the sensitivity of PM2.5 to climate change. Atmos Environ, 2010, 44(32): 3976 doi: 10.1016/j.atmosenv.2010.06.060 [2] Pateraki S, Asimakopoulos D N, Flocas H A, et al. The role of meteorology on different sized aerosol fractions (PM10, PM2.5, PM2.5-10). Sci Total Environ, 2012, 419: 124 doi: 10.1016/j.scitotenv.2011.12.064 [3] Zhao X J, Zhang X L, Xu X F, et al. Seasonal and diurnal variations of ambient PM2.5 concentration in urban and rural environments in Beijing. Atmos Environ, 2009, 43(18): 2893 doi: 10.1016/j.atmosenv.2009.03.009 [4] Pan B F, Zhao Y L, Li J J, et al. Analysis of the scavenging efficiency on PM2.5 concentration of some kinds of meteorological factors. Environ Sci Technol, 2012, 25(6): 41 doi: 10.3969/j.issn.1674-4829.2012.06.012潘本鋒, 趙熠琳, 李健軍, 等. 氣象因素對大氣中PM2.5的去除效應分析. 環境科技, 2012, 25(6): 41 doi: 10.3969/j.issn.1674-4829.2012.06.012 [5] Yan W L, Zhou D P, Wang Y F, et al. Concentrations and size distributions of inhalable particles in summer and winter in Shenyang. J Appl Meteorol Sci, 2008, 19(4): 435 doi: 10.3969/j.issn.1001-7313.2008.04.007嚴文蓮, 周德平, 王揚峰, 等. 沈陽冬夏季可吸入顆粒物濃度及尺度譜分布特征. 應用氣象學報, 2008, 19(4): 435 doi: 10.3969/j.issn.1001-7313.2008.04.007 [6] Liu J, Zhang X L, Xu X F, et al. Comparison analysis of variation characteristics of SO2, NOx, O3 and PM2.5 between rural and urban areas, Beijing. Environ Sci, 2008, 29(4): 1059 doi: 10.3321/j.issn:0250-3301.2008.04.036劉潔, 張小玲, 徐曉峰, 等. 北京地區SO2、NOx、O3和PM2.5變化特征的城郊對比分析. 環境科學, 2008, 29(4): 1059 doi: 10.3321/j.issn:0250-3301.2008.04.036 [7] Dong X L, Liu D M, Yuan Y S, et al. Pollution characteristics and influencing factors of atmospheric particulates in Beijing during the summer of 2005. Chin J Environ Eng, 2007, 1(9): 100 doi: 10.3969/j.issn.1673-9108.2007.09.022董雪玲, 劉大錳, 袁楊森, 等. 北京市2005年夏季大氣顆粒物污染特征及影響因素. 環境工程學報, 2007, 1(9): 100 doi: 10.3969/j.issn.1673-9108.2007.09.022 [8] Sillman S. The relation between ozone, NOx and hydrocarbons in urban and polluted rural environments. Atmos Environ, 1999, 33(12): 1821 doi: 10.1016/S1352-2310(98)00345-8 [9] Zhou J X. Correlative analysis on relationship between changes of several main contaminations and some meteorological elements. J Appl Meteorol Sci, 2005, 16(Suppl): 123 https://www.cnki.com.cn/Article/CJFDTOTAL-YYQX2005S1016.htm周江興. 北京市幾種主要污染物濃度與氣象要素的相關分析. 應用氣象學報, 2005, 16(增刊): 123 https://www.cnki.com.cn/Article/CJFDTOTAL-YYQX2005S1016.htm [10] Zhou L, Xu X D, Ding G A, et al. The correlation factors and pollution forecast model for PM2.5 concentration in Beijing Area. Acta Meteorol Sin, 2003, 61(6): 761 doi: 10.3321/j.issn:0577-6619.2003.06.013周麗, 徐祥德, 丁國安, 等. 北京地區氣溶膠PM2.5粒子濃度的相關因子及其估算模型. 氣象學報, 2003, 61(6): 761 doi: 10.3321/j.issn:0577-6619.2003.06.013 [11] Ong B T, Sugiura K, Zettsu K. Dynamically pre-trained deep recurrent neural networks using environmental monitoring data for predicting PM2.5. Neural Comput Appl, 2016, 27(6): 1553 doi: 10.1007/s00521-015-1955-3 [12] Lary D J, Faruque F S, Malakar N, et al. Estimating the global abundance of ground level presence of particulate matter (PM2.5). Geospatial Health, 2014, 8(3): 611 doi: 10.4081/gh.2014.292 [13] Ong B T, Sugiura K, Zettsu K. Dynamic pre-training of deep recurrent neural networks for predicting environmental monitoring data //2014 IEEE International Conference on Big Data (Big Data). Washington, DC, 2014: 760 [14] Zheng Y, Zhu C Z. A prediction method of atmospheric PM2.5 based on DBNs. J Shandong Univ Eng Sci, 2014, 44(6): 19 https://www.cnki.com.cn/Article/CJFDTOTAL-SDGY201406004.htm鄭毅, 朱成璋. 基于深度信念網絡的PM2.5預測. 山東大學學報(工學版), 2014, 44(6): 19 https://www.cnki.com.cn/Article/CJFDTOTAL-SDGY201406004.htm [15] Dai L J, Zhang C J, Ma L M. Dynamic forecasting model of shortterm PM2.5 concentration based on machine learning. J Comput Appl, 2017, 37(11): 3057 https://www.cnki.com.cn/Article/CJFDTOTAL-JSJY201711004.htm戴李杰, 張長江, 馬雷鳴. 基于機器學習的PM2.5短期濃度動態預報模型. 計算機應用, 2017, 37(11): 3057 https://www.cnki.com.cn/Article/CJFDTOTAL-JSJY201711004.htm [16] Li X, Peng L, Hu Y, et al. Deep learning architecture for air quality predictions. Environ Sci Pollut Res, 2016, 23(22): 22408 doi: 10.1007/s11356-016-7812-9 [17] Rumelhart D E, McClelland J L. Parallel Distributed Processing: Explorations in the Microstructure of Cognition. Volume 1. Foundations. Cambridge: MIT Press, 1986 [18] Hubel D H, Wiesel T N. Receptive fields of single neurones in the cat's striate cortex. J Physiol, 1959, 148(3): 574 doi: 10.1113/jphysiol.1959.sp006308 [19] Pigou L, Van Den Oord A, Dieleman S, et al. Beyond temporal pooling: Recurrence and temporal convolutions for gesture recognition in video. Int J Comput Vision, 2018, 126(2-4): 430 doi: 10.1007/s11263-016-0957-7 [20] Yang J B, Nguyen M N, San P P, et al. Deep convolutional neural networks on multichannel time series for human activity recognition//Proceedings of the Twenty-Fourth International Conference on Artificial Intelligence. Buenos Aires, 2015: 3995 [21] Hochreiter S, Schmidhuber J. Long short-term memory. Neural Comput, 1997, 9(8): 1735 doi: 10.1162/neco.1997.9.8.1735 [22] Jia M W, Kang N, Zhao T L. Characteristics oftypical autumn and winter haze pollution episodes and their boundary layer in Nanjing. Environ Sci Technol, 2014, 37(120): 105 https://www.cnki.com.cn/Article/CJFDTOTAL-FJKS2014S2024.htm賈夢唯, 康娜, 趙天良. 南京秋冬季典型霾污染過程及邊界層特征分析. 環境科學與技術, 2014, 37(120): 105 https://www.cnki.com.cn/Article/CJFDTOTAL-FJKS2014S2024.htm [23] Zhang J H, Xu S R, Zhao S M. Analysis of effect of temperature inversion to atmosphere pollution. Heilongjiang Environ J, 2008, 32(2): 24 https://www.cnki.com.cn/Article/CJFDTOTAL-HLJO200802013.htm張繼紅, 徐盛榮, 趙淑敏. 逆溫天氣對大氣污染的影響分析. 黑龍江環境通報, 2008, 32(2): 24 https://www.cnki.com.cn/Article/CJFDTOTAL-HLJO200802013.htm [24] Ning H W. An Analysis on Meteorological Factors and Study on Predicting Air Pollution in Xi'an City[Dissertation]. Nanjing: Nanjing University of Information Science and Technology, 2006寧海文. 西安市大氣污染氣象條件分析及空氣質量預報方法研究[學位論文]. 南京: 南京信息工程大學, 2006 [25] Xiao T Y, Ren H Y, Zhang X W. Analysis and prediction of the winter inversion in Harbin. J Northeast Agric Univ, 2001, 32(2): 139 doi: 10.3969/j.issn.1005-9369.2001.02.007肖同玉, 任紅玉, 張興文. 哈爾濱冬季逆溫規律分析及預報. 東北農業大學學報, 2001, 32(2): 139 doi: 10.3969/j.issn.1005-9369.2001.02.007 [26] Cao H L, Chen Q. Inverse temperature characteristics of boundary layer and its relationship with air pollution in Xi'an. J Shaanxi Meteorol, 2014(2): 13 doi: 10.3969/j.issn.1006-4354.2014.02.005曹紅麗, 陳奇. 西安邊界層逆溫特征及其與空氣污染的關系. 陜西氣象, 2014(2): 13 doi: 10.3969/j.issn.1006-4354.2014.02.005 -
點擊查看大圖
圖(8) / 表(1)
計量
- 文章訪問數: 1787
- HTML全文瀏覽量: 696
- PDF下載量: 163
- 被引次數: 0
