基于機(jī)器學(xué)習(xí)的蘭州市空氣質(zhì)量預(yù)報(bào)方法研究
發(fā)布時(shí)間：2019-02-14 20:49
【摘要】：空氣污染物(特別是PM2.5)嚴(yán)重危害人體健康。本文利用2001-2011、2013-2015年蘭州市空氣污染逐日監(jiān)測(cè)資料,在分析了蘭州市2001-2011年3種主要污染物SO2、NO2、PM10,2013-2015年6種主要污染物PM10、PM2.5、NO2、SO2、CO和O3的污染特征的基礎(chǔ)上、以2014-2015年歐洲中期天氣預(yù)報(bào)中心(ECMWF)與T639預(yù)報(bào)產(chǎn)品為預(yù)報(bào)因子,并引入小波分解方法,分別建立了基于BP神經(jīng)網(wǎng)絡(luò)、最小二乘法支持向量機(jī)(LS-SVM)和Elman神經(jīng)網(wǎng)絡(luò)的蘭州市6種主要空氣污染物濃度未來2日預(yù)報(bào)模型,并對(duì)預(yù)報(bào)結(jié)果進(jìn)行檢驗(yàn),分析了各建模方法的優(yōu)劣;最后結(jié)合以上模型以支持向量回歸方法(SVR)建立了6種主要污染物集合預(yù)報(bào)模型,并進(jìn)行仿真業(yè)務(wù)化預(yù)報(bào)檢驗(yàn)。結(jié)果表明:(1)2013-2015年間PM10依然蘭州市的主要污染物,是造成春季重污染天氣的首要原因;2013-2015年SO2年平均濃度相比2001-2011年下降明顯,并且從2013年起低于同期NO2的年平均濃度;O3的年平均濃度逐年增加,在2015年作為首要污染物的天數(shù)大幅度增加,成為夏季的最重要的污染物之一。(2)以LS-SVM建立的6種污染物24h和48h預(yù)報(bào)模型的評(píng)價(jià)指標(biāo)整體好于BP神經(jīng)網(wǎng)絡(luò)和Elman神經(jīng)網(wǎng)絡(luò);以BP神經(jīng)網(wǎng)絡(luò)建立的模型的穩(wěn)定性相對(duì)較差,48h的預(yù)報(bào)精度衰減幅度最高。(3)以ECMWF建立的預(yù)報(bào)模型對(duì)未來2d的PM10、PM2.5、NO2、SO2和CO的日均質(zhì)量濃度的預(yù)報(bào)效果好于T639,而T639對(duì)預(yù)報(bào)O3有一定優(yōu)勢(shì)。(4)通過小波分解方法對(duì)污染物資料進(jìn)行預(yù)處理后,LS-SVM的24h和48h預(yù)報(bào)模型的預(yù)測(cè)精度得到有效改善。(5)集合預(yù)報(bào)模型對(duì)6種主要污染物的日均質(zhì)量濃度的24h和48h預(yù)報(bào)精度比未進(jìn)行集合處理的模型高;集合預(yù)報(bào)模型預(yù)測(cè)的AQI與實(shí)際AQI相比,24h和48h預(yù)報(bào)的平均誤差為9.874和12.315,平均相對(duì)誤差為12.4%和15.1%,均方根誤差為14.033和17.095;空氣質(zhì)量指數(shù)等級(jí)的24h預(yù)報(bào)率為76.7%,漏報(bào)率為9.1%,誤報(bào)率為14.2%;48h的預(yù)報(bào)率為71.5%,漏報(bào)率為11.0%,誤報(bào)率為17.5%;集合模型對(duì)首要污染物的24h預(yù)報(bào)率為76.3%,48h預(yù)報(bào)率為70.0%。本文研究結(jié)果對(duì)提高蘭州空氣質(zhì)量業(yè)務(wù)預(yù)報(bào)能力具有一定參考價(jià)值。
[Abstract]:Air pollutants (especially PM2.5) are seriously harmful to human health. Based on the daily monitoring data of air pollution in Lanzhou from 2001 to 2011 to 2015, the PM10,PM2.5,NO2,SO2, of six major pollutants in Lanzhou from 2001 to 2011 was analyzed in this paper. Based on the pollution characteristics of CO and O3, the (ECMWF) and T639 forecasting products of the European Center for Medium-Term Weather Forecast (ECWFC) in 2014-2015 are taken as forecasting factors, and the wavelet decomposition method is introduced to establish the BP neural network, respectively. LS-SVM and Elman neural network are used to predict the concentration of six major air pollutants in Lanzhou in the next 2 days. The results of prediction are tested and the advantages and disadvantages of each modeling method are analyzed. Finally, six major pollutant ensemble prediction models are established by using the support vector regression (SVR) method combined with the above models, and the simulated operational prediction tests are carried out. The results are as follows: (1) PM10 is still the main pollutant in Lanzhou from 2013 to 2015, which is the main cause of heavy pollution weather in spring; The annual average concentration of SO2 in 2013-2015 was significantly lower than that in 2001-2011, and was lower than the annual average concentration of NO2 in the same period from 2013 to 2013. The annual average concentration of O3 increased year by year, and the number of days as the primary pollutant increased significantly in 2015. It has become one of the most important pollutants in summer. (2) the evaluation indexes of 6 kinds of pollutants prediction models based on LS-SVM are better than those of BP neural network and Elman neural network on the whole; The stability of the model based on BP neural network is relatively poor, and the attenuation range of prediction accuracy is the highest at 48 h. (3) the prediction model based on ECMWF is better than T639 in predicting the daily average concentration of PM10,PM2.5,NO2,SO2 and CO in the next 2 days. However, T639 has some advantages in predicting O3. (4) after pretreatment of pollutant data by wavelet decomposition, The prediction accuracy of 24 h and 48 h prediction models of LS-SVM is improved effectively. (5) the accuracy of 24 h and 48 h prediction of daily average concentration of six major pollutants by the ensemble prediction model is higher than that of the model without collective treatment. Compared with the actual AQI, the AQI predicted by the ensemble prediction model has an average error of 9.874 and 12.315 at 24 h and 48 h, an average relative error of 12.4% and 15.1%, and a root mean square error of 14.033 and 17.095. The 24-hour forecast rate of air quality index grade was 76.7, the false alarm rate was 9.1, the false alarm rate was 14.2and 48h prediction rate was 71.5, the false alarm rate was 11.0 and the false alarm rate was 17.5; The 24 hour forecast rate of the main pollutants by the ensemble model is 76. 3% and 48 h forecast rate is 70. 0%. The results of this paper have certain reference value for improving the operational forecast ability of Lanzhou air quality.
【學(xué)位授予單位】：蘭州大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：X51
本文編號(hào)：2422594
[Abstract]:Air pollutants (especially PM2.5) are seriously harmful to human health. Based on the daily monitoring data of air pollution in Lanzhou from 2001 to 2011 to 2015, the PM10,PM2.5,NO2,SO2, of six major pollutants in Lanzhou from 2001 to 2011 was analyzed in this paper. Based on the pollution characteristics of CO and O3, the (ECMWF) and T639 forecasting products of the European Center for Medium-Term Weather Forecast (ECWFC) in 2014-2015 are taken as forecasting factors, and the wavelet decomposition method is introduced to establish the BP neural network, respectively. LS-SVM and Elman neural network are used to predict the concentration of six major air pollutants in Lanzhou in the next 2 days. The results of prediction are tested and the advantages and disadvantages of each modeling method are analyzed. Finally, six major pollutant ensemble prediction models are established by using the support vector regression (SVR) method combined with the above models, and the simulated operational prediction tests are carried out. The results are as follows: (1) PM10 is still the main pollutant in Lanzhou from 2013 to 2015, which is the main cause of heavy pollution weather in spring; The annual average concentration of SO2 in 2013-2015 was significantly lower than that in 2001-2011, and was lower than the annual average concentration of NO2 in the same period from 2013 to 2013. The annual average concentration of O3 increased year by year, and the number of days as the primary pollutant increased significantly in 2015. It has become one of the most important pollutants in summer. (2) the evaluation indexes of 6 kinds of pollutants prediction models based on LS-SVM are better than those of BP neural network and Elman neural network on the whole; The stability of the model based on BP neural network is relatively poor, and the attenuation range of prediction accuracy is the highest at 48 h. (3) the prediction model based on ECMWF is better than T639 in predicting the daily average concentration of PM10,PM2.5,NO2,SO2 and CO in the next 2 days. However, T639 has some advantages in predicting O3. (4) after pretreatment of pollutant data by wavelet decomposition, The prediction accuracy of 24 h and 48 h prediction models of LS-SVM is improved effectively. (5) the accuracy of 24 h and 48 h prediction of daily average concentration of six major pollutants by the ensemble prediction model is higher than that of the model without collective treatment. Compared with the actual AQI, the AQI predicted by the ensemble prediction model has an average error of 9.874 and 12.315 at 24 h and 48 h, an average relative error of 12.4% and 15.1%, and a root mean square error of 14.033 and 17.095. The 24-hour forecast rate of air quality index grade was 76.7, the false alarm rate was 9.1, the false alarm rate was 14.2and 48h prediction rate was 71.5, the false alarm rate was 11.0 and the false alarm rate was 17.5; The 24 hour forecast rate of the main pollutants by the ensemble model is 76. 3% and 48 h forecast rate is 70. 0%. The results of this paper have certain reference value for improving the operational forecast ability of Lanzhou air quality.
【學(xué)位授予單位】：蘭州大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：X51
【參考文獻(xiàn)】
相關(guān)期刊論文 前10條
1 何建軍;余曄;劉娜;趙素平;陳晉北;;基于WRF模式的蘭州秋冬季大氣污染預(yù)報(bào)模型研究[J];氣象;2013年10期
2 ;環(huán)境空氣質(zhì)量指數(shù)(AQI)技術(shù)規(guī)定(試行)[J];中國(guó)環(huán)境管理干部學(xué)院學(xué)報(bào);2012年01期
3 王自發(fā);龐成明;朱江;安俊嶺;韓志偉;廖宏;;大氣環(huán)境數(shù)值模擬研究新進(jìn)展[J];大氣科學(xué);2008年04期
4 佟彥超;;中國(guó)重點(diǎn)城市空氣污染預(yù)報(bào)及其進(jìn)展[J];中國(guó)環(huán)境監(jiān)測(cè);2006年02期
5 吳小紅,康海燕,任德官;基于神經(jīng)網(wǎng)絡(luò)中小城市空氣污染指數(shù)預(yù)估器的設(shè)計(jì)[J];數(shù)學(xué)的實(shí)踐與認(rèn)識(shí);2005年02期
6 楊民,丁瑞強(qiáng),王式功,尚可政;蘭州市大氣氣溶膠的特征及其對(duì)呼吸道疾病的影響[J];干旱氣象;2005年01期
7 郎君,蘇小紅,周秀杰;基于有機(jī)灰色神經(jīng)網(wǎng)絡(luò)模型的空氣污染指數(shù)預(yù)測(cè)[J];哈爾濱工業(yè)大學(xué)學(xué)報(bào);2004年12期
8 楊民,王式功,李文莉,劉治國(guó),尚景文;沙塵暴天氣對(duì)蘭州市環(huán)境影響的個(gè)例分析[J];氣象;2004年04期
9 金龍,況雪源,黃海洪,覃志年,王業(yè)宏;人工神經(jīng)網(wǎng)絡(luò)預(yù)報(bào)模型的過擬合研究[J];氣象學(xué)報(bào);2004年01期
10 劉宇,胡非,王式功,鄒捍,楊德保,尚可政;蘭州市城區(qū)穩(wěn)定邊界層變化規(guī)律的初步研究[J];中國(guó)科學(xué)院研究生院學(xué)報(bào);2003年04期
相關(guān)會(huì)議論文 前1條
1 姜金華;胡非;陳玉春;彭新東;;蘭州市冬季二氧化硫濃度的數(shù)值模擬[A];慶祝中國(guó)力學(xué)學(xué)會(huì)成立50周年暨中國(guó)力學(xué)學(xué)會(huì)學(xué)術(shù)大會(huì)’2007論文摘要集（下）[C];2007年
，本文編號(hào)：2422594
本文鏈接：http://sikaile.net/shengtaihuanjingbaohulunwen/2422594.html
最近更新
教材專著
