基于SVR-LUR模型的城市道路PM10空间浓度分布模拟

陈雯君; 何红弟

doi:doi:10.3969/j.issn.1673-6141.2019.06.004

大气与环境光学学报, 2019, 14 (6): 431, 网络出版: 2019-12-05

基于SVR-LUR模型的城市道路PM10空间浓度分布模拟

Simulation of Spatial Concentration Distribution of Urban Road PM10 Based on SVR-LUR Model

论文大纲

陈雯君 ^*何红弟

作者单位

上海海事大学物流研究中心,上海 201306

土地利用回归模型 SVR-LUR模型空间分布模拟 PM10 PM10 land use regression model SVR-LUR model spatial distribution simulation

摘要

针对传统土地利用回归模型(Land use regression, LUR)未考虑影响因子与大气污染物之间非线性复杂关系和易出现多重共线性的问题。以PM10为例,采用支持向量回归机(Support vector machine regression, SVR) 改进土地利用回归模型的建模方法构建SVR-LUR模型,对上海市南浦大桥周边区域PM10空间分布进行模拟。研究结果表明: 1)研究区域PM10浓度与100 m缓冲区内的空地面积, 150 m缓冲区内的建筑工地面积、空地面积、河流面积, 200 m缓冲区内的绿地面积和河流面积,以及湿度、交通流量和背景浓度相关性较高。 2) SVR-LUR模型可较好地对研究区PM10浓度进行空间分布预测。SVR-LUR模型与LUR模型相比, SVR-LUR模型预测精度较高,其测试集比LUR模型测试集的平均绝对误差(Mean absolute error, MAE)及均方根误差(Root mean squares error, RMSE)分别减小了22.92%、33.51%,拟合指数(Index of agreement, IA)值增加了13.20%。相较于普通克里金插值模型所得到的单一梯度空间分布预测结果, SVR-LUR 模型能够更有效揭示小范围内的空间差异。 3)研究区PM10浓度空间分布呈现出西高东低的总格局,在建筑物和路网密集的地方浓度较高,而在靠近江面和空地的区域浓度相对较低。模拟结果与实际情况相符。

Abstract

The traditional land use regression(LUR) model does not consider the nonlinear complex relationship between impact factors and atmospheric pollutants. Taking PM10 as an example, Support Vector Machine Regression (SVR) has been used to improve the land use regression model modeling method to construct SVR-LUR model, and then the spatial distribution of PM10 around Nanpu Bridge in Shanghai, China is simulatedbased on the model. The results show that: 1) There is a high correlation between the PM10 concentration and the empty area in the 100 m buffer zone, the construction area, the empty area and the river area in the 150 m buffer zone, the green area and the river area in the 200 m buffer zone, as well as the humidity, traffic flow and background concentration. 2) the SVR-LUR model can better predict the spatial distribution of PM10 concentration in the study area. Compared with LUR model, SVR-LUR model has higher prediction accuracy. Compared with LUR model, the mean absolute error (MAE) and root mean squares error (RMSE) oftest set of SVR-LUR model reduces by are22.92%, 33.51% less than those of LUR model, MAE and RMSE respectively, and whilethe index of agreement (IA) value increases by 13.20%. Compared with the prediction results of single gradient spatial distribution obtained by ordinary Kriging interpolation model, SVR-LUR model can more effectively reveal the spatial differences in a small range. 3) The spatial distribution of PM10 concentration in the study area shows a general pattern of high concentration in the west and low in the east. The concentration is higher in the areas with dense buildings and road network, but relatively lower in the areas near the river and open space. The simulation results are consistent with the actual situation.

参考文献

[1] 韦晶,孙林,刘双双,等.大气颗粒物污染对土地覆盖变化的响应[J].生态学报, 2015, 35(16): 5495-5506.

Wei Jing, Sun Lin, Liu Shuangshuang, et al. Response of particulate matter pollution to land cover change[J]. Acta Ecologica Sinica, 2015, 35(16): 5495-5506(in Chinese).

[2] 周侃.中国环境污染的时空差异与集聚特征[J].地理科学, 2016, 36(07): 989-997.

Zhou Kan. Spatial and temporal differences and concentration characteristics of environmental pollution in China[J]. Geographic Science, 2016, 36(07): 989-997(in Chinese).

[3] 李名升,张建辉,张殷俊,等.近10年中国大气PM10污染时空格局演变[J].地理学报, 2013, 68(11): 1504-1512.

LiMingsheng, Zhang Jianhui, Zhang Yinjun, et al. Evolution of temporal and spatial patterns of PM10 pollution in China in recent 10 years[J]. Acta Geographica, 2013, 68(11): 1504-1512(in Chinese).

[4] 汉瑞英,陈健,王彬.利用LUR模型模拟杭州市PM2.5质量浓度空间分布[J].环境科学学报, 2016, 36(09): 3379-3385.

Han Ruiying, Chen Jian, Wang Bin. Using LUR model to simulate the spatial distribution of PM2.5 concentration in Hangzhou[J]. Journal of Environmental Sciences, 2016, 36(09): 3379-3385(in Chinese).

[5] 王郭臣,王珏,信玉洁,等.天津PM10和NO2输送路径及潜在源区研究[J].中国环境科学, 2014, 34(12): 3009-3016.

Wang Guochen, Wang Jue, XinYujie, et al. Study on PM10 and NO2 transport routes and potential sources in Tianjin[J]. China Environmental Science, 2014, 34(12): 3009-3016(in Chinese).

[6] 段杰雄, 翟卫欣, 程承旗, 等. 中国PM2.5 污染空间分布的社会经济影响因素分析[J]. 环境科学, 2018, 39(5): 2498-2504.

DuanJiexiong, Zhai Weixin, Cheng Chengqi, et al.Analysis of Socio-economic Influencing Factors on Spatial Distribution of PM2.5 Pollution in China[J]. Environmental Science, 2018, 39(5): 2498-2504(in Chinese).

[7] [t]16cm6张生玲, 王雨涵,李跃, 等. 中国雾霾空间分布特征及影响因素分析[J]. 中国人口资源与环境, 2017, 27(9): 15-22.

ZhangShengling, Wang Yuhan, Li Yue, et al. Spatial distribution characteristics and influencing factors of fog and haze in China[J]. Population, resources and environment in China, 2017, 27(9): 15-22(in Chinese).

[8] 符立伟,郭秀锐.国内空气污染暴露水平评价方法研究进展[J].环境科学与技术, 2015, 38(S2): 226-230.

Fu Liwei, Guo Xiurui. Advances in assessment methods of air pollution exposure level in China[J]. Environmental Science and Technology, 2015, 38(S2): 226-230(in Chinese).

[9] Ross Z,Jerrett M, Ito K, et al．A land use regression for predicting fine particulate matter concentrations in the New York City region[J]. Atmos Environ, 2007, 41(11): 2255-2269.

[10] Ha H, Olson R,Bian L, et al. Analysis of heavy metal sources in soil using kriging interpolation on principal components[J]. Environmental Science & Technology, 2014, 48(9): 4999-5007.

[11] Henderson S B, Beckerman B,Jerrett M, et al. Applicationof land use regression to estimate long-term concentrations of traffic-related nitrogen oxides and fine particulate matter[J]. Environmental Science and Technology, 2007, 41(7): 2422-2428.

[12] Briggs D, Collins S, Elliot P, et al. Mapping urban air pollution using GIS: a regression based approach[J]. Geogr. Inf. Sci, 1997, 11: 699-718.

[13] Tan H B, Liu L, Fan S J,et al. Aerosol optical properties and mixing state of black carbon in the Pearl River Delta, China[J]. Atmospheric Environment. 2016, 131: 196-208.

[14] Chen L, Du S Y, Bai Z P,et al. Application of land use regression for estimating concentrations of major outdoor air pollutants in Jinan, China[J]. Journal of Zhejiang University-SCIENCE A (Applied Physics & Engineering), 2010, 11: 857-867.

[15] 吴健生,谢舞丹,李嘉诚.土地利用回归模型在大气污染时空分异研究中的应用[J].环境科学, 2016, 37(02): 413-419.

Wu Jiansheng, Xie Wudan, Li Jiacheng. Application of land use regression model in the study of temporal and spatial differentiation of atmospheric pollution[J]. Environmental Science, 2016, 37(02): 413-419(in Chinese).

[16] Liu J K, Zhu L J, Wang H H, et al. Dry deposition of particulate matter at an urban forest, wetland and ake surface in Beijing[J]. Atmospheric Environment, 2016(125): 78-187.

[17] Health Effects Institute. Traffic-Related Air Pollution: A Critical Review of the Literature on Emissions, exposure, and Health Effects[R]. Special Report 17, 2010.

[18] Hoek, G.Beelen, R., Hoogh K.A review of land-use regression models to assess spatial variation of outdoor air pollution[J]. Atmospheric Environment. 2008, 42: 7561-7578.

[19] Vapnik V N. The Nature of Statistical Learning Theory[M]. Springer, 1995. 8 (6): 988-999.

[20] 张在旭,宋杰鲲,张宇.一种基于支持向量机的企业财务危机预警新模型[J].中国石油大学学报(自然科学版), 2006(04): 132-136.

Zhang Zaixu, Song Jiekun, Zhang Yu. A new financial crisis early warning model based on support vector machine[J]. Journal of China Petroleum University (Natural Science Edition), 2006 (04): 132-136(in Chinese).

[21] 兰浩,张国忠,刘刚,等.应用支持向量回归预测胶凝原油启动屈服应力[J].中国石油大学学报(自然科学版), 2008(03):119-121, 127.

Lanhao, Zhang Guozhong, Liu Gang, et al. Prediction of startup yield stress of gelled crude oil by support vector regression[J]. Journal of China Petroleum University (Natural Science Edition), 2008 (03): 119-121, 127(in Chinese).

[22] 王霞,王占岐,金贵,等.基于核函数支持向量回归机的耕地面积预测[J].农业工程学报, 2014, 30(04): 204-211.

Wang Xia, Wang Zhanqi, JinGui, et al. Prediction of cultivated land area based on kernel function support vector regression[J]. Journal of Agricultural Engineering, 2014, 30(04): 204-211(in Chinese).

[23] 阳海鸥,陈文波,梁照凤.LUR模型模拟的南昌市PM2.5浓度与土地利用类型的关系[J].农业工程学报, 2017, 33(06): 232-239.

Yang Haiou, Chen Wenbo, Liang Zhaofeng. The relationship between PM2.5 concentration and land use types simulated by LUR model in Nanchang[J]. Journal of Agricultural Engineering, 2017, 33(06): 232-239(in Chinese).

陈雯君, 何红弟. 基于SVR-LUR模型的城市道路PM10空间浓度分布模拟[J]. 大气与环境光学学报, 2019, 14(6): 431. CHEN Wenjun, HE Hongdi. Simulation of Spatial Concentration Distribution of Urban Road PM10 Based on SVR-LUR Model[J]. Journal of Atmospheric and Environmental Optics, 2019, 14(6): 431.

基于SVR-LUR模型的城市道路PM10空间浓度分布模拟

关于本站 Cookie 的使用提示

全站搜索

基于SVR-LUR模型的城市道路PM10空间浓度分布模拟

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索