中国东部典型城市群AOD 时空演变及预测

大气与环境光学学报 ›› 2021, Vol. 16 ›› Issue (4): 320-330.

中国东部典型城市群AOD 时空演变及预测

唐燕∗, 许睿, 孟繁玥

天津理工大学管理学院, 天津 300384

收稿日期:2020-06-24 修回日期:2021-02-12 出版日期:2021-07-28 发布日期:2021-07-28
通讯作者: E-mail: sugaryan@yeah.net E-mail:sugaryan@yeah.net
作者简介:唐燕 (1984 - ), 女, 天津人, 博士, 副教授, 硕士生导师, 主要从事生态经济与环境保护方面的研究。 E-mail: sugaryan@yeah.net
基金资助:
Supported by Soft Science Research Project of Tianjin Science and Technology Development Strategic Research Plan (天津市科技发展战略研究计划软科学研究项目, 19ZLZXZF00390), Research Project Planning Fund for Humanities and Social Sciences of the Ministry of Education (教育部人文社会科学研究项目规划基金项目, 20A10060005)

Spatiotemporal Evolution and Prediction of AOD in Typical Urban Agglomerations in Eastern China

TANG Yan∗, XU Rui , MENG Fanyue

School of Management, Tianjin University of Technology, Tianjin 300384, China

Received:2020-06-24 Revised:2021-02-12 Published:2021-07-28 Online:2021-07-28

摘要/Abstract

摘要： 为精准预测我国东部典型城市群的气溶胶光学厚度 (AOD), 基于 2010–2019 年 MODIS 数据, 分析了京津冀、长三角、珠三角区域之间以及区域内部的 AOD 时空差异特征, 构建了小波变换与 BP 神经网络相结合的 AOD 预测模型, 并对典型城市群 AOD 进行了预测。研究结果表明: 1) 各城市群气溶胶浓度峰值均出现在夏季, 京津冀地区 AOD 均值最高, 长三角次之, 珠三角最小; 2) AOD 影响因素分析表明, 生产总值指数、人口密度、温度因素与 AOD 正相关, 植被覆盖指数 (NDVI)、降水量、风速与 AOD 负相关; 3) 各地区 AOD 预测结果其平均绝对误差 (MAE) 均低于 0.12, 误差小于 BP 神经网络预测结果, R2 均大于 0.75, 说明该模型相比 BP 神经网络, 能够有效提高 AOD 预测能力。

关键词: 典型城市群, 气溶胶光学厚度, 时空演变分析, 气溶胶光学厚度预测

Abstract: To accurately predict the aerosol optical depth (AOD) of typical urban agglomerations in eastern China, based on MODIS data from 2010 to 2019, the spatial and temporal differences of AOD between Beijing-TianjinHebei region, Yangtze River Delta and Pearl River Delta and within them were analyzed. The AOD prediction model based on the combination of wavelet transform and BP neural network was built to predict AOD in typical urban agglomerations. The results show that: 1) the peak value of aerosol concentration in all urban agglomerations occurs in summer, and the average AOD of Beijing-Tianjin-Hebei region is the highest, followed by Yangtze River Delta and Pearl River Delta. 2) the analysis of AOD influencing factors shows that GDP index, population density and temperature are positively correlated with AOD, while normalized difference vegetation index (NDVI), precipitation and wind speed are negatively correlated with AOD. 3) the mean absolute error (MAE) of AOD prediction results in each region is lower than 0.12, error is less than BP neural network and R2 is greater than 0.75, indicating that the model can effectively improve AOD prediction ability compared with BP neural network.

Key words: typical urban agglomeration, aerosol optical depth, analysis on spatial and temporal evolution; aerosol optical depth prediction

中图分类号:

X513

唐燕∗, 许睿, 孟繁玥. 中国东部典型城市群AOD 时空演变及预测[J]. 大气与环境光学学报, 2021, 16(4): 320-330.

TANG Yan∗, XU Rui , MENG Fanyue. Spatiotemporal Evolution and Prediction of AOD in Typical Urban Agglomerations in Eastern China[J]. Journal of Atmospheric and Environmental Optics, 2021, 16(4): 320-330.

参考文献 19

[1]	Shi Guangyu, Wang Biao, Zhang Hua, et al. The radiative and climatic effects of atmospheric aerosols [J]. Chinese Journal of
	Atmospheric Sciences, 2008, 32(4): 826-840.
	石广玉, 王标, 张华, 等. 大气气溶胶的辐射与气候效应 [J]. 大气科学, 2008, 32(4): 826-840.
[2]	Wang Yinpai, Yu Xin, Xie Guangqi. Spatial distribution and temporal variation of aerosol optical depth over China in the past
15	years [J]. China Environmental Science, 2018, 38(2): 426-434.
	王银牌, 喻鑫, 谢广奇. 中国近 15 年气溶胶光学厚度时空分布特征 [J]. 中国环境科学, 2018, 38(2): 426-434.
[3]	Liu Zhuang, Shi Chenlie, Zhang Meng, et al. Temporal characteristics of aerosol optical depth based on cluster analysis method
[J]	Journal of Atmospheric and Environmental Optics, 2019, 14(6): 411-418.
	刘状, 石晨烈, 张萌, 等. 基于聚类分析的气溶胶光学厚度时间变化特征研究 [J]. 大气与环境光学学报, 2019, 14(6):
41	1-418.
[4]	Gao Ling, Li Jun, Chen Lin, et al. Retrieval atmospheric aerosol optical depth over China from AVHRR by multiple regression
	method [J]. Journal of Atmospheric and Environmental Optics, 2015, 10(4): 286-294.
	高玲, 李俊, 陈林, 等. 利用多元回归方法反演中国陆地地区 AVHRR 气溶胶光学厚度 [J]. 大气与环境光学学报, 2015,
10	(4): 286-294.
[5]	Albayrak A, Wei J, Petrenko M , et al. Global bias adjustment for MODIS aerosol optical thickness using neural network [J].
	Journal of Applied Remote Sensing, 2013, 7(1): 073514.
[6]	Nabavi S O, Haimberger L, Abbasi R, et al. Prediction of aerosol optical depth in West Asia using deterministic models and
	machine learning algorithms [J]. Aeolian Research, 2018, 35(12): 69-84.
[7]	Das D, Radosavljevic V, Vucetic S, et al. Reducing need for collocated ground and satellite based observations in statistical
	aerosol optical depth estimation [C]. IEEE International Geoscience and Remote Sensing Symposium, Boston: IEEE, 2008.
[8]	Falamarzi Y, Palizdan N, Huang Y, et al. Estimating evapotranspiration from temperature and wind speed data using artificial
	and wavelet neural networks (WNNs) [J]. Agricultural Water Management, 2014, 140(7): 26-36.
[9]	Samadianfard S, Asadi E, Jarhan S, et al. Wavelet neural networks and gene expression programming models to predict
	short-term soil temperature at different depths [J]. Soil and Tillage Research, 2018, 175(1): 37-50.
[10]	Nourani V, Kisi O, Komasi M. Two hybrid artificial intelligence approaches for modeling rainfal-runo ¨ ff process [J]. Journal of
	Hydrology, 2011, 402(1): 41-59.
[11]	Zhang Chenhe, Zhao Tianliang, Wang Fu, et al. Variationsin aerosol optical depth over three northeastern provinces of China
	in 2003–2014 [J]. Environmental Science, 2017, 38(2): 476-484.
	张宸赫, 赵天良, 王富, 等. 2003–2014 年东北三省气溶胶光学厚度变化分析 [J]. 环境科学, 2017, 38(2): 476-484.
[12]	Zhu Yuhong, Zhang Zili, Tian Ping, et al. Satellite-based long-term trends analysis in aerosol optical properties over the plain
	areas of north Zhejiang Province [J]. Acta Scientiae Circumstantiae, 2015, 35(2): 352-362.
	朱于红, 张自力, 田平, 等. 基于卫星遥感的浙北平原气溶胶光学特性长期变化分析 [J]. 环境科学学报, 2015, 35(2):
35	2-362.
[13]	Dong Zipeng, Yu Xing, Li Xingmin, et al. Analysis of aerosol optical thickness variation and its causes in Shaanxi Province
	based on MODIS data [J]. Chinese Science Bulletin, 2014, 59(3): 306-316.
	董自鹏, 余兴, 李星敏, 等. 基于 MODIS 数据的陕西省气溶胶光学厚度变化趋势与成因分析 [J]. 科学通报, 2014, 59(3):
30	6-316.
[14]	Zhang Q, Benveniste A. Wavelet networks [J]. IEEE Transactions on Neural Networks, 1992, 3(6): 889-898.
[15]	Kang N, Raghavendra K, Hu K, et al. Long-term (2002–2014) evolution and trend in Collection 5.1 Level-2 aerosol products
	derived from the MODIS and MISR sensors over the Chinese Yangtze River Delta [J]. Atmospheric Research, 2016, 181(11):
29	-43.
[16]	Sun Qiang, Fan Xuehua, Xia Xiang′ao. Observation and analysis of aerosol vertical distribution characteristics in North China
	Plain [J]. Meteorological and Environmental Sciences, 2016, 39(1): 26-33.
	孙强, 范学花, 夏祥鳌. 华北地区气溶胶垂直分布特征的观测与分析 [J]. 气象与环境科学, 2016, 39(1): 26-33.
[17]	He Q S, Li C C, Geng F H, et al. Study on long-term aerosol distribution over the land of east China using MODIS data [J].
	Aerosol and Air Quality Research, 2012, 12(3): 304-319.
[18]	Xiao H W, Xiao H Y, Luo L, et al. Stable carbon and nitrogen isotope compositions of bulk aerosol samples over the South
	China Sea [J]. Atmospheric Environment, 2018, 193(11): 1-10.
[19]	Guangdong Provincial Bureau of Statistics. Guangdong statistical yearbook [OL].[2019-09-29]. http://stats.gd.gov.cn/.
	广东省统计局. 广东统计年鉴 [OL]. [2019-09-29]. http://stats.gd.gov.cn/.