基于MAIAC AOD时空补值数据的PM2.5浓度估算研究
Research on PM2.5 Concentration Estimation Based on MAIAC AOD Spatiotemporal Supplement Data
摘要: 气溶胶光学厚度被广泛应用于PM2.5浓度估算中，受极端气候影响以及卫星传感器影响，AOD数据存在大量缺失，本文提出Prophet-LSTM + P-Bshade时空补值模型对MAIAC AOD数据进行补值并使用Catbooost模型结合AOD数据以及ERA5气象数据对中国2020年陆地区域的PM2.5浓度进行估算。结果表明：① Prophet-LSTM + P-Bshade时空补值模型精度明显优于传统补值方法，R、MASE和MAE分别为0.891、0.275和0.183。② Catboost模型在PM2.5浓度估算中比常用的其他机器学习等模型显示更高的估算精度，R、MASE和MAE分别为0.93、15.89 μg∙m−3和10.54 μg∙m−3。③ 中国陆地区域2020年的PM2.5浓度在季节尺度分布上明显，整体呈现冬季 > 春季 > 秋季 > 夏季的季节分布特点。在空间分布上，PM2.5浓度整体呈现东部地区较高，塔里木盆地区域局部较高的特点。
Abstract: Aerosol optical thickness is widely used in PM2.5 concentration estimation, due to the influence of extreme climate and satellite sensors, there are a large number of missing AOD data, this paper proposes the Prophet-LSTM + P-Bshade spatiotemporal compensation model to supplement the MAIAC AOD data, and uses the Catbooost model combined with AOD data and ERA5 meteorological data to estimate the PM2.5 concentration in the land area of China in 2020. The results show that: (1) The accuracy of the Prophet-LSTM + P-Bshade spatiotemporal compensation model is significantly better than that of the traditional compensation method, with R, MASE and MAE of 0.891, 0.275 and 0.183, respectively. (2) The Catboost model showed higher estimation accuracy than other commonly used machine learning models in PM2.5 concentration estimation, with R, MASE and MAE of 0.93, 15.89 μg∙m−3 and 10.54 μg∙m−3, respectively. (3) PM2.5 concentrations in China’s land areas in 2020 were significantly distributed on a seasonal scale, showing the seasonal distribution characteristics of winter > spring > autumn > summer. In terms of spatial distribution, PM2.5 concentrations were higher in the eastern region and higher in the Tarim Basin.
文章引用：熊英杰, 杜宁, 王莉, 王耀. 基于MAIAC AOD时空补值数据的PM2.5浓度估算研究[J]. 理论数学, 2024, 14(6): 447-459. https://doi.org/10.12677/pm.2024.146263

参考文献

[1] 徐栋夫, 曹萍萍, 王源程. 成都一次重污染过程的气溶胶光学特性垂直分布[J]. 气象, 2020, 46(7): 948-958.
[2] 任秀龙, 胡伟, 吴春苗, 等. 华北南部重污染城市周边区域二次气溶胶的化学特征及来源解析[J]. 环境科学, 2022, 43(3): 1159-1169.
[3] 王跃思, 张军科, 王莉莉, 等. 京津冀区域大气霾污染研究意义、现状及展望[J]. 地球科学进展, 2014, 29(3): 388-396.
[4] Ramanathan, V., Crutzen, P.J., Kiehl, J.T. and Rosenfeld, D. (2001) Aerosols, Climate, and the Hydrological Cycle. Science, 294, 2119-2124. [Google Scholar] [CrossRef] [PubMed]
[5] Peng, J., Han, H., Yi, Y., Huang, H. and Xie, L. (2022) Machine Learning and Deep Learning Modeling and Simulation for Predicting PM2.5 Concentrations. Chemosphere, 308, Article ID: 136353. [Google Scholar] [CrossRef] [PubMed]
[6] van Donkelaar, A., Martin, R.V., Levy, R.C., da Silva, A.M., Krzyzanowski, M., Chubarova, N.E., et al. (2011) Satellite-Based Estimates of Ground-Level Fine Particulate Matter during Extreme Events: A Case Study of the Moscow Fires in 2010. Atmospheric Environment, 45, 6225-6232. [Google Scholar] [CrossRef] 
[7] Lin, J., Nielsen, C.P., Zhao, Y., Lei, Y., Liu, Y. and McElroy, M.B. (2010) Recent Changes in Particulate Air Pollution over China Observed from Space and the Ground: Effectiveness of Emission Control. Environmental Science & Technology, 44, 7771-7776. [Google Scholar] [CrossRef] [PubMed]
[8] Engel-Cox, J.A., Holloman, C.H., Coutant, B.W. and Hoff, R.M. (2004) Qualitative and Quantitative Evaluation of MODIS Satellite Sensor Data for Regional and Urban Scale Air Quality. Atmospheric Environment, 38, 2495-2509. [Google Scholar] [CrossRef] 
[9] van Donkelaar, A., Martin, R.V., Brauer, M., Hsu, N.C., Kahn, R.A., Levy, R.C., et al. (2016) Global Estimates of Fine Particulate Matter Using a Combined Geophysical-Statistical Method with Information from Satellites, Models, and Monitors. Environmental Science & Technology, 50, 3762-3772. [Google Scholar] [CrossRef] [PubMed]
[10] 吴迪, 杜宁, 王莉, 等. 基于GTWR-XGBoost模型的四川省PM_(2.5)小时浓度估算[J]. 环境科学, 2023, 44(7): 3738-3748.
[11] 吴宇宏, 杜宁, 王莉等. 基于iLME+Geoi-RF模型的四川省PM_(2.5)浓度估算[J]. 环境科学, 2021, 42(12): 5602-5615.
[12] 吴迪. 基于GTWR-XGBoost模型的PM_(2.5)浓度估算及与城市化关系研究[D]: [硕士学位论文]. 贵阳: 贵州大学, 2023.
[13] Chatterjee, A., Michalak, A.M., Kahn, R.A., Paradise, S.R., Braverman, A.J. and Miller, C.E. (2010) A Geostatistical Data Fusion Technique for Merging Remote Sensing and Ground‐Based Observations of Aerosol Optical Thickness. Journal of Geophysical Research: Atmospheres, 115, D20207. [Google Scholar] [CrossRef] 
[14] 许悦蕾, 刘延安, 施润和, 等. 气象要素对气溶胶光学厚度估算PM_(2.5)的影响[J]. 环境科学学报, 2018, 38(10): 3868-3876.
[15] Kim, S., Koo, J., Lee, H., Mok, J., Choi, M., Go, S., et al. (2021) Comparison of PM2.5 in Seoul, Korea Estimated from the Various Ground-Based and Satellite AOD. Applied Sciences, 11, Article No. 10755. [Google Scholar] [CrossRef] 
[16] Ma, Z., Hu, X., Sayer, A.M., Levy, R., Zhang, Q., Xue, Y., et al. (2016) Satellite-Based Spatiotemporal Trends in PM2.5 Concentrations: China, 2004-2013. Environmental Health Perspectives, 124, 184-192. [Google Scholar] [CrossRef] [PubMed]
[17] Liu, Y., Paciorek, C.J. and Koutrakis, P. (2009) Estimating Regional Spatial and Temporal Variability of PM2.5 Concentrations Using Satellite Data, Meteorology, and Land Use Information. Environmental Health Perspectives, 117, 886-892. [Google Scholar] [CrossRef] [PubMed]
[18] He, Q. and Huang, B. (2018) Satellite-Based Mapping of Daily High-Resolution Ground PM2.5 in China via Space-Time Regression Modeling. Remote Sensing of Environment, 206, 72-83. [Google Scholar] [CrossRef] 
[19] Liu, N., Zou, B., Li, S., Zhang, H. and Qin, K. (2021) Prediction of PM2.5 Concentrations at Unsampled Points Using Multiscale Geographically and Temporally Weighted Regression. Environmental Pollution, 284, Article ID: 117116. [Google Scholar] [CrossRef] [PubMed]
[20] Liu, Z., Xiao, Q. and Li, R. (2023) Full Coverage Hourly PM2.5 Concentrations’ Estimation Using Himawari-8 and MERRA-2 AODs in China. International Journal of Environmental Research and Public Health, 20, Article No. 1490. [Google Scholar] [CrossRef] [PubMed]
[21] Li, L., Zhang, J., Meng, X., Fang, Y., Ge, Y., Wang, J., et al. (2018) Estimation of PM2.5 Concentrations at a High Spatiotemporal Resolution Using Constrained Mixed-Effect Bagging Models with MAIAC Aerosol Optical Depth. Remote Sensing of Environment, 217, 573-586. [Google Scholar] [CrossRef] 
[22] 金囝囡, 杨兴川, 晏星, 等. 京津冀及周边MAIAC AOD和PM_(2.5)质量浓度特征及相关性分析[J]. 环境科学, 2021, 42(6): 2604-2615.
[23] Lyapustin, A., Wang, Y., Korkin, S. and Huang, D. (2018) MODIS Collection 6 MAIAC Algorithm. Atmospheric Measurement Techniques, 11, 5741-5765. [Google Scholar] [CrossRef] 
[24] Lyapustin, A. and Wang, Y. (2022) MODIS/Terra+Aqua Land Aerosol Optical Depth Daily L2G Global 1 km SIN Grid V061. MODIS/Terra+Aqua Land Aerosol Optical Depth Daily L2G Global 1 km SIN Grid LAADS DAAC (nasa.gov).
[25] Ichoku, C., Chu, D.A., Mattoo, S., Kaufman, Y.J., Remer, L.A., Tanré, D., et al. (2002) A Spatio‐Temporal Approach for Global Validation and Analysis of MODIS Aerosol Products. Geophysical Research Letters, 29, MOD1. [Google Scholar] [CrossRef] 
[26] Kahn, R.A., Gaitley, B.J., Martonchik, J.V., Diner, D.J., Crean, K.A. and Holben, B. (2005) Multiangle Imaging Spectroradiometer (MISR) Global Aerosol Optical Depth Validation Based on 2 Years of Coincident Aerosol Robotic Network (AERONET) Observations. Journal of Geophysical Research: Atmospheres, 110, D10S04. [Google Scholar] [CrossRef] 
[27] Liu, J., Weng, F. and Li, Z. (2019) Satellite-Based PM2.5 Estimation Directly from Reflectance at the Top of the Atmosphere Using a Machine Learning Algorithm. Atmospheric Environment, 208, 113-122. [Google Scholar] [CrossRef] 
[28] 岳书平, 闫业超, 张树文, 等. 基于ERA5-LAND的中国东北地区近地表土壤冻融状态时空变化特征[J]. 地理学报, 2021, 76(11): 2765-2779.
[29] Taylor, S.J. and Letham, B. (2018) Forecasting at Scale. The American Statistician, 72, 37-45. [Google Scholar] [CrossRef] 
[30] Wang, Z., Zhou, Y., Zhao, R., Wang, N., Biswas, A. and Shi, Z. (2021) High-Resolution Prediction of the Spatial Distribution of PM2.5 Concentrations in China Using a Long Short-Term Memory Model. Journal of Cleaner Production, 297, Article ID: 126493. [Google Scholar] [CrossRef] 
[31] Liang, L., Daniels, J., Biancardi, M. and Zhou, Y. (2023) Reconstructing Aerosol Optical Depth Using Spatiotemporal Long Short-Term Memory Convolutional Autoencoder. Scientific Data, 10, Article No. 842. [Google Scholar] [CrossRef] [PubMed]
[32] Prokhorenkova, L., Gusev, G., Vorobev, A., et al. (2019) CatBoost: Unbiased Boosting with Categorical Features.
[33] Guo, Z., Wang, X. and Ge, L. (2023) Classification Prediction Model of Indoor PM2.5 Concentration Using Catboost Algorithm. Frontiers in Built Environment, 9, Article No. 6174. [Google Scholar] [CrossRef] 
[34] Shahriar, S.A., Kayes, I., Hasan, K., Hasan, M., Islam, R., Awang, N.R., et al. (2021) Potential of ARIMA-ANN, ARIMA-SVM, DT and Catboost for Atmospheric PM2.5 Forecasting in Bangladesh. Atmosphere, 12, Article No. 100. [Google Scholar] [CrossRef] 
[35] 李欣, 曹建华, 孙星. 空间视角下城市化对雾霾污染的影响分析——以长三角区域为例[J]. 环境经济研究, 2017, 2(2): 81-92.
[36] Filonchyk, M., Yan, H., Zhang, Z., Yang, S., Li, W. and Li, Y. (2019) Combined Use of Satellite and Surface Observations to Study Aerosol Optical Depth in Different Regions of China. Scientific Reports, 9, Article ID: 1207193. [Google Scholar] [CrossRef] [PubMed]

为你推荐