| 基于MODIS数据与多机器学习法的日PM2.5模拟研究 |
| |
| 引用本文： | 徐发昭,李净,褚馨德,满元伟.基于MODIS数据与多机器学习法的日PM2.5模拟研究[J].中国环境科学,2022,42(6):2523-2529. |
| |
| 作者姓名： | 徐发昭 李净 褚馨德 满元伟 |
| |
| 作者单位： | 西北师范大学地理与环境科学学院, 甘肃 兰州 730070 |
| |
| 基金项目： | 国家自然科学基金资助项目(41861013,42071089,41801052)； |
| |
| 摘 要： | 为了深入了解地面PM2.5的空间分布,以山东省为研究区,利用2019年的PM2.5站点实测数据,结合中分辨率成像光谱仪(MODIS)的L3级别的MCD19A2气溶胶光学厚度产品,充分考虑人口、地形、气象等因素,使用RF、SVR、BPNN、DNN等4种机器学习算法对山东省2019年逐日PM2.5进行了模拟.结果表明:随机森林模型(RF)的RMSE和MAE的值分别为12.67和6.62,优于BPNN、SVR和DNN模型.随机森林模型(RF)最适合山东省的日PM2.5模拟.
|
| 关 键 词： | 遥感 PM2.5 AOD 机器学习 |
| 收稿时间： | 2021-11-24 |
Simulation of daily PM2.5 based on MODIS data and multi-machine learning method |
| |
| XU Fa-zhao,LI Jing,CHU Xin-de,MAN Yuan-wei.Simulation of daily PM2.5 based on MODIS data and multi-machine learning method[J].China Environmental Science,2022,42(6):2523-2529. |
| |
| Authors: | XU Fa-zhao LI Jing CHU Xin-de MAN Yuan-wei |
| |
| Institution: | College of Geography and Environmental Science, Northwest Normal University, Lanzhou 730070, China |
| |
| Abstract: | In order to further understand the spatial distribution of PM2.5 on the ground, based on the PM2.5 measured data in 2019, MCD19A2 aerosol optical depth product of the Moderate Resolution Imaging Spectroradiometer (MODIS) at the L3 level, taking Shandong Province as the study area, and fully considering the factors including population, terrain, and weather. The daily PM2.5 in 2019 was simulated by using the four machine learning algorithms of Random Forest (RF), Support Vector Regression (SVR), Back Propagation Neural Network (BPNN), and Deep Neural Networks (DNN). The result shows the RMSE and MAE values of the RF are 12.67 and 6.62, respectively, which are better than BPNN, SVR and DNN models. RF is most suitable for the daily PM2.5 simulation in Shandong Province. |
| |
| Keywords: | remote sensing PM2 5 AOD machine learning |
|
| 点击此处可从《中国环境科学》浏览原始摘要信息 |
| 点击此处可从《中国环境科学》下载免费的PDF全文 |
|
