Haze Grading Using the Convolutional Neural Networks

Atmosphere

Lei Wang¹  Lirong Yin¹  Bo Yang²  Shan Liu²  Jiawei Tian²  Weizheng Huang²  Wenfeng Zheng² 

[1] Department of Geography and Anthropology, Louisiana State University, Baton Rouge, LA 70803, USA;School of Automation, University of Electronic Science and Technology of China, Chengdu 610054, China;

关键词: CNN;    MODIS;    PM2.5;    haze forecast;    aerosol optical depth;    air pollution;   

DOI  :  10.3390/atmos13040522

来源: DOAJ

【 摘 要 】

As an air pollution phenomenon, haze has become one of the focuses of social discussion. Research into the causes and concentration prediction of haze is significant, forming the basis of haze prevention. The inversion of Aerosol Optical Depth (AOD) based on remote sensing satellite imagery can provide a reference for the concentration of major pollutants in a haze, such as PM2.5 concentration and PM10 concentration. This paper used satellite imagery to study haze problems and chose PM2.5, one of the primary haze pollutants, as the research object. First, we used conventional methods to perform the inversion of AOD on remote sensing images, verifying the correlation between AOD and PM2.5. Subsequently, to simplify the parameter complexity of the traditional inversion method, we proposed using the convolutional neural network instead of the traditional inversion method and constructing a haze level prediction model. Compared with traditional aerosol depth inversion, we found that convolutional neural networks can provide a higher correlation between PM2.5 concentration and satellite imagery through a more simplified satellite image processing process. Thus, it offers the possibility of researching and managing haze problems based on neural networks.

【 授权许可】

Unknown