Many studies about estimation of air pollutants such as particulate matter (PM), PM2.5 and PM10, have used the aerosol optical depth (AOD). But, due to coarse resolution of AOD images, the use of satellite-derived based AOD products for PM estimation of small cities is not possible. To deal with this difficulty, we use the level 1 product of MODIS. The proposed method uses a deep neural network and a random forest model and utilizes the first and second bands of MODIS to estimate the PM values. The results show the superior performance of the proposed models compared to some state-of-the-art PM estimation methods. The outcome of this research is design of a PM map generation for Tehran city.
Imani, M. (2023). Concentration Estimation of Air Pollutants (PM2.5 and PM10) Using MODIS Satellite Data, Deep Neural Network and Random Forest. Soft Computing Journal, (), -. doi: 10.22052/scj.2023.248326.1097
MLA
Maryam Imani. "Concentration Estimation of Air Pollutants (PM2.5 and PM10) Using MODIS Satellite Data, Deep Neural Network and Random Forest". Soft Computing Journal, , , 2023, -. doi: 10.22052/scj.2023.248326.1097
HARVARD
Imani, M. (2023). 'Concentration Estimation of Air Pollutants (PM2.5 and PM10) Using MODIS Satellite Data, Deep Neural Network and Random Forest', Soft Computing Journal, (), pp. -. doi: 10.22052/scj.2023.248326.1097
VANCOUVER
Imani, M. Concentration Estimation of Air Pollutants (PM2.5 and PM10) Using MODIS Satellite Data, Deep Neural Network and Random Forest. Soft Computing Journal, 2023; (): -. doi: 10.22052/scj.2023.248326.1097