Applying Deep Learning and Machine Learning Algorithms to Estimate PM$_{2.5}$ Concentration Using Satellite Data and Meteorological Data
Open Access
- 1 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 19, 2387-2404
Abstract
No abstract availableKeywords
Funding Information
- Center of Excellence in Digital Earth and Emerging Technology
- National Research Council of Thailand
- Hub of Talents in AI and Emerging Technology
This publication has 77 references indexed in Scilit:
- Influence of Temperature and Relative Humidity on PM2.5 Concentration over DelhiMAPAN, 2023
- Estimating daily PM2.5 concentrations using an extreme gradient boosting model based on VIIRS aerosol products over southeastern EuropeAir Quality, Atmosphere & Health, 2022
- Relational Study of PM2.5 Surface Concentration with MODIS Level 3 AOD Data Over India2022
- A hybrid CNN-LSTM model for predicting PM2.5 in Beijing based on spatiotemporal correlationEnvironmental and Ecological Statistics, 2021
- A review on the long short-term memory modelArtificial Intelligence Review, 2020
- Deep learning PM2.5 concentrations with bidirectional LSTM RNNAir Quality, Atmosphere & Health, 2019
- A novel hybrid-Garch model based on ARIMA and SVM for PM 2.5 concentrations forecastingAtmospheric Pollution Research, 2017
- Estimating national-scale ground-level PM25 concentration in China using geographically weighted regression based on MODIS and MISR AODEnvironmental Science and Pollution Research, 2016
- Ensemble Learning2012
- Support-vector networksMachine Learning, 1995