Evaluation of machine learning techniques with multiple remote sensing datasets in estimating monthly concentrations of ground-level PM_2.5

Keyphrases

• Machine Learning Techniques 100%
• Aerosol Optical Depth 100%
• Ground-level PM2.5 100%
• Multiple Remote Sensing 100%
• Remote Sensing Dataset 100%
• PM2.5 60%
• Cubist 40%
• Satellite Images 20%
• Satellite Data 20%
• Satellite Products 20%
• Nonlinear Relationship 20%
• Machine Learning Algorithms 20%
• Predictive Algorithm 20%
• Uneven Distribution 20%
• Air Pollutants 20%
• Spatiotemporal Variation 20%
• PM2.5 Concentration 20%
• Complex Terrain 20%
• Fine Particulate Matter PM2.5 20%
• Weather Station 20%
• Depth Data 20%
• Land Surface Temperature 20%
• Random Forest 20%
• Population Risk 20%
• Wildfire 20%
• Spatiotemporal Prediction 20%
• Sparse Distribution 20%
• Image Learning 20%
• Extreme Gradient Boosting 20%
• Land Use Regression 20%
• PM2.5 Prediction 20%
• Variable Importance Analysis 20%
• Geospatial Techniques 20%
• Two-element Array 20%
• Better Performance 20%
• High Spatiotemporal 20%
• Depth Dataset 20%

Earth and Planetary Sciences

• Machine Learning 100%
• Particular Matter 2.5 100%
• Remote Sensing 100%
• Complex Terrain 12%
• Satellite Image 12%
• Land Surface Temperature 12%
• Fine Particulate Matter 12%
• Air Pollutant 12%
• Land Use 12%
• Weather Stations 12%
• Extreme Gradient Boosting 12%