Ensemble averaging based assessment of spatiotemporal variations in ambient PM_2.5 concentrations over Delhi, India, during 2010–2016

Keyphrases

• Spatiotemporal Variation 100%
• India 100%
• Ensemble Averaging 100%
• PM2.5 Concentration 100%
• Ambient PM2.5 100%
• Particulate Matter 2.5 (PM2.5) 66%
• Generalized Additive Model 66%
• Spatiotemporal 66%
• Extreme Gradient Boosting 66%
• Particulate Matter Concentration 66%
• High-resolution 33%
• Neural Network 33%
• PM2.5 Exposure 33%
• PM10 33%
• Morbidity Mortality 33%
• Premature Mortality 33%
• Prediction Accuracy 33%
• Population Density 33%
• High Concentration 33%
• Major Risk Factors 33%
• Geographical Differences 33%
• High Spatial 33%
• Land Use 33%
• Root Mean Square Error 33%
• Sparsity 33%
• Particulate Matter 33%
• Random Forest 33%
• Prediction Bias 33%
• Monitoring Data 33%
• Ambient Air Pollution 33%
• Tensor Product 33%
• Dose-response Relationship 33%
• Elastic Net 33%
• Satellite Data 33%
• Variable Density 33%
• Spatial Smoothing 33%
• Daily Averages 33%
• Meteorological Variables 33%
• Model Accuracy 33%
• Product Basis 33%
• Health Effects 33%
• Spatial Modeling 33%
• Tree-based 33%
• Exposure Assessment 33%
• Seasonal Differences 33%
• Multiple Data Sources 33%
• Land Use Features 33%
• Least Squares Support Vector Regression (LSSVR) 33%
• Regression Forest 33%
• Polluted Regions 33%
• Modeling Exercises 33%
• Multi-stage Modeling 33%
• Ground Monitoring 33%
• Indo-Gangetic Plain 33%
• Averaging Approach 33%
• Calibration Regression 33%
• Data Ensemble 33%

Earth and Planetary Sciences

• Particular Matter 2.5 100%
• India 100%
• Atmospheric Aerosol 75%
• Land Use 50%
• Air Pollution 25%
• Population Density 25%
• Satellite Data 25%
• Monitoring Data 25%
• Support Vector Machine 25%
• Ambient Air 25%
• Exposure Assessment 25%
• Major Risk 25%