A satellite-based spatio-temporal machine learning model to reconstruct daily PM_2.5 concentrations across great britain

Keyphrases

• Machine Learning Models 100%
• Particulate Matter 2.5 (PM2.5) 100%
• Satellite-based 100%
• Great Britain 100%
• High Temporal Resolution 100%
• PM2.5 Concentration 100%
• Spatio-temporal Learning 100%
• Short-term Exposure 50%
• Epidemiological Study 50%
• Four-stage 50%
• Epidemiological Analysis 50%
• Health Risk 50%
• Prediction Model 50%
• Random Forest 50%
• Reliable Estimate 50%
• PM10 50%
• Air Pollution Health Effects 50%
• Aerosol Optical Depth 50%
• Long-term Exposure to PM2.5 50%
• PM2.5 Level 50%
• Satellite Products 50%
• Air Pollution Exposure 50%
• Good Accuracy 50%
• Spatial Component 50%
• Satellite Observations 50%
• Chemical Transport Model 50%
• Random Forest Algorithm 50%
• Temporal Coverage 50%
• Spatial-temporal 50%
• Fine Particulate Matter PM2.5 50%
• High-resolution Model 50%
• Geospatial Variables 50%
• Product Variables 50%
• Forest Architecture 50%
• Pollution Concentration 50%
• Reanalysis Model 50%
• Spatiotemporal Parameters 50%
• Atmospheric Reanalysis 50%

Earth and Planetary Sciences

• Machine Learning 100%
• United Kingdom 100%
• Particular Matter 2.5 100%
• Air Pollution 33%
• Atmospherics 16%
• Satellite Observation 16%
• Chemical Transport 16%
• Fine Particulate Matter 16%