Spatial-temporal characterization of air pollutants using a hybrid deep learning/Kriging model incorporated with a weather normalization technique

Keyphrases

• Normalization Method 100%
• Spatial-temporal 100%
• SO42- 100%
• Air Pollutants 100%
• Hybrid Deep Learning 100%
• Temporal Characterization 100%
• PM2.5 Chemical Composition 100%
• Weather Model 100%
• Weather Normalization 100%
• Kriging Model 100%
• Neural Network 66%
• Central Taiwan 66%
• Air Pollutant Concentration 66%
• Primary Emission 66%
• Multi-step Ahead 66%
• High-resolution 33%
• Politicians 33%
• Prediction Model 33%
• Artificial Neural Network 33%
• Urban Areas 33%
• Spatiotemporal Variation 33%
• Quality Control Strategy 33%
• Temporal Variation 33%
• Air Quality 33%
• Reduction Strategies 33%
• Hotspot Detection 33%
• Neural Network Algorithm 33%
• Exposure Risk 33%
• Composition Measurement 33%
• Monitoring Station 33%
• Air Pollution Control 33%
• Anthropogenic Activities 33%
• COVID-19 33%
• COVID-19 Impact 33%
• Spatio-temporal Prediction 33%
• Meteorological Parameters 33%
• PM2.5 Constituents 33%
• Human Exposure Assessment 33%
• Air Pollutant Reduction 33%
• Network Kriging 33%
• Air Quality Control 33%

Earth and Planetary Sciences

• Kriging 100%
• Air Pollutant 100%
• Particular Matter 2.5 80%
• Taiwan 40%
• Emissions 40%
• Temporal Variation 40%
• Pollutant Concentration 40%
• Artificial Neural Network 40%
• Time Series 20%
• Exposure Assessment 20%
• Air Pollution 20%
• Monitoring Station 20%
• Pollution Control 20%
• Risk Exposure 20%
• Meteorological Parameter 20%
• Air Quality Control 20%
• Pollutant Reduction 20%
• Air Quality 20%