A neural network-based land use regression model to estimate spatial-temporal variability of SO₂

Keyphrases

• Neural Network 100%
• Spatiotemporal Variation 100%
• Land Use Regression 100%
• Deep Neural Network Algorithm 50%
• Explanatory Ability 50%
• Taiwan 33%
• Regression Approach 33%
• Predictor Variables 33%
• Thermal Power Plant 33%
• Environmental Protection Agency 33%
• Industrial Waste 16%
• Health Impact 16%
• Prediction Model 16%
• Performance Level 16%
• Selection Strategy 16%
• Land Use 16%
• Combustion 16%
• PM10 16%
• Performance Prediction 16%
• Air Pollutants 16%
• Monitoring Station 16%
• External Data 16%
• Data Verification 16%
• 10-fold Cross Validation 16%
• Respiratory Problems 16%
• Validation Data 16%
• Sulfur Dioxide SO2 16%
• Plant Distribution 16%
• Regression Neural Network 16%
• Environmental Resources 16%
• Stepwise Variable Selection 16%
• Meteorological Dataset 16%
• Resource Database 16%
• Road Network Map 16%
• Digital Road Networks 16%
• Spatial Predictors 16%
• MODIS NDVI 16%
• Landmark Data 16%

Earth and Planetary Sciences

• Land Use 100%
• Artificial Neural Network 42%
• Taiwan 28%
• Environmental Protection Agency 28%
• Industrial Waste 14%
• Regional Geography 14%
• Human Health 14%
• Air Pollutant 14%
• Nitrogen Dioxide 14%
• Natural Resource 14%
• MODIS 14%
• Road Network 14%
• Monitoring Station 14%
• Digital Terrain Model 14%
• Sulphur Dioxide 14%

Engineering

• Land Use 100%
• Artificial Neural Network 42%
• Deep Neural Network 42%
• Electric Power Plant 28%
• Predictor Variable 28%
• Environmental Protection Agency 28%
• Human Health 14%
• Road Network 14%
• Prediction Performance 14%
• Natural Resource 14%
• Selection Procedure 14%