Space-Time Prediction of PM_2.5 Concentrations in Santiago de Chile Using LSTM Networks

Keyphrases

• Air Pollutants 33%
• Air Pollution 66%
• Attention Network 33%
• Classical Neural Network 33%
• Fixed Monitoring 33%
• Harmful Effects 33%
• Health Impact 33%
• Historical Value 66%
• Humidity 33%
• LSTM Model 33%
• LSTM Network 100%
• Meteorological Variables 33%
• Multi-layer LSTM 33%
• New Locations 33%
• Nitrogen Dioxide 33%
• PM2.5 Concentration 100%
• Pollutant Concentration 66%
• Preprocessing Techniques 33%
• Recurrent Network Model 33%
• Santiago De Chile 100%
• Series Analysis 33%
• Space-time Prediction 100%
• Spatial Points 33%
• Statistical Methods 33%
• Variable Temperature 33%
• Wind Direction 33%
• Wind Speed 33%

Engineering

• Air Pollution 100%
• Good Result 50%
• Harmful Effect 50%
• Human Health 50%
• Network Model 50%
• Particular Matter 2.5 100%
• Processing Step 50%
• Recurrent Network 50%
• Relative Humidity 50%