Spatial and meteorological relevance in NO2 estimations: a case study in the Bay of Algeciras (Spain)

摘要: This study focuses on how to determine the most relevant variables in order estimate hourly NO2 concentrations a monitoring network located Bay of Algeciras (Spain). For each station network, artificial neural networks and multiple linear regression have been used compute estimation models. Meteorological from nearby stations as inputs, feature selection procedure has applied previous step. The different models developed statistically compared. inputs best model for were important concentration level. These estimations can be very useful resource provide autonomous capacities automatic decalibration detection or missing data imputation networks. Finally, similarities between stations, according relevance variables, analysed with aid hierarchical clustering algorithm.