Artificial neural network models for prediction of PM10 hourly concentrations, in the Greater Area of Athens, Greece

By G. Grivas, A. Chaloulakou. 2006

338 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Synoptic and meteorological drivers of extreme ozone concentrations over Europe (2016, background): “Moreover, it has been shown that model performance increases by including persistence of air quality variables (Pérez et al 2000, Smith et al 2000, Grivas and Chaloulakou 2006).”
Long short-term memory - Fully connected (LSTM-FC) neural network for PM2.5 concentration prediction. (2019, methodology): “Physical-model-based methods are widely used in environmental community, such as operational street canyon models (Hertel and Berkowicz (2015)), Gaussian plume models (Carruthers et al. (1992)) and reduced-scale models (Baker and Hargreaves (2001)).”
Comparing the Performance of Statistical Models for Predicting PM10 Concentrations (2014, methodology): “However, other models, such as NN have been applied for analysing PM10 levels and their results are compared with different models, especially MLRM (Chaloulakou et al., 2003; Grivas and Chaloulakou, 2006; Ul-Saufie et al., 2011) and statistical parameters such correlation coefficients, bias errors, ”