New atmospheric stability indices have been recently developed for the evaluation of primary pollution and the application results show their ability to grasp the physical features of the boundary layer. They are based on radon progeny measurements and multiple linear correlations with benzene. Here, neural networks are used in order to catch non-linearities in the boundary layer and to build non-linear indices. Their application to the modelling of benzene behaviour shows better prognostic results if compared with those coming from linear indices.
Non-linear atmospheric stability indices by neural network modelling
Pasini A;Perrino C;
2003
Abstract
New atmospheric stability indices have been recently developed for the evaluation of primary pollution and the application results show their ability to grasp the physical features of the boundary layer. They are based on radon progeny measurements and multiple linear correlations with benzene. Here, neural networks are used in order to catch non-linearities in the boundary layer and to build non-linear indices. Their application to the modelling of benzene behaviour shows better prognostic results if compared with those coming from linear indices.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
