Open AccessA neural network model for visibility nowcasting from surface observations: Results and sensitivity to physical input variables
Author(s) -
Pasini Antonello,
Pelino Vinicio,
Potestà Sergio
Publication year - 2001
Publication title -
journal of geophysical research: atmospheres
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.67
H-Index - 298
eISSN - 2156-2202
pISSN - 0148-0227
DOI - 10.1029/2001jd900134
Subject(s) - nowcasting , visibility , artificial neural network , pruning , sensitivity (control systems) , computer science , bivariate analysis , range (aeronautics) , meteorology , artificial intelligence , machine learning , geography , engineering , electronic engineering , aerospace engineering , agronomy , biology
A neural network model recently developed for fog nowcasting from surface observations is summarized in its features, paying attention to its particular learning structure (weighted least squares training), introduced because of the nonconstant errors associated with the estimation of visibility values. We apply it to a winter forecast of meteorological visibility in Milan (Italy). The performance of this model is presented and shown to be always better than persistence and climatology. Finally, we introduce a bivariate analysis and a network pruning scheme and discuss the possibility of identifying the more significant physical input variables for a correct very short‐range forecast of visibility.