A neural network model for visibility nowcasting from surface observations: Results and sensitivity to physical input variables

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.

[1]  William W. Hsieh,et al.  Applying Neural Network Models to Prediction and Data Analysis in Meteorology and Oceanography. , 1998 .

[2]  Antonello Pasini,et al.  Short-range visibility forecast by means of neural-network modelling: a case-study , 1995 .

[3]  Caren Marzban,et al.  The Notion of “Best Predictors”: An Application to Tornado Prediction , 1999 .

[4]  Timothy Masters,et al.  Practical neural network recipes in C , 1993 .

[5]  Antonello Pasini,et al.  Neural Network Modelling: Perspectives of Application for Monitoring and Forecasting Physical-Chemical Variables in the Boundary Layer , 1996 .

[6]  D. McCann.  A Neural Network Short-Term Forecast of Significant Thunderstorms , 1992 .

[7]  C. Marzban.  A Neural Network for Tornado Diagnosis: Managing Local Minima , 2000, Neural Computing & Applications.

[8]  J. Shao,et al.  Improving Nowcasts of Road Surface Temperature by a Backpropagation Neural Network , 1998 .

[9]  C. Marzban.  Scalar measures of performance in rare-event situations , 1998 .

[10]  D. N. Asimakopoulos,et al.  A neural network approach for modeling the Heat Island phenomenon in urban areas during the summer period , 1999 .

[11]  F. Tangang,et al.  Forecasting ENSO Events: A Neural Network–Extended EOF Approach. , 1998 .

[12]  Marija Zlata Boznar,et al.  A neural network-based method for short-term predictions of ambient SO2 concentrations in highly polluted industrial areas of complex terrain , 1993 .

[13]  A. Pasini,et al.  Towards Fog Forecasting in Meteorology by Means of Back-Propagation Neural Networks with Weighted Least-Squares Training , 1997 .

[14]  Caren Marzban,et al.  A Neural Network for Tornado Prediction Based on Doppler Radar-Derived Attributes , 1996 .

[15]  Charles A. Doswell,et al.  Precipitation Forecasting Using a Neural Network , 1999 .

[16]  G. Mihalakakou,et al.  Modeling ambient air temperature time series using neural networks , 1998 .

[17]  William W. Hsieh,et al.  Forecasting regional sea surface temperatures in the tropical Pacific by neural network models, with wind stress and sea level pressure as predictors , 1998 .

[18]  Caren Marzban,et al.  A Neural Network for Damaging Wind Prediction , 1998 .