Ceiling and Visibility Forecasts via Neural Networks

Abstract Statistical postprocessing of numerical model output can improve forecast quality, especially when model output is combined with surface observations. In this article, the development of nonlinear postprocessors for the prediction of ceiling and visibility is discussed. The forecast period is approximately 2001–05, involving data from hourly surface observations, and from the fifth-generation Pennsylvania State University–National Center for Atmospheric Research Mesoscale Model. The statistical model for mapping these data to ceiling and visibility is a neural network. A total of 39 such neural networks are developed for each of 39 terminal aerodrome forecast stations in the northwest United States. These postprocessors are compared with a number of alternatives, including logistic regression, and model output statistics (MOS) derived from the Aviation Model/Global Forecast System. It is found that the performance of the neural networks is generally superior to logistic regression and MOS. Depend...

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

[2]  Caren Marzban,et al.  A neural network for tornado diagnosis , 2000 .

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

[4]  Joby L. Hilliker,et al.  An Observations-Based Statistical System for Warm-Season Hourly Probabilistic Forecasts of Low Ceiling at the San Francisco International Airport , 1999 .

[5]  J. Fritsch,et al.  The Impact of High-Frequency Surface Weather Observations on Short-Term Probabilistic Forecasts of Ceiling and Visibility , 2004 .

[6]  Paul Roebber,et al.  Improving Snowfall Forecasting by Diagnosing Snow Density , 2003 .

[7]  Stephen M. Leyton,et al.  Short-Term Probabilistic Forecasts of Ceiling and Visibility Utilizing High-Density Surface Weather Observations , 2003 .

[8]  Brunello Tirozzi,et al.  Linear and nonlinear post-processing of numerically forecasted surface temperature , 2003 .

[9]  E. Grimit,et al.  Initial Results of a Mesoscale Short-Range Ensemble Forecasting System over the Pacific Northwest , 2002 .

[10]  Caren Marzban,et al.  MOS, Perfect Prog, and Reanalysis , 2006 .

[11]  Antonello Pasini,et al.  A neural network model for visibility nowcasting from surface observations: Results and sensitivity to physical input variables , 2001 .

[12]  C. João,et al.  FOG FORECAST FOR THE INTERNATIONAL AIRPORT OF MACEIÓ , BRAZIL USING ARTIFICIAL NEURAL NETWORK , 2006 .

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

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

[15]  A. H. Murphy,et al.  A General Framework for Forecast Verification , 1987 .

[16]  Petri Koistinen,et al.  Kernel regression and backpropagation training with noise , 1991, [Proceedings] 1991 IEEE International Joint Conference on Neural Networks.

[17]  A. H. Murphy,et al.  Diagnostic verification of probability forecasts , 1992 .

[18]  Robert L. Vislocky,et al.  An Automated, Observations-Based System for Short-Term Prediction of Ceiling and Visibility , 1997 .

[19]  Caren Marzban,et al.  Neural Networks for Postprocessing Model Output: ARPS , 2003 .