Linear and nonlinear post-processing of numerically forecasted surface temperature

In this paper we test different approaches to the statistical post-processing of gridded numerical surface air temperatures (provided by the European Centre for Medium- Range Weather Forecasts) onto the temperature measured at surface weather stations located in the Italian region of Puglia. We consider simple post-processing techniques, like correction for altitude, linear regression from different input parameters and Kalman filtering, as well as a neural net- work training procedure, stabilised (i.e. driven into the ab- solute minimum of the error function over the learning set) by means of a Simulated Annealing method. A comparative analysis of the results shows that the performance with neu- ral networks is the best. It is encouraging for systematic use in meteorological forecast-analysis service operations.

[1]  Marc Dejardin,et al.  Simulated annealing and neural networks as alternative methods for nonlinear constrained optimization , 1996 .

[2]  Anders Krogh,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

[3]  Darrell R. Massie,et al.  Predicting Daily Maximum Temperatures Using Linear Regression and Eta Geopotential Thickness Forecasts , 1997 .

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

[5]  Emanuel Marom,et al.  Efficient Training of Recurrent Neural Network with Time Delays , 1997, Neural Networks.

[6]  H. N. Mhaskar,et al.  Neural Networks for Optimal Approximation of Smooth and Analytic Functions , 1996, Neural Computation.

[7]  Ko Koizumi.  An Objective Method to Modify Numerical Model Forecasts with Newly Given Weather Data Using an Artificial Neural Network , 1999 .

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

[9]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Kathleen E. Duncan,et al.  Ozone Modeling Using Neural Networks , 2000 .

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

[12]  William W. Hsieh,et al.  Skill Comparisons between Neural Networks and Canonical Correlation Analysis in Predicting the Equatorial Pacific Sea Surface Temperatures , 2000 .

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

[14]  M. Marrocu,et al.  Meteorological forecasting for the European Southern observatory in Chile , 2000 .