Predictive Uncertainty in Environmental Modelling

Artificial neural networks have proved an attractive approach to non-linear regression problems arising in environmental modelling, such as statistical downscaling, short-term forecasting of atmospheric pollutant concentrations and rainfall run-off modelling. However, environmental datasets are frequently very noisy and characterised by a noise process that may be heteroscedastic (having input dependent variance) and/or non-Gaussian. The aim of this paper is to review an existing methodology for estimating predictive uncertainty in such situations, and more importantly illustrate how a model of the predictive distribution may be exploited in assessing the possible impacts of climate change and to improve current decision making processes. The results of the WCCI-2006 predictive uncertainty in environmental modelling challenge are also reviewed and some areas suggested where further research may provide significant benefits.

[1]  D. Cox,et al.  An Analysis of Transformations , 1964 .

[2]  T. K. Leen.  Learning Local Error Bars for Nonlinear Regression , 1995 .

[3]  P. M. Williams,et al.  Using Neural Networks to Model Conditional Multivariate Densities , 1996, Neural Computation.

[4]  D. Mackay,et al.  A Practical Bayesian Framework for Backprop Networks , 1991 .

[5]  T. Wigley,et al.  Statistical downscaling of general circulation model output: A comparison of methods , 1998 .

[6]  Peter M. Williams,et al.  Modelling Seasonality and Trends in Daily Rainfall Data , 1997, NIPS.

[7]  H. Storch,et al.  The Analog Method as a Simple Statistical Downscaling Technique: Comparison with More Complicated Methods , 1999 .

[8]  Christopher M. Bishop,et al.  Bayesian Inference of Noise Levels in Regression , 1996, ICANN.

[9]  Gavin C. Cawley,et al.  Statistical downscaling with artificial neural networks , 2003, ESANN.

[10]  Geoffrey E. Hinton,et al.  Bayesian Learning for Neural Networks , 1995 .

[11]  Richard A. Johnson,et al.  A new family of power transformations to improve normality or symmetry , 2000 .

[12]  A.N. Belbachir,et al.  A comparative study of artificial neural network techniques for river stage forecasting , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[13]  I. M. Pyshik,et al.  Table of integrals, series, and products , 1965 .

[14]  Dimitri P. Solomatine,et al.  Neural networks and M5 model trees in modelling water level-discharge relationship , 2005, Neurocomputing.

[15]  M. Aitkin.  Modelling variance heterogeneity in normal regression using GLIM , 1987 .

[16]  D. A. Woolhiser,et al.  Maximum Likelihood Estimation of Fourier Coefficients to Describe Seasonal Variations of Parameters in Stochastic Daily Precipitation Models , 1979 .

[17]  Richard Coe,et al.  A Model Fitting Analysis of Daily Rainfall Data , 1984 .

[18]  Gavin C. Cawley,et al.  Modelling SO2 concentration at a point with statistical approaches , 2004, Environ. Model. Softw..

[19]  Robert L. Wilby,et al.  Multi-site downscaling of heavy daily precipitation occurrence and amounts , 2005 .

[20]  David J. C. MacKay,et al.  A Practical Bayesian Framework for Backpropagation Networks , 1992, Neural Computation.

[21]  P. McCullagh,et al.  Generalized Linear Models , 1992 .

[22]  Peter J. Bickel,et al.  Maximum Likelihood Estimation of Intrinsic Dimension , 2004, NIPS.

[23]  Gavin C. Cawley,et al.  Heteroscedastic kernel ridge regression , 2004, Neurocomputing.

[24]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[25]  C. Bishop.  Mixture density networks , 1994 .

[26]  Elie Bienenstock,et al.  Neural Networks and the Bias/Variance Dilemma , 1992, Neural Computation.

[27]  David J. C. MacKay,et al.  Bayesian Interpolation , 1992, Neural Computation.

[28]  Ian T. Nabney,et al.  Netlab: Algorithms for Pattern Recognition , 2002 .

[29]  A. Weigend,et al.  Estimating the mean and variance of the target probability distribution , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[30]  A. N. Tikhonov,et al.  Solutions of ill-posed problems , 1977 .

[31]  Gavin C. Cawley,et al.  A rigorous inter-comparison of ground-level ozone predictions , 2003 .

[32]  F. Giorgi,et al.  Introduction to special section : Regional climate modeling revisited , 1999 .

[33]  G. Cawley,et al.  Published online in Wiley InterScience (www.interscience.wiley.com). DOI: 10.1002/joc.1318 DOWNSCALING HEAVY PRECIPITATION OVER THE UNITED KINGDOM: A COMPARISON OF DYNAMICAL AND STATISTICAL METHODS AND THEIR FUTURE SCENARIOS , 2006 .

[34]  B. Hewitson,et al.  Climate downscaling: techniques and application , 1996 .

[35]  Carl E. Rasmussen,et al.  Warped Gaussian Processes , 2003, NIPS.

[36]  Michael I. Jordan,et al.  Regression with input-dependent noise: A Gaussian process treatment , 1998 .

[37]  L. M. M.-T..  Theory of Probability , 1929, Nature.

[38]  I. S. Gradshteyn,et al.  Table of Integrals, Series, and Products , 1976 .

[39]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[40]  Wray L. Buntine,et al.  Bayesian Back-Propagation , 1991, Complex Syst..

[41]  Peter M. Williams,et al.  Bayesian Regularization and Pruning Using a Laplace Prior , 1995, Neural Computation.