Simulation of daily temperatures for climate change scenarios over Portugal: a neural network model approach

Methods to assess the impact of global warming on the temperature regime of a single site are explored with reference to Coimbra in Portugal. The basis of the analysis is information taken from a climate change simulation performed with a state-of-the-art general circulation model (the Hadley Centre model). First, it is shown that the model is unable to reproduce accurately the statistics of daily maximum and minimum temperature at the site. Second, using a re-analysis data set, downscaling models are developed to predict site temperature from large-scale free atmosphere variables derived from the sea level pressure and 500 hPa geopotential height fields. In particular, the relative per- formances of linear models and non-linear artificial neural networks are compared using a set of rigor- ous validation techniques. It is shown that even a simple configuration of a 2-layer non-linear neural network significantly improves on the performance of a linear model. Finally, the non-linear neural network model is initialised with general circulation model output to construct scenarios of daily tem- perature at the present day (1970-79) and for a future decade (2090-99). These scenarios are analysed with special attention to the comparison of the frequencies of heat waves (days with maximum tem- perature greater than 35°C) and cold spells (days with minimum temperature below 5°C).

[1]  J. Corte-Real,et al.  A weather generator for obtaining daily precipitation scenarios based on circulation patterns , 1999 .

[2]  M. Gardner,et al.  Neural network modelling and prediction of hourly NOx and NO2 concentrations in urban air in London , 1999 .

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

[4]  G. Bürger,et al.  Linear versus nonlinear techniques in downscaling , 1998 .

[5]  C. Goodess,et al.  DEVELOPMENT OF DAILY RAINFALL SCENARIOS FOR SOUTHEAST SPAIN USING A CIRCULATION-TYPE APPROACH TO DOWNSCALING , 1998 .

[6]  M. W Gardner,et al.  Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences , 1998 .

[7]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[8]  Budong Qian,et al.  Regional climate change in Portugal: precipitation variability associated with large‐scale atmospheric circulation , 1998 .

[9]  C. Thompson,et al.  A Comparison of Statistical and Model-Based Downscaling Techniques for Estimating Local Climate Variations. , 1998 .

[10]  Robert J. Kuligowski,et al.  Experiments in Short-Term Precipitation Forecasting Using Artificial Neural Networks , 1998 .

[11]  Bruce Hewitson,et al.  Doubled CO2 precipitation changes for the Susquehanna basin: down-scaling from the Genesis general c , 1998 .

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

[13]  The Simulation of Daily Temperature Time Series from GCM Output. Part I: Comparison of Model Data with Observations , 1997 .

[14]  C. Goodess,et al.  The Simulation of Daily Temperature Time Series from GCM Output. Part II: Sensitivity Analysis of an Empirical Transfer Function Methodology , 1997 .

[15]  Tereza Cavazos.  Downscaling large-scale circulation to local winter rainfall in north-eastern Mexico , 1997 .

[16]  Xiaolan L. Wang,et al.  On the relationships between daily circulation patterns and precipitation in Portugal , 1997 .

[17]  John F. B. Mitchell,et al.  The second Hadley Centre coupled ocean-atmosphere GCM: model description, spinup and validation , 1997 .

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

[19]  Guido Visconti,et al.  A Neural Network Approach for blocking recognition , 1996 .

[20]  Xiaolan L. Wang,et al.  Downscaling GCM information to regional scales: a non-parametric multivariate regression approach , 1995 .

[21]  Richard G. Jones,et al.  Simulation of climate change over europe using a nested regional‐climate model. I: Assessment of control climate, including sensitivity to location of lateral boundaries , 1995 .

[22]  Linda O. Mearns,et al.  Analysis of daily variability of precipitation in a nested regional climate model: comparison with observations and doubled CO2 results , 1995 .

[23]  Daniel S. Wilks,et al.  Statistical Methods in the Atmospheric Sciences: An Introduction , 1995 .

[24]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[25]  H A Ceccatto,et al.  Predicting Indian monsoon rainfall: a neural network approach , 1994 .

[26]  Predicting Snowfall from Synoptic Circulation: A Comparison of Linear Regression and Neural Network Methodologies , 1994 .

[27]  U. Cubasch,et al.  Downscaling of global climate change estimates to regional scales: an application to Iberian rainfal , 1993 .

[28]  B. Hewitson,et al.  Large‐scale atmospheric controls on local precipitation in tropical Mexico , 1992 .

[29]  Paul M. Tag,et al.  Toward Automated Interpretation of Satellite Imagery for Navy Shipboard Applications , 1992 .

[30]  P. G. J. Lisboa.  Neural Networks: Current Applications , 1992 .

[31]  M. Schlesinger,et al.  A Method of Relating General Circulation Model Simulated Climate to the Observed Local Climate. Part I: Seasonal Statistics , 1990 .

[32]  F. Giorgi.  Simulation of Regional Climate Using a Limited Area Model Nested in a General Circulation Model , 1990 .

[33]  T. Wigley,et al.  Obtaining sub-grid-scale information from coarse-resolution general circulation model output , 1990 .

[34]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[35]  A. H. Murphy,et al.  Skill Scores Based on the Mean Square Error and Their Relationships to the Correlation Coefficient , 1988 .

[36]  R. H. Myers.  Classical and modern regression with applications , 1986 .

[37]  J. Peixoto,et al.  Physics of climate , 1984 .

[38]  T. Hassard,et al.  Applied Linear Regression , 2005 .