Downscaling GCMs using the Smooth Support Vector Machine method to predict daily precipitation in the Hanjiang Basin

General circulation models (GCMs) are often used in assessing the impact of climate change at global and continental scales. However, the climatic factors simulated by GCMs are inconsistent at comparatively smaller scales, such as individual river basins. In this study, a statistical downscaling approach based on the Smooth Support Vector Machine (SSVM) method was constructed to predict daily precipitation of the changed climate in the Hanjiang Basin. NCEP/NCAR reanalysis data were used to establish the statistical relationship between the larger scale climate predictors and observed precipitation. The relationship obtained was used to project future precipitation from two GCMs (CGCM2 and HadCM3) for the A2 emission scenario. The results obtained using SSVM were compared with those from an artificial neural network (ANN). The comparisons showed that SSVM is suitable for conducting climate impact studies as a statistical downscaling tool in this region. The temporal trends projected by SSVM based on the A2 emission scenario for CGCM2 and HadCM3 were for rainfall to decrease during the period 2011–2040 in the upper basin and to increase after 2071 in the whole of Hanjiang Basin.

[1]  Roberto Deidda,et al.  Multifractal analysis and simulation of rainfall fields in space , 1999 .

[2]  Hayley J. Fowler,et al.  Linking climate change modelling to impacts studies: recent advances in downscaling techniques for hydrological modelling , 2007 .

[3]  T. Wigley,et al.  Application of Markov models to area-average daily precipitation series and interannual variability in seasonal totals , 1993 .

[4]  P. Whetton,et al.  Guidelines for Use of Climate Scenarios Developed from Statistical Downscaling Methods , 2004 .

[5]  R. Reynolds,et al.  The NCEP/NCAR 40-Year Reanalysis Project , 1996, Renewable Energy.

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

[7]  John C. Platt,et al.  Fast training of support vector machines using sequential minimal optimization, advances in kernel methods , 1999 .

[8]  John F. B. Mitchell,et al.  The simulation of SST, sea ice extents and ocean heat transports in a version of the Hadley Centre coupled model without flux adjustments , 2000 .

[9]  P. Jones,et al.  Precipitation and air flow indices over the British Isles , 1996 .

[10]  T. Wigley,et al.  Downscaling general circulation model output: a review of methods and limitations , 1997 .

[11]  P. Coulibaly,et al.  Downscaling Precipitation and Temperature with Temporal Neural Networks , 2005 .

[12]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[13]  G. Boer,et al.  Warming asymmetry in climate change simulations , 2001 .

[14]  Robert L. Wilby,et al.  Integrated modelling of climate change impacts on water resources and quality in a lowland catchment: River Kennet, UK , 2006 .

[15]  A. Bardossy,et al.  Fuzzy rule-based downscaling of precipitation , 2005 .

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

[17]  C. Harpham,et al.  A daily weather generator for use in climate change studies , 2007, Environ. Model. Softw..

[18]  Witold F. Krajewski,et al.  Rainfall forecasting in space and time using a neural network , 1992 .

[19]  Subimal Ghosh,et al.  Statistical downscaling of GCM simulations to streamflow using relevance vector machine , 2008 .

[20]  Chris Kilsby,et al.  A stochastic rainfall model for the assessment of regional water resource systems under changed climatic condition , 2000 .

[21]  Martin Dubrovský,et al.  High-Frequency and Low-Frequency Variability in Stochastic Daily Weather Generator and Its Effect on Agricultural and Hydrologic Modelling , 2004 .

[22]  Deliang Chen,et al.  Performance of statistical downscaling models in GCM validation and regional climate change estimates: application for Swedish precipitation , 2001 .

[23]  Shie-Yui Liong,et al.  Forecasting of hydrologic time series with ridge regression in feature space , 2007 .

[24]  David R. Musicant,et al.  Successive overrelaxation for support vector machines , 1999, IEEE Trans. Neural Networks.

[25]  L. Hay,et al.  A comparison of downscaled and raw GCM output: implications for climate change scenarios in the San Juan River basin, Colorado , 1999 .

[26]  D. Wilks.  Conditioning stochastic daily precipitation models on total monthly precipitation , 1989 .

[27]  Philipp Slusallek,et al.  Introduction to real-time ray tracing , 2005, SIGGRAPH Courses.

[28]  M. Maccracken,et al.  The Use of General Circulation Models to Predict Regional Climatic Change , 1991 .

[29]  Vijay P. Singh,et al.  Historical temporal trends of hydro-climatic variables and runoff response to climate variability and their relevance in water resource management in the Hanjiang basin , 2007 .

[30]  H. Tatli,et al.  A statistical downscaling method for monthly total precipitation over Turkey , 2004 .

[31]  R. Huth.  Statistical downscaling in central Europe: evaluation of methods and potential predictors , 1999 .

[32]  Keith Beven,et al.  Climate change and fluvial flood risk in the UK: more of the same? , 2008 .

[33]  Akira Kawamura,et al.  Neural Networks for Rainfall Forecasting by Atmospheric Downscaling , 2004 .

[34]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[35]  Chong-yu Xu.  From GCMs to river flow: a review of downscaling methods and hydrologic modelling approaches , 1999 .

[36]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[37]  V. V. Srinivas,et al.  Downscaling of precipitation for climate change scenarios: A support vector machine approach , 2006 .

[38]  C. Obled,et al.  Quantitative precipitation forecasts: a statistical adaptation of model outputs through an analogues sorting approach , 2002 .

[39]  A. Soldati,et al.  River flood forecasting with a neural network model , 1999 .

[40]  Yuh-Jye Lee,et al.  epsilon-SSVR: A Smooth Support Vector Machine for epsilon-Insensitive Regression , 2005, IEEE Trans. Knowl. Data Eng..

[41]  Shenglian Guo,et al.  A nonlinear perturbation model based on artificial neural network , 2007 .

[42]  Dingfang Li,et al.  A macro-scale and semi-distributed monthly water balance model to predict climate change impacts in China , 2002 .

[43]  R. Abrahart,et al.  Detection of conceptual model rainfall—runoff processes inside an artificial neural network , 2003 .

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

[45]  Chong-Yu Xu,et al.  Statistical precipitation downscaling in central Sweden with the analogue method , 2005 .

[46]  Thorsten Joachims,et al.  Making large-scale support vector machine learning practical , 1999 .

[47]  B. Schölkopf,et al.  Advances in kernel methods: support vector learning , 1999 .

[48]  Simon J. Mason,et al.  Simulating Climate over Western North America Using Stochastic Weather Generators , 2004 .

[49]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[50]  Hiromitsu Saegusa,et al.  Runoff analysis in humid forest catchment with artificial neural network , 2000 .

[51]  T. McMahon,et al.  Stochastic generation of annual, monthly and daily climate data: A review , 2001 .