Application of PLS-Regression as Downscaling Tool for Pichola Lake Basin in India

Manish Kumar Goyal, Chandra Shekhar Prasad Ojha

.

DOI: 10.4236/ijg.2010.12007                

Abstract

In this paper, downscaling models are developed using Partial Least Squares (PLS) Regression for obtaining projections of mean monthly precipitation to lake-basin scale in an arid region in India. The effectiveness of this approach is demonstrated through application to downscale the predictand for the Pichola lake region in Rajasthan state in India, which is considered to be a climatically sensitive region. The predictor variables are extracted from (1) the National Centers for Environmental Prediction (NCEP) reanalysis dataset for the period 1948-2000, and (2) the simulations from the third-generation Canadian Coupled Global Climate Model (CGCM3) for emission scenarios A1B, A2, B1 and COMMIT for the period 2001-2100. The selection of important predictor variables becomes a crucial issue for developing downscaling models since reanalysis data are based on wide range of meteorological measurements and observations. In this paper, we use PLS regression for quality prediction and its use for the variable selection based on the variable importance. The results of downscaling models using PLS regression show that precipitation is projected to increase in future for A2 and A1B scenarios, whereas it is least for B1 and COMMIT scenarios using predictors.

Keywords

PLS Regression, Precipitation, VIP Score

Conflicts of Interest

The authors declare no conflicts of interest.

References

[1]	R. Weisse and R. Oestreicher, “Reconstruction of Potential Evaporation for Water Balance Studies,” Climate Research, Vol. 16, No. 2, 2001, pp. 123-131.
[2]	C. Prudhomme, D. Jakob and C. Svensson, “Uncertainty and Climate Change Impact on the Flood Regime of Small UK Catchments,” Journal of Hydrology, Vol. 277, No. 1, 2003, pp. 1-23.
[3]	R. L. Wilby, C. W. Dawson and E. M. Barrow, “SDSM – A Decision Support Tool for the Assessment of Climate Change Impacts,” Environmental Modelling & Software, Vol. 17, No. 2, 2002, pp. 147-159.
[4]	M. K. Goyal and C. S. P. Ojha, “Robust Weighted Re-gression as a Downscaling Tool in Temperature Projec-tions,” International Journal of Global Warming. http:// www.inderscience.com/browse/index.php?journalID=331 &action=coming
[5]	R. L. Wilby, “Modelling Low-Frequency Rainfall Events Using Airflow Indices, Weather Patterns and Frontal Frequencies,” Journal of Hydrology, Vol. 213, No.1-4, 1998, pp. 380-392.
[6]	A. J. Cannon and P. H. Whitfield, “Downscaling Recent Streamflow Conditions in British Columbia, Canada Using Ensemble Neural Network Models,” Journal of Hydrology, Vol. 259, No. 1, 2002, pp. 136-151.
[7]	S. Tripathi, V. V. Srinivas and R. S. Nanjundiah, “Downscaling of Precipitation for Climate Change Sce-narios: A Support Vector Machine Approach,” Journal of Hydrology, Vol. 330, No. 3-4, 2006, pp. 621-640.
[8]	S. Ghosh and P. P. Mujumdar, “Statistical Downscaling of GCM Simulations to Streamflow Using Relevance Vector Machine,” Advances in Water Resources, Vol. 31, No. 1, 2008, pp. 132-146.
[9]	E. Kalnay, et al., “The NCEP/NCAR 40-Year Reanalysis Project,” Bulletin of the American Meteorological Society, Vol. 77, No. 3, 1996, pp. 437-471.
[10]	S. D. Khobragade, “Studies on Evaporation from Open Water Surfaces in Tropical Climate,” PhD Dissertation, Indian Institute of Technology, Roorkee, 2009.
[11]	K. Bergant and L. K. Bogataj, “N-PLS Regression as Empirical Downscaling Tool in Climate Change Studies,” Theoretical and Applied Climatology, Vol. 81, No. 1-2, 2005, pp. 11-23.
[12]	R. Manne, “Analysis of Two Partial Least Squares Algo-rithms for Multivariate Calibration,” Chemometrics and Intelligent Laboratory Systems, Vol. 2, No. 1, 1987, pp. 187-197.
[13]	W. Svante, M. Sjostrom and L. Eriksson, “PLS-Regre- ssion: A Basic Tool of Chemometric,” Chemometrics and Intelligent Laboratory Systems, Vol. 58, No. 2, 2001, pp. 109-130.
[14]	B. C. Hewitson and R. G. Crane, “Climate Downscaling: Techniques and Application,” Climate Research, Vol. 7, 1996, pp. 85-95.
[15]	I. G. Chong and C. H. Jun, “Performance of Some Varia-ble Selection Methods When Multicollinearity is Present,” Chemometrics and Intelligent Laboratory Systems, Vol. 78, No. 1-2, 2005, pp. 103-112.
[16]	L. Eriksson, E. Johansson, N. Kettaneh-Wold and S. Wold, Multi- and Megavariate Data Analysis: Principles and Applications, Umetrics Academy, Ume?, 2001.
[17]	A. Anandhi, V. V. Srinivas, D. N. Kumar, R. S. Nanjun-diah, “Role of Predictors in Downscaling Surface Tem-perature to River Basin in India for IPCC SRES Scenarios Using Support Vector Machine,” International Journal of Climatology, Vol. 29, No. 4, 2009, pp. 583-603.