Skip to main content

Advertisement

Springer Nature Link
Log in

Evaluation of machine learning tools as a statistical downscaling tool: temperatures projections for multi-stations for Thames River Basin, Canada

  • Original Paper
  • Published:
Theoretical and Applied Climatology Aims and scope Submit manuscript

Abstract

Many impact studies require climate change information at a finer resolution than that provided by global climate models (GCMs). This paper investigates the performances of existing state-of-the-art rule induction and tree algorithms, namely single conjunctive rule learner, decision table, M5 model tree, and REPTree, and explores the impact of climate change on maximum and minimum temperatures (i.e., predictands) of 14 meteorological stations in the Upper Thames River Basin, Ontario, Canada. The data used for evaluation were large-scale predictor variables, extracted from National Centers for Environmental Prediction/National Center for Atmospheric Research reanalysis dataset and the simulations from third generation Canadian coupled global climate model. Data for four grid points covering the study region were used for developing the downscaling model. M5 model tree algorithm was found to yield better performance among all other learning techniques explored in the present study. Hence, this technique was applied to project predictands generated from GCM using three scenarios (A1B, A2, and B1) for the periods (2046–2065 and 2081–2100). A simple multiplicative shift was used for correcting predictand values. The potential of the downscaling models in simulating predictands was evaluated, and downscaling results reveal that the proposed downscaling model can reproduce local daily predictands from large-scale weather variables. Trend of projected maximum and minimum temperatures was studied for historical as well as downscaled values using GCM and scenario uncertainty. There is likely an increasing trend for T max and T min for A1B, A2, and B1 scenarios while decreasing trend has been observed for B1 scenarios during 2081–2100.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

Explore related subjects

Discover the latest articles and news from researchers in related subjects, suggested using machine learning.

References

  • Amor VMI, James WH (2006) Bias correction of daily GCM rainfall for crop simulation studies. Agric For Meteorol 138:44–53

    Article  Google Scholar 

  • Anandhi A, Srinivas VV, Kumar DN, Nanjundiah RS (2009) Role of predictors in downscaling surface temperature to river basin in India for IPCC SRES scenarios using support vector machine. Int J Climatol 29:583–603

    Article  Google Scholar 

  • Arora M, Goel NK, Singh P (2005) Evaluation of temperature trends over India. Hydrol Sci J 50(1):1–93

    Article  Google Scholar 

  • Bardossy A, Bogardi I, Matyasovszky I (2005) Fuzzy rule-based downscaling of precipitation. Theor Appl Climatol 82:119–129

    Article  Google Scholar 

  • Bhattacharya B, Solomatine DP (2005) Neural networks and M5 model trees in modelling water level–discharge relationship. Neurocomputing 63:381–396

    Article  Google Scholar 

  • Bhattacharya B, Price RK, Solomatine DP (2007) Machine learning approach to modeling sediment transport. J Hydraul Eng 133(4):440–450

    Article  Google Scholar 

  • Breiman L (1984) Classification and regression trees. Chapman & Hall/CRC, Boca Raton, p 368

    Google Scholar 

  • Burn HB, Hag Elnur MA (2002) Detection of hydrologic trends and variability. J Hydrol 255:107–122

    Article  Google Scholar 

  • Cannon AJ (2011) Quantile regression neural networks: implementation in R and application to precipitation downscaling. Comput Geosci 37:1277–1284

    Article  Google Scholar 

  • Cannon AJ, Lord ER (2000) Forecasting summertime surface-level ozone concentrations in the Lower Fraser Valley of British Columbia. An ensemble neural network approach. J Air Waste Manage Assoc 50:322–339

    Article  Google Scholar 

  • Cannon AJ, Whitfield PH (2002) Downscaling recent streamflow conditions in British Columbia, Canada using ensemble neural network models. J Hydrol 259:136–151

    Article  Google Scholar 

  • Chu JT, Xia J, Xu CY, Singh VP (2010) Statistical downscaling of daily mean temperature, pan evaporation and precipitation for climate change scenarios in Haihe River, China. Theor Appl Climatol 99:149–161

    Article  Google Scholar 

  • Clark P, Niblett T (1989) The CN2 rule induction algorithm. Mach Learn 3:261–284

    Google Scholar 

  • Cohen W (1995) Fast effective rule induction. In: Proceedings 12th International Conference on Machine Learning. Morgan Kaufmann, San Francisco, pp 115–123

  • Conway D, Wilby RL, Jones PD (1996) Precipitation and air flow indices over the British Isles. Clim Res 7:169–183

    Article  Google Scholar 

  • Coulibaly P (2004) Downscaling daily extreme temperatures with genetic programming. Geophys Res Lett 31:L16203. doi:10.1029/2004GL020075

    Article  Google Scholar 

  • Coulibaly P, Dibike YB, Anctil F (2005) Downscaling precipitation and temperature with temporal neural networks. J Hydrometeorol 6(4):483–496

    Article  Google Scholar 

  • Daud MNR, Corne DW (2007) Human readable rule induction in medical data mining: a survey of existing algorithms. In: WSEAS European Computing Conference, 2007, Athens, Greece

  • Douglas EM, Vogel RM, Kroll CN (2000) Trends in floods and low flows in the United States: impact of spatial correlation. J Hydrol 240:90–105

    Article  Google Scholar 

  • Dubrovsky M, Buchtele J, Zalud Z (2004) High-frequency and low frequency variability in stochastic daily weather generator and its effect on agricultural and hydrologic modelling. Clim Chang 63:145–179

    Article  Google Scholar 

  • Shahidi AE, Mahjoobi J (2009) Comparison between M5 model tree and neural networks for prediction of significant wave height in Lake Superior. Ocean Eng 36:1175–1181

    Article  Google Scholar 

  • Fowler HJ, Wilby RL (2007) Beyond the downscaling comparison study. Int J Climatol 27:1543–1545

    Article  Google Scholar 

  • Fowler HJ, Kilsby CG, O’Connell PE (2000) A stochastic rainfall model for the assessment of regional water resource systems under changed climatic conditions. Hydrol Earth Syst Sci 4:261–280

    Article  Google Scholar 

  • Fowler HJ, Blenkinsop S, Tebaldi C (2007) Linking climate change modelling to impacts studies: recent advances in downscaling techniques for hydrological modelling. Int J Climatol 27:1547–1578

    Article  Google Scholar 

  • Gachon P, Dibike Y (2007) Temperature change signals in northern Canada: convergence of statistical downscaling results using two driving GCMs. Int J Climatol 27:1623–1641

    Article  Google Scholar 

  • Gangopadhyay SM, Clark B, Rajagopalan (2005) Statistical downscaling using K-nearest neighbors. Water Resour Res 41:W02024. doi:10.1029/2004WR003444

    Article  Google Scholar 

  • Gardner MW, Dorling SR (1998) Artificial neural networks (the multi layer perceptron)—a review of applications in the atmospheric sciences. Atmos Environ 32:2627–2636

    Article  Google Scholar 

  • Giorgi F, Hewitson BC (2001) Regional climate information—evaluation and projections. In: Houghton JT, Ding Y, Griggs DJ, Noguer M, van der Linden PJ, Dia X, Maskell K, Johnson CA (eds) Climate change 2001: the scientific basis. Cambridge University Press, Cambridge

    Google Scholar 

  • Goodess CM, Palutikof J (1998) Development of daily rainfall scenarios for southeast Spain using a circulation-type approach to downscaling. Int J Climatol 18:1051–1083

    Article  Google Scholar 

  • Grotch SL, MacCracken MC (1991) The use of general circulation models to predict regional climatic change. J Clim 4:286–303

    Article  Google Scholar 

  • Goyal MK and Ojha CSP (2010a) Robust Weighted Regression As A Downscaling Tool In Temperature Projections International Journal of Global Warming, Interscience Publishers, UK, 2(3):234–251

    Google Scholar 

  • Goyal MK and Ojha CSP (2010b) Evaluation of Various Linear Regression Methods for Downscaling of Mean Monthly Precipitation in Arid Pichola Watershed Natural Resources, Scientific Research, USA, 1(1):11–18 doi:10.4236/nr.2010.11002

    Google Scholar 

  • Goyal MK and Ojha CSP (2010c) Application of PLS-Regression as downscaling tool for Pichola lake basin in India International Journal of Geosciences, Scientific Research, USA 1:51–57, doi:10.4236/ijg.2010.12007

    Google Scholar 

  • Goyal MK, Ojha CSP and Burn DH (2011) Nonparametric Statistical Downscaling of Temperature, Precipitation and Evaporation for Semi-Arid Region in India, ASCE-Journal of Hydrologic Engg. doi:10.1061/(ASCE)HE.1943-5584.0000479

    Google Scholar 

  • Goyal MK and Ojha CSP (2011a) PLS regression based Pan evaporation and Minimum-Maximum Temperature projections for an arid lake basin in India Theoretical and Applied Climatology, Springer Netherlands, 105(3):403–415. doi:10.1007/s00704-011-0406-z

    Google Scholar 

  • Goyal MK and Ojha CSP (2011b) Downscaling of Surface Temperature for Lake Catchment in Arid Region in India using Linear Multiple Regression and Neural Networks International Journal of Climatology, John Wiley & Sons. doi:10.1002/joc.2286

    Google Scholar 

  • Goyal MK and Ojha CSP (2011c) Evaluation of Linear Regression Methods As Downscaling Tool in Temperature Projections Over Pichola lake Basin in India Hydrological Processes, John Wiley & Sons, 25(9):1453–1465. doi:10.1002/hyp.7911

    Google Scholar 

  • Goyal MK and Ojha CSP (2011d) Estimation of Scour Downstream of a Ski—Jump Bucket Using Support Vector and M5 Model Tree, Water Resources Management, Springer Netherlands, 25(9):2177–2195. doi:10.1007/s11269-011-9801-6

    Google Scholar 

  • Goyal MK and Ojha CSP (2011e) Downscaling of Precipitation on a Lake Basin: Evaluation of Rule and Decision Tree Induction Algorithms, Hydrology Research vol. 43 (In Press).

  • Hessami M, Gachon P, Ouarda Taha BMJ, St-Hilaire A (2008) Automated regression-based statistical downscaling tool. Environ Model Softw 23(6):813–834

    Article  Google Scholar 

  • Hewitson BC, Crane RG (eds) (1994) Neural nets applications in geography. Kluwer Academic, Dordrecht

    Google Scholar 

  • Heyen H, Zorita E, von Storch H (1996) Statistical downscaling of monthly mean North Atlantic air-pressure to sea level anomalies in the Baltic Sea. Tellus 48A:312–323

    Google Scholar 

  • Huth R (2004) Sensitivity of local daily temperature change estimates to the selection of downscaling models and predictors. J Clim 17:640–652

    Article  Google Scholar 

  • Ibrahim F, Abu Osman NA, Usman J, Kadri NA (eds) (2006) Biomed 06, IFMBE Proceedings 15: 520–523, 2007

    Google Scholar 

  • Intergovernmental Panel on Climate Change (IPCC) (2007) Climate change 2007—the physical science basis. Contribution of Working Group I to the Fourth Assessment Report of the Intergovernmental Panel on Climate Change. In: Solomon S, Qin D, Manning M, Marquis M, Averyt K, Tignor MMB, Miller HLR Jr, Chen Z (eds). Cambridge University Press, Cambridge. IPCC Data Distribution Centre (DDC). http://www.mad.zmaw.de/IPCC_DDC/html/ddc_gcmdata.html

  • IPCC (2001) In: Houghton JT et al (eds) The scientific basis. Contribution of WGI to the Third Assessment Report of the Intergovernmental panel on Climate Change. Cambridge University Press, Cambridge, p 881

    Google Scholar 

  • Kalnay E, Kanamitsu M, Kistler R, Collins W, Deaven D, Gandin L, Iredell M, Saha S, White G, Woollen J, Zhu Y, Chelliah M, Ebisuzaki W, Higgins W, Janowiak J, Mo KC, Ropelewski C, Wang J, Leetmaa A, Reynolds R, Jenne R, Joseph D (1996) The NCEP/NCAR 40-year reanalysis project. Bull Am Meteorol Soc 77(3):437–471

    Article  Google Scholar 

  • Kang HW, An KH, Park CK, Solis ALS, Stitthichivapak K (2007) Multimodel output statistical downscaling prediction of precipitation in the Philippines and Thailand. Geophys Res Lett 34:L15710. doi:10.1029/2007GL030730

    Article  Google Scholar 

  • Kendall MG (1975) Rank correlation methods. Charles Griffin, London, p 202

    Google Scholar 

  • Kilsby CG, Cowpertwait PSP, O’Connell PE, Jones PD (1998) Predicting rainfall statistics in England and Wales using atmospheric circulation variables. Int J Climatol 18:523–539

    Article  Google Scholar 

  • King L, Solaiman T, Simonovic SP (2009) Assessment of climatic vulnerability in the Upper Thames River Basin. Water Resources Research Report no. 064. Facility for Intelligent Decision Support, Department of Civil and Environmental Engineering, London, p 62

  • Kite GW (1997) Simulating Columbia river flows with data from regional-scale climate models. Water Resour Res 33(6):1275–1285

    Article  Google Scholar 

  • Kohavi R (1995) The power of decision tables. In: Machine learning, pp 174–189

  • Mann HB (1945) Nonparametric tests against trend. Econometrica 13:245–259

    Article  Google Scholar 

  • Mason SJ (2004) Simulating climate over Western North America using stochastic weather generators. Clim Chang 62:155–187

    Article  Google Scholar 

  • Nilsson JN (1999) Introduction to machine learning. California, United Stated of Americas

  • Ojha CSP., Goyal MK and Adeloye AJ (2010) Downscaling of Precipitation for Lake Catchment in Arid Region in India using Linear Multiple Regression and Neural Networks The Open Journal of Hydrology, Bentham Science Publishers, 2010, 4, 122–136.

    Google Scholar 

  • Othman MFb, Moh TSY (2007) Comparison of different classification techniques using WEKA for breast cancer. Biomed 06: IFMBE proceedings 15, pp 520–523

  • Prodanovic P, Simonovic SP (2007) Integrated water resources modelling of the Upper Thames River Basin. In: 18th Canadian Hydrotechnical Conference—Challenges for Water Resources Engineering in a Changing World, Winnipeg, Manitoba, August 22–24

  • Quinlan JR (1992) Learning with continuous classes. In: Proc. of the Fifth Australian Joint Conference on Artificial Intelligence. World Scientific, Singapore, pp 343–348

  • Quinlan JR (1996) Improved use of continuous attributes in C4.5. J Artif Intell Res 4:77–90

    Google Scholar 

  • Salathé EP Jr (2003) Comparison of various precipitation downscaling methods for the simulation of streamflow in a rainshadow river basin. Int J Climatol 23:887–901

    Article  Google Scholar 

  • Salathé EP Jr, Mote Philip W, Wiley Matthew W (2007) Review of scenario selection and downscaling methods for the assessment of climate change impacts on hydrology in the United States pacific northwest. Int J Climatol 27:1611–1621

    Article  Google Scholar 

  • Schoof JT, Pryor SC (2001) Downscaling temperature and precipitation: a comparison of regression-based methods and artificial neural networks. Int J Climatol 21:773–790

    Article  Google Scholar 

  • Senthil kumar AR, Ojha CSP, Goyal MK, Singh RD, Swamee PK (2011), Modelling of Suspended Sediment Concentration at Kasol in India using ANN, Fuzzy Logic and Decision Tree Algorithms, ASCE's Journal of Hydrologic Engineering. doi:10.1061/(ASCE)HE.1943-5584.0000445

  • Shannon DA, Hewitson BC (1996) Cross-scale relationships regarding local temperature inversions at Cape Town and global climate change implications. S Afr J Sci 92(4):213–216

    Google Scholar 

  • Sharif M, Burn DH (2006) Simulating climate change scenarios using an improved K-nearest neighbor model. J Hydrol 325:179–196

    Article  Google Scholar 

  • Sharif M, Burn DH (2007) An improved K-nearest neighbor weather generating model. J Hydrol Eng 12(1):42–51

    Article  Google Scholar 

  • Solaiman T, Simonovic SP (2010) Assessing NCEP–NCAR hydroclimatic data for macroscale hydrologic modelling in South-Western Ontario, Canada. Can J Civ Eng 37:611–623

    Article  Google Scholar 

  • Solomatine DP, Xue Y (2004) M5 model trees and neural networks: application to flood forecasting in the upper reach of the Huai River in China. J Hydrol Eng 9(6):491–501

    Article  Google Scholar 

  • Solomatine DP, Dulal KN (2003) Model tree as an alternative to neural network in rainfall–runoff modelling. Hydrol Sci J 48(3):399–411

    Article  Google Scholar 

  • Tripathi S, Srinivas VV, Nanjundiah RS (2006) Downscaling of precipitation for climate change scenarios: a support vector machine approach. J Hydrol 330(3–4):621–640

    Article  Google Scholar 

  • Wang Y, Witten IH (1997) Induction of model trees for predicting continuous lasses. In: Proceedings of the Poster Papers of the European Conference on Machine Learning. University of Economics, Faculty of Informatics and Statistics, Prague

  • Wang YQ, Leung LR, Mcgregor JL, Wang WC, Ding YH, Kimura F (2004) Regional climate modeling: progress, challenges, and prospects. J Meteorol Soc Jpn 82(6):1599–1628

    Article  Google Scholar 

  • Wetterhall F, Halldin S, Xu C-Y (2005) Statistical precipitation downscaling in central Sweden with the analogue method. J Hydrol 306:174–190

    Article  Google Scholar 

  • Wilby RL, Harris I (2006) A framework for assessing uncertainties in climate change impacts: low-flow scenarios. Water Resour Res 42:W02419. doi:10.1029/2005WR004065

    Article  Google Scholar 

  • Wilby RL, Wigley TML (1997) Downscaling general circulation model output: a review of methods and limitations. Prog Phys Geogr 21:530–548

    Article  Google Scholar 

  • Wilby RL, Wigley TME (2000) Precipitation predictors for downscaling: observed and general circulation model relationships. Int J Climatol 20:641–661

    Article  Google Scholar 

  • Wilby RL, Wigley TML, Conway D, Jones PD, Hewitson BC, Main J, Wilks DS (1998) Statistical downscaling of general circulation model output: a comparison of methods. Water Resour Res 34:2995–3008

    Article  Google Scholar 

  • Wilby RL, Charles SP, Zorita E, Timbal B, Whetton P, Mearns LO (2004) Guidelines for use of climate scenarios developed from statistical downscaling methods, available from the DDC of IPCC TGCIA, p 27. Available from: IPCC-DDC: http://www.ipcc-data.org/

  • Wilks DS (1989) Conditioning stochastic daily precipitation models on total monthly precipitation. Water Resour Res 25(6):1429–1439

    Article  Google Scholar 

  • Willmott CJ, Rowe CM, Philpot WD (1985) Small-scale climate map: a sensitivity analysis of some common assumptions associated with the grid-point interpolation and contouring. Am Cartograph 12:5–16

    Article  Google Scholar 

  • Witten IH, Frank E (2005) Data mining: practical machine learning tools and techniques with Java implementations. Morgan Kaufmann, San Francisco

    Google Scholar 

  • Xoplaki E, Luterbacher J, Burkard R, Patrikas I, Maheras P (2000) Connection between the large-scale 500 hPa geopotential height fields and precipitation over Greece during wintertime. Clim Res 14:129–146

    Article  Google Scholar 

  • Xu C-Y (1999) From GCMs to river flow: a review of downscaling methods and hydrologic modelling approaches. Progr Phys Geogr 23(2):229–249

    Google Scholar 

Download references

Acknowledgments

This work was made possible through a Canadian Commonwealth Scholarship program, awarded to the first author from the Canadian Bureau for International Education to pursue research at University of Waterloo, Waterloo, ON, Canada.

Author information

Author notes

  1. Manish Kumar Goyal

    Present address: Department of Civil and Environmental Engineering, Nanyang Technological University, 637332, Singapore, Singapore

Authors and Affiliations

  1. Department of Civil and Environmental Engineering, University of Waterloo, Waterloo, ON, N2L3G1, Canada

    Manish Kumar Goyal & Donald H. Burn

  2. Department of Civil Engineering, Indian Institute of Technology, Roorkee, India

    Manish Kumar Goyal & C. S. P. Ojha

Authors
  1. Manish Kumar Goyal
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Donald H. Burn
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. C. S. P. Ojha
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Manish Kumar Goyal.

Appendix

Appendix

T max: M5 pruned model tree (using smoothed linear models)

pc1 ≤ 0.303

| pc1 ≤ −5.489: LM1 (990/29.777%)

| pc1 > −5.489: LM2 (1,233/29.451%)

pc1 > 0.303: LM3 (2,161/25.473%)

LM num 1

MaxTemp = 1.9188 × pc1 − 0.3197 × pc2 − 0.7801 × pc3 − 1.3322 × pc4 + 0.0036 × pc5 − 0.9671 × pc6 + 0.9386 × pc7 − 4.2026 × pc8 + 0.0235 × pc9 + 0.005 × pc10 + 12.4731

LM num 2

MaxTemp = 1.8496 × pc1 − 0.4515 × pc2 − 0.7399 × pc3 − 1.2969 × pc4 + 0.4277 × pc5 − 1.0828 × pc6 + 0.815 × pc7 − 2.4603 × pc8 + 1.2959 × pc9 + 0.005 × pc10 + 12.1503

LM num: 3

MaxTemp = 1.8513 × pc1 − 0.5194 × pc2 − 0.6143 × pc3 − 1.6666 × pc4 − 0.4695 × pc5 − 0.5368 × pc6 + 1.4823 × pc7 − 1.4421 × pc8 + 2.4781 × pc9 + 0.6268 × pc10+ 10.9677

Number of rules—3

T min: M5 pruned model tree (using smoothed linear models):

pc1 ≤ 1.317

| pc1 ≤ −5.439

| | pc4 ≤ 0.37: LM1 (498/30.741%)

| | pc4 > 0.37: LM2 (503/36.681%)

| pc1 > −5.439

| | pc1 ≤ −2.22

| | | pc3 ≤ 2.042: LM3 (521/30.204%)

| | | pc3 > 2.042: LM4 (186/40.401%)

| | pc1 > −2.22: LM5 (757/31.316%)

pc1 > 1.317: LM6 (1,919/27.471%)

LM num 1

MaxTemp = 1.9749 × pc1 − 0.1784 × pc2 − 1.1794 × pc3 − 1.3166 × pc4 + 1.3908 × pc5 − 0.0124 × pc6 + 0.0415 × pc7 − 2.9836 × pc8 − 0.017 × pc9 + 0.0171 × pc10 + 6.4099

LM num 2

MaxTemp = 2.815 × pc1 − 0.007 × pc2 − 2.0276 × pc3 − 1.5988 × pc4 + 1.8935 × pc5 − 0.6826 × pc6 + 0.0413 × pc7 − 5.8322 × pc8 − 1.8691 × pc9 + 0.0171 × pc10 + 12.2365

LM num 3

MaxTemp = 1.3874 × pc1 − 0.0965 × pc2 − 0.962 × pc3 − 0.5622 × pc4 + 1.6538 × pc5 − 0.4808 × pc6 + 0.0306 × pc7 − 2.4992 × pc8 − 0.5334 × pc9 + 0.0136 × pc10 + 3.7766

LM num 4

MaxTemp = 1.8142 × pc1 − 0.0157 × pc2 − 1.448 × pc3 − 2.2798 × pc4 + 1.9731 × pc5 − 0.6306 × pc6 + 1.4846 × pc7 − 2.6684 × pc8 − 1.528 × pc9 + 0.0136 × pc10 + 5.4219

LM num 5

MaxTemp = 1.2122 × pc1 − 0.1827 × pc2 − 0.95 × pc3 − 0.7975 × pc4 + 0.8704 × pc5 − 0.2823 × pc6 + 0.816 × pc7 − 1.5892 × pc8 + 0.3301 × pc9 + 0.0136 × pc10 + 3.0578

LM num 6

MaxTemp = 1.3961 × pc1 − 0.1521 × pc2 − 0.7257 × pc3 − 0.8519 × pc4 + 0.3926 × pc5 + 0.7775 × pc7 − 1.0703 × pc8 + 1.2162 × pc9 + 0.39 × pc10 + 2.9588

Number of rules—6

where pc represents principal component.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Goyal, M.K., Burn, D.H. & Ojha, C.S.P. Evaluation of machine learning tools as a statistical downscaling tool: temperatures projections for multi-stations for Thames River Basin, Canada. Theor Appl Climatol 108, 519–534 (2012). https://doi.org/10.1007/s00704-011-0546-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00704-011-0546-1

Keywords