Advertisement

Support Vector Regression to Downscaling Climate Big Data: An Application for Precipitation and Temperature Future Projection Assessment

  • Stalin Jimenez
  • Alex AvilesEmail author
  • Luciano Galán
  • Andrés Flores
  • Carlos Matovelle
  • Cristian Vintimilla
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1099)

Abstract

The techniques for downscaling climatic variables are essential to support tools for water resources planning and management in a climate change context in the entire world. Support vector machines (SVM) through regression approach (SVR), constitute an artificial intelligence method to downscaling climatic variables. Since that statistical downscaling based on regression methodologies is susceptible to the predictor variables, the aim of this study was exploring a big database of predictor variables to achieve the best performance of a statistical downscaling model using SVR to predict precipitation and temperature future projections. Data from regional climate models of Ecuador and information of three meteorological stations was used to apply this approach in the Tomebamba river sub-basin, located in southern Ecuadorian Andean region. The results show that the downscaling model has a better performance with the climatic averages. The precipitation extremes do not estimate in a good manner, but the model achieves an effective behavior with the temperature extremes values. These results could serve to improve water balance projections in the future for formulating suitable measures for climate change decision-making.

Keywords

Artificial intelligence SVR Statistical downscaling Climate change Climate big data Andean basin 

Notes

Acknowledgments

The authors would like to thank the MAE and INAMHI for the information provided.

Funding

This research was funded by the Ecuadorian Corporation for the Development of Research and Academia (CEDIA) and the University of Cuenca through its Research Department (DIUC) via project “Evaluación de los efectos de las actividades socioeconómicas en el cambio del uso del suelo y del cambio climático en las amenazas a inundaciones y sequías en la cuenca del río Tomebamba”.

References

  1. 1.
    Aksornsingchai, P., Srinilta, C.: Statistical Downscaling for Rainfall and Temperature Prediction in Thailand (2011)Google Scholar
  2. 2.
    Ali, S.: Assessment of climate extremes in future projections downscaled by multiple statistical downscaling methods over Pakistan. Atmos. Res. (2019).  https://doi.org/10.1016/j.atmosres.2019.02.009CrossRefGoogle Scholar
  3. 3.
    Anandhi, A.: Downscaling precipitation to river basin in India for IPCC SRES scenarios using support vector machine. Int. J. Climatol. (2008).  https://doi.org/10.1002/joc.1529CrossRefGoogle Scholar
  4. 4.
    Auria, L., Moro, R.A.: Support Vector Machines (SVM) as a Technique for Solvency Analysis (2009).  https://doi.org/10.2139/ssrn.1424949
  5. 5.
    Buytaert, W.: Uncertainties in climate change projections and regional downscaling: implications for water resources management. Hydrol. Earth Syst. Sci. Discuss. 7(2), 1821–1848 (2010).  https://doi.org/10.5194/hessd-7-1821-2010CrossRefGoogle Scholar
  6. 6.
    Camus, P.: Statistical downscaling of seasonal wave forecasts. Ocean Model. (2019).  https://doi.org/10.1016/j.ocemod.2019.04.001CrossRefGoogle Scholar
  7. 7.
    Danandeh Mehr, A., Kahya, E.: Grid-based performance evaluation of GCM-RCM combinations for rainfall reproduction. Theor. Appl. Climatol. 129(1–2), 47–57 (2017).  https://doi.org/10.1007/s00704-016-1758-1CrossRefGoogle Scholar
  8. 8.
    Dosio, A., Paruolo, P.: Bias correction of the ENSEMBLES high-resolution climate change projections for use by impact models: evaluation on the present climate. J. Geophys. Res. Atmos. 116(16), 1–22 (2011).  https://doi.org/10.1029/2011JD015934CrossRefGoogle Scholar
  9. 9.
    Duhan, D., Pandey, A.: Statistical downscaling of temperature using three techniques in the Tons River basin in Central India. Theor. Appl. Climatol. (2015).  https://doi.org/10.1007/s00704-014-1253-5CrossRefGoogle Scholar
  10. 10.
    Dzakiyullah, N.R.: Comparison neural network and support vector machine for production quantity prediction. Adv. Sci. Lett. (2014).  https://doi.org/10.1166/asl.2014.5708CrossRefGoogle Scholar
  11. 11.
    Ministerio del Ambiente del Ecuador: Tercera Comunicación Nacional del Ecuador a la Convención Marco de las Naciones Unidas sobre el Cambio Climático (2017)Google Scholar
  12. 12.
    Bin Farhan, S.: Assessing the impacts of climate change on the high altitude snow- and glacier-fed hydrological regimes of Astore and Hunza, the sub-catchments of Upper Indus Basin. J. Water Clim. Chang. (2018).  https://doi.org/10.2166/wcc.2018.107CrossRefGoogle Scholar
  13. 13.
    Firebug: r - Meaning of Epsilon in SVM regression - cross validated. https://stats.stackexchange.com/questions/259018/meaning-of-epsilon-in-svm-regression
  14. 14.
    Fu, G.: Uncertainties of statistical downscaling from predictor selection: equifinality and transferability. Atmos. Res. (2018).  https://doi.org/10.1016/j.atmosres.2017.12.008CrossRefGoogle Scholar
  15. 15.
    Ghosh, S.: SVM-PGSL coupled approach for statistical downscaling to predict rainfall from GCM output. J. Geophys. Res. Atmos. (2010).  https://doi.org/10.1029/2009JD013548CrossRefGoogle Scholar
  16. 16.
    Goly, A., Teegavarapu, R.S.V.: Assessment of various statistical downscaling methods for downscaling precipitation in Florida. In: World Environmental and Water Resources Congress 2013, pp. 1086–1098. American Society of Civil Engineers, Reston (2013).  https://doi.org/10.1061/9780784412947.105
  17. 17.
    Gudmundsson, L. et al.: Technical note: downscaling RCM precipitation to the station scale using statistical transformations & ndash; a comparison of methods. Hydrol. Earth Syst. Sci. (2012).  https://doi.org/10.5194/hess-16-3383-2012
  18. 18.
    Hanel, M., et al.: Evaluation of simple statistical downscaling methods for monthly regional climate model simulations with respect to the estimated changes in runoff in the Czech Republic. Water Resour. Manag. (2013).  https://doi.org/10.1007/s11269-013-0466-1CrossRefGoogle Scholar
  19. 19.
    Hua, C., et al.: Downscaling GCMs using the smooth support vector machine method to predict daily precipitation in the Hanjiang Basin: downscaling GCMs using the smooth support vector machine method to predict daily precipitation in the Hanjiang. Adv. Atmos. Sci. 27(2), 274–284 (2010).  https://doi.org/10.1007/s00376-009-8071-1CrossRefGoogle Scholar
  20. 20.
    Laflamme, E.M., et al.: Statistical downscaling of regional climate model output to achieve projections of precipitation extremes. Weather Clim. Extrem. (2015).  https://doi.org/10.1016/j.wace.2015.12.001CrossRefGoogle Scholar
  21. 21.
    Leander, R., Buishand, T.A.: Resampling of regional climate model output for the simulation of extreme river flows. J. Hydrol. (2007).  https://doi.org/10.1016/j.jhydrol.2006.08.006CrossRefGoogle Scholar
  22. 22.
    Manzanas, R.: Dynamical and statistical downscaling of seasonal temperature forecasts in Europe: added value for user applications. Clim. Serv. (2018).  https://doi.org/10.1016/j.cliser.2017.06.004CrossRefGoogle Scholar
  23. 23.
    Maurer, E.P., Hidalgo, H.G.: Utility of daily vs. monthly large-scale climate data: an intercomparison of two statistical downscaling methods. Hydrol. Earth Syst. Sci. (2008).  https://doi.org/10.5194/hess-12-551-2008CrossRefGoogle Scholar
  24. 24.
    McCarthy, J., et al.: IPCC Climate Change: Impacts, Adaptation and Vulnerability. Contribution of Working Group II to the Third Assessment Report of the Inter-governmental Panel on Climate Change (2001)Google Scholar
  25. 25.
    Mehrvand, M., et al.: AI-based (ANN and SVM) statistical downscaling methods for precipitation estimation under climate change scenarios (2017)Google Scholar
  26. 26.
    Miel, S.: What is the intuition behind the Cost and Gamma parameters in SVM? – Quora. https://www.quora.com/What-is-the-intuition-behind-the-Cost-and-Gamma-parameters-in-SVM
  27. 27.
    Morán-Tejeda, E.: The changing roles of temperature and precipitation on snowpack variability in Switzerland as a function of altitude. Geophys. Res. Lett. 40(10), 2131–2136 (2013).  https://doi.org/10.1002/grl.50463CrossRefGoogle Scholar
  28. 28.
    Ohmura, A.: Enhanced temperature variability in high-altitude climate change. Theor. Appl. Climatol. 110(4), 499–508 (2012).  https://doi.org/10.1007/s00704-012-0687-xCrossRefGoogle Scholar
  29. 29.
    Pal, J.S., et al.: Regional climate modeling for the developing world: the ICTP RegCM3 and RegCNET. Bull. Am. Meteorol. Soc. (2007).  https://doi.org/10.1175/BAMS-88-9-1395CrossRefGoogle Scholar
  30. 30.
    Patz, J.A., et al.: Impact of regional climate change on human health (2005).  https://doi.org/10.1038/nature04188CrossRefGoogle Scholar
  31. 31.
    Piani, C.: Statistical bias correction for daily precipitation in regional climate models over Europe. Theor. Appl. Climatol. (2010).  https://doi.org/10.1007/s00704-009-0134-9CrossRefGoogle Scholar
  32. 32.
    Pounds, J.A.: Biological response to climate change on a tropical mountain. Nature 398(6728), 611–615 (1999).  https://doi.org/10.1038/19297CrossRefGoogle Scholar
  33. 33.
    Prudhomme, C., Nick Reynard, S.C.: Downscaling of global climate models for flood frequency analysis: where are we now? Hydrol. Process. (2002).  https://doi.org/10.1002/hyp.1054CrossRefGoogle Scholar
  34. 34.
    Revadekar, J.V.: Impact of altitude and latitude on changes in temperature extremes over South Asia during 1971–2000. Int. J. Climatol. 33(1), 199–209 (2013).  https://doi.org/10.1002/joc.3418CrossRefGoogle Scholar
  35. 35.
    Sachindra, D.A.: Statistical downscaling of precipitation using machine learning techniques. Atmos. Res. (2018).  https://doi.org/10.1016/j.atmosres.2018.05.022CrossRefGoogle Scholar
  36. 36.
    Sayad, S.: Support Vector Machine - Regression (SVR). https://www.saedsayad.com/support_vector_machine_reg.htm
  37. 37.
    Souvignet, M., Heinrich, J.: Statistical downscaling in the arid central Andes: uncertainty analysis of multi-model simulated temperature and precipitation. Theor. Appl. Climatol. 106(1–2), 229–244 (2011).  https://doi.org/10.1007/s00704-011-0430-zCrossRefGoogle Scholar
  38. 38.
    Sunyer, M.A., et al.: A comparison of different regional climate models and statistical downscaling methods for extreme rainfall estimation under climate change. In: Rainfall in the Urban Context: Forecasting, Risk and Climate Change (2012).  https://doi.org/10.1016/j.atmosres.2011.06.011CrossRefGoogle Scholar
  39. 39.
    Sunyer, M.A.: Inter-comparison of statistical downscaling methods for projection of extreme precipitation in Europe. Hydrol. Earth Syst. Sci. Discuss. 11(6), 6167–6214 (2014).  https://doi.org/10.5194/hessd-11-6167-2014CrossRefGoogle Scholar
  40. 40.
    Vandal, T., et al.: Intercomparison of machine learning methods for statistical downscaling: the case of daily and extreme precipitation, file, Kodra, Ganguly - 2018 - Intercomparison of machine learning methods for statistical downscaling the case of daily and extreme pr.pdf (2018).  https://doi.org/10.1007/s00704-018-2613-3CrossRefGoogle Scholar
  41. 41.
    Yang, C.: A comparison of three predictor selection methods for statistical downscaling. Int. J. Climatol. (2017).  https://doi.org/10.1002/joc.4772CrossRefGoogle Scholar
  42. 42.
    Yang, C., et al.: Performance comparison of three predictor selection methods for statistical downscaling of daily precipitation. Theor. Appl. Climatol. 131(1–2), 43–54 (2018).  https://doi.org/10.1007/s00704-016-1956-xCrossRefGoogle Scholar
  43. 43.
    Zhang, Q., et al.: A new statistical downscaling approach for global evaluation of the CMIP5 precipitation outputs: model development and application. Sci. Total Environ. (2019).  https://doi.org/10.1016/j.scitotenv.2019.06.310CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Stalin Jimenez
    • 1
  • Alex Aviles
    • 1
    Email author
  • Luciano Galán
    • 1
  • Andrés Flores
    • 1
  • Carlos Matovelle
    • 2
  • Cristian Vintimilla
    • 3
  1. 1.Carrera de Ingeniería Ambiental, Facultad de Ciencias QuímicasUniversidad de CuencaCuencaEcuador
  2. 2.Carrera de Ingeniería AmbientalUniversidad Católica de CuencaCuencaEcuador
  3. 3.Carrera de Ingeniería CivilUniversidad Católica de CuencaAzoguesEcuador

Personalised recommendations