Performance evaluation of artificial neural networks in statistical downscaling of monthly precipitation (Case study: Minab watershed)

Document Type : Research Paper

Authors

1 Ph.D. student, Department of Civil Engineering, University of Sistan and Baluchestan, Zahedan, Iran

2 Associate Professor, Department of Civil Engineering, University of Sistan and Baluchestan, Zahedan, Iran

3 Assistant Professor, Department of Civil Engineering, University of Sistan and Baluchestan, Zahedan, Iran

4 Associate Professor, Faculty of Geography, University of Tehran, Tehran, Iran

Abstract

Assessment of the impacts of climate change on water resources has been obtained
significant attentions in the past decade. This paper assesses the climate change impacts on
precipitation in the Minab basin, in the Hormozgan province in Iran. Two monthly
precipitation downscaling methods were proposed based on multi-layer perceptron (MLP)
and radial basis function (RBF) neural networks. The downscaling models were calibrated
and validated using the large scale climatic parameters (predictors) derived from National
Center for Environmental Prediction (NCEP)/ National Centre for Atmospheric Research
(NCAR) reanalysis data set for downscaling monthly precipitation in the Minab basin in
Iran. Pearson correlation was employed to choose the predictors among the NCEP/ NCAR
reanalysis data set and final predictor combination for each station is assigned. The results
of the downscaling models revealed that the MLP model produced more accurate and
consistent results by downscaling the large scale climatic parameters compared to the RBF
model. The proposed model can be reliably utilized for developing future projections of
precipitation using the general circulation models outputs which can be employed also as
the inputs in hydrological models.

Keywords

References

Abdellatif, M., Atherton, W., Alkhaddar, A., and Osman, Y. 2015. Flood risk assessment for urban water system in a changing climate using artificial neural network. Natural Hazards, 79(2), 1059-1077.
Acharya, N., Shrivastava, N.A., Panigrahi, B.K., and Mohanty, U.C. 2014. Development of an artificial neural network based multi-model ensemble to estimate the northeast monsoon rainfall over south peninsular India: an application of extreme learning machine. Climate Dynamic, 43(5-6), 1303-1310.
Ahmed, K., Shahid, S., Haroon, S.B., and Xiao-jun, W. 2015. Multilayer perceptron neural network for downscaling rainfall in arid region: A case study of Baluchistan, Pakistan. Journal of Earth System Science, 124(6), 1325-1341.
Akbari, M., Ownegh, M., Asgari, H., Sadoddin, A., and Khosravi, H. 2016. Drought Monitoring Based on the SPI and RDI Indices under Climate Change Scenarios (Case Study: Semi-Arid Areas of West Golestan Province). Journal of Ecopersia, 4(4), 1585-1602
Anandhi, A., Srinivas ,V.V., Nanjundiah, R.S., and Kumar, D.N. 2008. Downscaling precipitation to river basin in India for IPCC SRES scenarios using support vector machine. International Journal of Climatology, 28(3), 401-420.
Banerjee, P., Prasad, R.K., and Singh, V.S. 2009. Forecasting of groundwater level in hard rock region using artificial neural network. Environmental Geology, 58(6), 1239-1246. 
Chang, J., Wang, G., and Mao, T. 2015. Simulation and prediction of suprapermafrost groundwater level variation in response to climate change using a neural network model. Journal of Hydrology, 529, 1211–1220.
Chen, S.T., Yu, P.S., and Tang, Y.H. 2010. Statistical downscaling of daily precipitation using support vector machines and multivariate analysis. Journal of Hydrology, 385(1), 13-22.
Christensen, J.H., Carter, T.R., Rummukainen, R., and Amanatidis, G. 2007. Evaluating the performance and utility of regional climate models: the PRUDENCE project. Climate Change, 81(1), 1-6.
Coulibaly, P. 2004. Downscaling daily extreme temperatures with genetic programming. Geophysical Research Letters 31. http://dx.doi.org/10.1029/2004GL020075.
Daliakopoulos, I.N., Coulibaly, P., Tsanis, I.K. 2005. Groundwater level forecasting using artificial neural networks. Journal of Hydrology, 309, 229–240.
Fistikoglu, O., and Okkan, U. 2010. Statistical downscaling of monthly precipitation using NCEP/NCAR reanalysis data for Tahtali River Basin in Turkey. Journal of Hydrologic Engineering, 16(2), 157-164.
Gautam, N. P., Arora, M., and Goel, N.K. 2014. Prediction of Precipitation for Considering Climate Change and GCM Outputs: Satluj River. Journal of Ecopersia, 2(4), 757-765
George, J., Janaki, L., and Gomathy, J.P. 2015. Statistical Downscaling Using Local Polynomial Regression for Rainfall Predictions , A Case Study. Water Resource Management, 30(1), 183-193.
Giorgi, F., Hewitson, B., Christensen, J., Hulme, M., Von Storch, H., Whetton, P., Jones, R., Mearns, L., and Fu, C. 2001. Climate change. The scientific basis, contribution of working group I to the third assessment report of the IPCC. Chapter, 10, 583–638.
Hashmi, M.Z., Shamseldin, A.Y., and Melville, B.W. 2011. Statistical downscaling of watershed precipitation using Gene Expression Programming (GEP). Environmental Modelling and Software, 26(12), 1639-1646.
Haykin, S. 1999. Neural Networks: A Comprehensive Foundation, second ed. Prentice-Hall, Englewood Cliffs. New York.
Hornik, K., and Stinchcombe, M. 1989. White, M., Multilayer feed forward networks are universal approximates. Neural Networks.
Joshi, D., St-Hilaire, A., Ouarda, T., and Daigle, A. 2015. Statistical downscaling of precipitation and temperature using sparse Bayesian learning, multiple linear regression and genetic programming frameworks. Can Water Resource Journal, 40(4), 392-408.
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, K.C., Ropelewski, C., Wang, J., Leetmaa, A., Reynolds, R., Jenne, R., and Joseph, D. 1996. The NCEP/NCAR reanalysis project. Bulletin of the American Meteorological Society, 77, 437–471.
Kang, B., Kim, Y.D., Lee, J.M., and Kim, S.J. 2015. Hydro-environmental Runoff Projection under GCM Scenario Downscaled by Artificial Neural Network in the Namgang Dam Watershed, Korea. KSCE Journal of Civil Engineering, 19(2), 434-44.
Kim, S., and Kim, H.S. 2008. Neural networks and genetic algorithm approach for nonlinear evaporation and evapotranspiration modeling. Journal of . Hydrology, 351, 299–317.
Kourgialas, N.N, Dokou, Z., and Karatzas, G.P. 2015. Statistical analysis and ANN modeling for predicting hydrological extremes under climate change scenarios: The example of a small Mediterranean agro-watershed. Journal of Environmental Management, 154, 86-101.
Levenberg, K.A. 1944. A Method for the solution of certain non-linear problems in least squares. Quarterly of Applied Mathematics, 2, 164–168.
Lin, G.F., Chang, M.J., and Wu, J.T. 2016. A Hybrid Statistical Downscaling Method Based on the Classification of Rainfall Patterns. Water Resource Management. DOI 10.1007/s11269-016-1532-2.
Lua, Y., Qina, X.S., Xie, Y.J. 2016. An integrated statistical and data-driven framework for supporting flood risk analysis under climate change. Journal of Hydrology, 533, 28-39.
Marquardt, D.W. 1963. An algorithm for least-squares estimation of nonlinear parameters. Journal of the Society for Industrial and Applied Mathematics, 11, 431–441.
Mendes, D., and Marengo, J.A. 2010. Temporal downscaling: a comparison between artificial neural network and autocorrelation techniques over the Amazon Basin in present and future climate change scenarios. Theoretical and Applied Climatology, 100: 413–421.
Mohammadian, E., Motamedi, S., Shamshirband, S., Hashim, R., Junin, R., Roy, C., and Azdarpour, A. 2016. Application of extreme learning machine for prediction of aqueous solubility of carbon dioxide.Environmental Earth Sciences, 75, 215-220.
Mohanty, S., Jha, M.K., Kumar, A., and Sudheer, K.P. 2010. Artificial Neural Network Modeling for Groundwater Level Forecasting in a River Island of Eastern India. Water Resources Management.
Murphy J. 1998. An evaluation of statistical and dynamical techniques for downscaling local climate. Int. Journal of Climate, 12, 2256–2284 
Okkan, U., and Inan, G. 2015. Statistical downscaling of monthly reservoir inflows for Kemer watershed in Turkey: use of machine learning methods, multiple GCMs and emission scenarios. International Journal of Climatology, 35, 3274–3295.
Pearson K. 1895. Mathematical contributions to the theory of evolution. iii. Regression heredity and panmixia. Philosophical Transactions of the Royal Society of London Series A, 187, 253–318.
Sachindra, D.A., and Perera, B.J.C. 2016. Annual statistical downscaling of precipitation and evaporation and monthly disaggregation. Theoretical and Applied Climatology. DOI 10.1007/s00704-016-1968-6
Sachindra, D.A., Huang, F., Barton, A., and Perera, B.J.C. 2013. Least square support vector and multi‐ linear regression for statistically downscaling general circulation model outputs to catchment stream flows. International Journal of Climatology, 33(5), 1087-1106.
Sarhadi, A., Burn, D.H., Johnson, F., Mehrotra, R., and Sharma, A. 2016. Water resources climate change projections using supervised nonlinear and multivariate soft computing techniques. Journal of Hydrology, 536, 119-132.
Shenify, M., Danesh, A.S., Gocić, M., Taher, R.S., Wahab, A., Gani, A., Shamshirband, S., and Petković, D. 2016. Precipitation estimation using support vector machine with discrete wavelet transform." Water Resource Management, 30(2), 641-652.
Vernieuwe, H., Georgieva, O., De Baets, B., Pauwels, V.R.N., Verhoest, N.E.C., and Troch, F.P. 2005.
Comparison of data-driven Takagi–Sugeno models of rainfall–discharge dynamics. Journal of Hydrology, 302, 173–186 
Wilby, R.L., Wigley, T.M.L., Conway, D., Jones, P.D., Hewitson, B.C., Main, J., and Wilks, D.S. 1998.
Statistical downscaling of generation circulation model output: a comparison of methods. Water Resources Research, 34, 2995–3008.
Wilby, R.L., Conway, D., and Jones, P.D. 2002. Prospects for downscaling seasonal precipitation variability using conditioned weather generator parameters. Hydrological Processes,16(6), 1215– 1234.
Yang, C., Wang, N., and Wang, S. 2016. A comparison of three predictor selection methods for statistical downscaling. International Journal of Climatology, 2, 1-10
Environmental Resources Research
Volume 5, Issue 2
July 2017
Pages 169-182

Files

Share

How to cite

Statistics