Abstract
Increasing temperature from climate change can bring a number of different risks such as more droughts and heat waves, and increasing sea level rise. Assessment of climate change with future scenarios is essential to adapt these impacts. To provide climate change information through the outputs of general circulation models at finer resolution, a reliable and accurate downscaling model has always been of great interest. Meeting this need, artificial neural network (ANN) has been commonly employed in downscaling for nonlinear models. Extreme learning machine (ELM), a recently developed ANN, is an efficient learning algorithm for generalized single hidden layer feedforward neural networks. In light of its simple learning algorithm, we introduced a useful approach to combine the stepwise feature selection method into ELM for temperature downscaling, as stepwise ELM (SWELM), since model complexity and computational time consumption of a traditional ANN impedes application of stepwise feature selection. This SWELM is able to identify the most influential predictors in a dataset and use them to train a nonlinear model while removing the irrelevant ones. The ELM and SWELM as well as regular ANN were tested in a simulation study. Results indicated that ELM even with randomness of weights and biases in the nodes of input and hidden layers better performed than did ANN. Also, SWELM presents a capability to select the influential predictors and remove the unrelated variables. A case study with downscaling temperature of Wisconsin, USA, showed that ELM was a comparable alternative to ANN. SWELM outperformed the ANN algorithm for temperature downscaling and sometimes predicted the temperature increase larger than did others for future scenarios. The current study of temperature downscaling with the statistical tool allows assessing the possible impacts of climate change in a local scale and some developing countries where sophisticate research cannot be eligible.
Similar content being viewed by others
References
Ahmed K, Shahid S, Harun S, Wang X (2015) Multilayer perceptron neural network for downscaling rainfall in arid region: a case study of Baluchistan, Pakistan. J Earth Syst Sci 124:1325–1341. https://doi.org/10.1007/s12040-015-0602-9
Atiquzzaman M, Kandasamy J (2015) Prediction of hydrological time-series using extreme learning machine. J Hydroinform 18(2):345–353. https://doi.org/10.2166/hydro.2015.020
Balasundaram S, Gupta DD, Gupta K (2014) 1-Norm extreme learning machine for regression and multiclass classification using Newton method. Neurocomputing 128:4–14. https://doi.org/10.1016/j.neucom.2013.03.051
Balbay A, Kaya Y, Sahin O (2012) Drying of black cumin (Nigella sativa) in a microwave assisted drying system and modeling using extreme learning machine. Energy 44(1):352–357. https://doi.org/10.1016/j.energy.2012.06.022
Busuioc A, Tomozeiu R, Cacciamani C (2008) Statistical downscaling model based on canonical correlation analysis for winter extreme precipitation events in the Emilia-Romagna region. Int J Climatol 28(4):449–464. https://doi.org/10.1002/joc.1547
Butcher JB, Verstraeten D, Schrauwen B, Day CR, Haycock PW (2013) Reservoir computing and extreme learning machines for non-linear time-series data analysis. Neural Netw 38:76–89. https://doi.org/10.1016/j.neunet.2012.11.011
Cavazos T, Hewitson B (2005) Performance of NCEP-NCAR reanalysis variables in statistical downscaling of daily precipitation. Clim Res 28:95–107
Chen FL, Ou TY (2011) Sales forecasting system based on Gray extreme learning machine with Taguchi method in retail industry. Expert Syst Appl 38(3):1336–1345. https://doi.org/10.1016/j.eswa.2010.07.014
Chen X, Dong ZY, Meng K, Xu Y, Wong KP, Ngan HW (2012) Electricity price forecasting with extreme learning machine and bootstrapping. IEEE Trans Power Syst 27(4):2055–2062. https://doi.org/10.1109/TPWRS.2012.2190627
Chen ZX, Zhu HY, Wang YG (2013) A modified extreme learning machine with sigmoidal activation functions. Neural Comput Appl 22(3):541–550. https://doi.org/10.1007/s00521-012-0860-2
Chu JT, Xia J, Xu C-Y, Singh VP (2010) Statistical downscaling of daily mean temperature, pan evaporation and precipitation for climate change scenarios in Haihe River, China. Theoret Appl Climatol 99(1):149–161. https://doi.org/10.1007/s00704-009-0129-6
City-Data. http://www.city-data.com/city/Kenosha-Wisconsin.html. Accessed 3 Jan 2019
Deo RC, Şahin M (2015) Application of the extreme learning machine algorithm for the prediction of monthly effective drought index in eastern Australia. Atmos Res 153:512–525. https://doi.org/10.1016/j.atmosres.2014.10.016
Dorji S, Herath S, Mishra BK (2017) Future climate of colombo downscaled with SDSM-neural network. Climate 5(1):24
Eum H-I, Cannon AJ, Murdock TQ (2017) Intercomparison of multiple statistical downscaling methods: multi-criteria model selection for South Korea. Stoch Environ Res Risk Assess 31(3):683–703. https://doi.org/10.1007/s00477-016-1312-9
Gaitan CF, Hsieh WW, Cannon AJ (2014) Comparison of statistically downscaled precipitation in terms of future climate indices and daily variability for southern Ontario and Quebec, Canada. Clim Dyn 43(12):3201–3217. https://doi.org/10.1007/s00382-014-2098-4
Goyal MK, Ojha CSP (2012) Downscaling of surface temperature for lake catchment in an arid region in India using linear multiple regression and neural networks. Int J Climatol 32(4):552–566. https://doi.org/10.1002/joc.2286
Gurney K (1997) An introduction to neural networks. Taylor & Francis Inc, Bristol
Guyon I, Elisseeff A (2003) An introduction to variable and feature selection. J Mach Learn Res 3:1157–1182
Hammami D, Tae SL, Ouarda TBMJ, Lee J (2012) Predictor selection for downscaling GCM data with LASSO. J Geophys Res Atmos. https://doi.org/10.1029/2012jd017864
Hasan DSNAPA, Ratnayake U, Shams S, Nayan ZBH, Rahman EKA (2018) Prediction of climate change in Brunei Darussalam using statistical downscaling model. Theor Appl Climatol 133(1):343–360. https://doi.org/10.1007/s00704-017-2172-z
Hashmi MZ, Shamseldin AY, Melville BW (2011) Comparison of SDSM and LARS-WG for simulation and downscaling of extreme precipitation events in a watershed. Stoch Environ Res Risk Assess 25(4):475–484. https://doi.org/10.1007/s00477-010-0416-x
Hellström C, Chen D, Achberger C, Räisänen J (2001) Comparison of climate change scenarios for Sweden based on statistical and dynamical downscaling of monthly precipitation. Clim Res 19:45–55. https://doi.org/10.3354/cr019045
Hertig E, Jacobeit J (2008) Downscaling future climate change: temperature scenarios for the Mediterranean area. Global Planet Change 63(2):127–131. https://doi.org/10.1016/j.gloplacha.2007.09.003
Hessami M, Gachon P, Ouarda T, St-Hilaire A (2008) Automated regression-based statistical downscaling tool. Environ Model Soft 23(6):813–834. https://doi.org/10.1016/j.envsoft.2007.10.004
Huang G-B (2014) An insight into extreme learning machines: random neurons, random features and kernels. Cogn Comput 6(3):376–390. https://doi.org/10.1007/s12559-014-9255-2
Huang G-B, Chen L (2008) Enhanced random search based incremental extreme learning machine. Neurocomputing 71(16):3460–3468. https://doi.org/10.1016/j.neucom.2007.10.008
Huang G-B, Chen L, Siew C-K (2006a) Universal approximation using incremental constructive feedforward networks with random hidden nodes. Trans Neural Netw 17(4):879–892. https://doi.org/10.1109/tnn.2006.875977
Huang G-B, Zhu Qin-Yu, Siew C-K (2006b) Extreme learning machine: theory and applications. Neurocomputing 70(1):489–501. https://doi.org/10.1016/j.neucom.2005.12.126
Huang G-B, Wang DH, Lan Y (2011a) Extreme learning machines: a survey. Int J Mach Learn Cybern 2(2):107–122. https://doi.org/10.1007/s13042-011-0019-y
Huang J, Zhang J, Zhang Z, ChongYu X, Wang B, Yao J (2011b) Estimation of future precipitation change in the Yangtze River basin by using statistical downscaling method. Stoch Environ Res Risk Assess 25(6):781–792. https://doi.org/10.1007/s00477-010-0441-9
Huang G, Zhou H, Ding X, Zhang R (2012) Extreme learning machine for regression and multiclass classification. IEEE Trans Syst Man Cybern Part B (Cybernetics) 42(2):513–529. https://doi.org/10.1109/tsmcb.2011.2168604
Huang G, Huang G-B, Song S, You K (2015) Trends in extreme learning machines: a review. Neural Netw 61:32–48. https://doi.org/10.1016/j.neunet.2014.10.001
Huth R (2004) Sensitivity of local daily temperature change estimates to the selection of downscaling models and predictors. J Clim 17(3):640–652. https://doi.org/10.1175/1520-0442(2004)017%3c0640:Soldtc%3e2.0.Co;2
Jeong DI, St-Hilaire A, Ouarda TBMJ, Gachon P (2012) Comparison of transfer functions in statistical downscaling models for daily temperature and precipitation over Canada. Stoch Environ Res Risk Assess 26(5):633–653. https://doi.org/10.1007/s00477-011-0523-3
Katz JO (1992) Developing neural network forecasters for trading. Tech Anal Stocks Commodities 8:58–70
Kucharik CJ, Serbin SP (2008) Impacts of recent climate change on Wisconsin corn and soybean yield trends. Environ Res Lett 3(3):034003. https://doi.org/10.1088/1748-9326/3/3/034003
Kumar V, Minz S (2014) Feature selection: a literature review. Smart Comput Rev 4:211–229
Lakhanpal A, Vinit Sehgal R, Maheswaran R Khosa, Sridhar V (2017) A non-linear and non-stationary perspective for downscaling mean monthly temperature: a wavelet coupled second order Volterra model. Stoch Env Res Risk Assess 31(9):2159–2181. https://doi.org/10.1007/s00477-017-1444-6
Lee T, Ouarda TBMJ (2012) Stochastic simulation of nonstationary oscillation hydroclimatic processes using empirical mode decomposition. Water Resour Res. https://doi.org/10.1029/2011wr010660
Linderson M-L, Achberger C, Chen D (2004) Statistical downscaling and scenario construction of precipitation in Scania, southern Sweden. Hydrol Res 35(3):261–278. https://doi.org/10.2166/nh.2004.0019
Liu W, Guobin F, Liu C, Song X, Ouyang R (2013) Projection of future rainfall for the North China Plain using two statistical downscaling models and its hydrological implications. Stoch Env Res Risk Assess 27(8):1783–1797. https://doi.org/10.1007/s00477-013-0714-1
Lu S-X, Wang X, Zhang G, Zhou X (2015) Effective algorithms of the Moore–Penrose inverse matrices for extreme learning machine. Intell Data Anal 19:73–760
Masters T (1993) Practical neural network recipes in C ++. Academic Press Professional Inc, San Diego
May R, Dandy G, Maier H (2011) Review of input variable selection methods for artificial neural networks. Artif Neural Netw Methodol Adv Biomed Appl. https://doi.org/10.5772/16004
Mendes D, Marengo JA (2010) Temporal downscaling: a comparison between artificial neural network and autocorrelation techniques over the Amazon Basin in present and future climate change scenarios. Theoret Appl Climatol 100(3):413–421. https://doi.org/10.1007/s00704-009-0193-y
Minhas R, Baradarani A, Seifzadeh S, Jonathan Wu QM (2010) Human action recognition using extreme learning machine based on visual vocabularies. Neurocomputing 73(10):1906–1917. https://doi.org/10.1016/j.neucom.2010.01.020
Nian R, He B, Lendasse A (2013) 3D object recognition based on a geometrical topology model and extreme learning machine. Neural Comput Appl 22(3):427–433. https://doi.org/10.1007/s00521-012-0892-7
Pal M (2009) Extreme-learning-machine-based land cover classification. Int J Remote Sens 30(14):3835–3841. https://doi.org/10.1080/01431160902788636
Pal M, Maxwell AE, Warner TA (2013) Kernel-based extreme learning machine for remote-sensing image classification. Remote Sens Lett 4(9):853–862. https://doi.org/10.1080/2150704X.2013.805279
Pang B, Yue J, Zhao G, Zongxue X (2017) Statistical downscaling of temperature with the random forest model. Adv Meteorol. https://doi.org/10.1155/2017/7265178
Rao CR, Mitra SK (1972) Generalized inverse of a matrix and its applications. In: Proceedings of the sixth Berkeley symposium on mathematical statistics and probability: theory of statistics, vol 1
Reunanen J (2003) Overfitting in making comparisons between variable selection methods. J Mach Learn Res 3(Mar):1371–1382
Salam MA, Zawbaa HM, Emary E, Ghany KKA, Parv B (2016) A hybrid dragonfly algorithm with extreme learning machine for prediction. In: 2016 International symposium on innovations in intelligent systems and applications (INISTA)
Schoof JT, Pryor SC, Robeson SM (2007) Downscaling daily maximum and minimum temperatures in the midwestern USA: a hybrid empirical approach. Int J Climatol 27(4):439–454
Sivakumar B (2011) Global climate change and its impacts on water resources planning and management: assessment and challenges. Stoch Environ Res Risk Assess 25(4):583–600
Sousounis PJ, Bisanz JM (2000) Preparing for a changing climate: the potential consequences of climate variability and change: Great Lakes. University of Michigan, Atmospheric, Great Lakes Regional Assessment
Sovilj D, Sorjamaa A, Qi Yu, Miche Y, Séverin E (2010) OPELM and OPKNN in long-term prediction of time series using projected input data. Neurocomputing 73(10–12):1976–1986
Stocker T (2014) Climate change 2013: the physical science basis: Working Group I contribution to the fifth assessment report of the Intergovernmental Panel on Climate Change. Cambridge University Press, Cambridge
Tang J, Niu X, Wang S, Gao H, Wang X, Jian W (2016) Statistical downscaling and dynamical downscaling of regional climate in China: present climate evaluations and future climate projections. J Geophys Res Atmos 121(5):2110–2129
Tomassetti B, Verdecchia M, Giorgi F (2009) NN5: a neural network based approach for the downscaling of precipitation fields—model description and preliminary results. J Hydrol 367(1–2):14–26
Trigo RM, Palutikof JP (2001) Precipitation scenarios over Iberia: a comparison between direct GCM output and different downscaling techniques. J Clim 14(23):4422–4446
Tryhorn L, DeGaetano A (2011) A comparison of techniques for downscaling extreme precipitation over the Northeastern United States. Int J Climatol 31(13):1975–1989
Wang Y, Cao F, Yuan Y (2011) A study on effectiveness of extreme learning machine. Neurocomputing 74(16):2483–2490
Wang X, Yang T, Shao Q, Acharya K, Wang W, Zhongbo Yu (2012) Statistical downscaling of extremes of precipitation and temperature and construction of their future scenarios in an elevated and cold zone. Stoch Environ Res Risk Assess 26(3):405–418
Wilby RL, Dawson CW, Barrow EM (2002) SDSM—a decision support tool for the assessment of regional climate change impacts. Environ Model Softw 17(2):145–157. https://doi.org/10.1016/S1364-8152(01)00060-3
Wilby R, Tomlinson OJ, Dawson C (2003) Multisite simulation of precipitation by conditional resampling. Clim Res 23:183–194. https://doi.org/10.3354/cr023183
Wilby R, Charles S, Zorita E, Timbal B, Whetton P, Mearns L (2004) Guidelines for use of climate scenarios developed from statistical downscaling methods. Supporting material of the Intergovernmental Panel on Climate Change, available from the DDC of IPCC TGCIA 27
Xu Y, Dai Y, Dong ZY, Zhang R, Meng K (2013) Extreme learning machine-based predictor for real-time frequency stability assessment of electric power systems. Neural Comput Appl 22(3):501–508. https://doi.org/10.1007/s00521-011-0803-3
Yang T, Li H, Wang W, Chong-Yu X, Zhongbo Yu (2012) Statistical downscaling of extreme daily precipitation, evaporation, and temperature and construction of future scenarios. Hydrol Process 26:3510–3523. https://doi.org/10.1002/hyp.8427
Acknowledgements
This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korean Government (MEST) (2018R1A2B6001799). The temperature daily data of the Kenosha station, Wisconsin, USA, can be downloaded from the National Weather Service Climate Website (https://w2.weather.gov/climate/xmacis.php?wfo=mkx). The CanESM2 predictor variables can be found in the Government of Canada website (http://climate-scenarios.canada.ca/?page=pred-canesm2).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
MoradiKhaneghahi, M., Lee, T. & Singh, V.P. Stepwise extreme learning machine for statistical downscaling of daily maximum and minimum temperature. Stoch Environ Res Risk Assess 33, 1035–1056 (2019). https://doi.org/10.1007/s00477-019-01680-4
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00477-019-01680-4