A technique for simulating future climate change variable using improved K-nearest neighbors algorithm (k-NN)

Document Type : Research paper


Department of Civil Engineering, Nigerian Defence Academy, Kaduna, Nigeria


A method for simulating future rainfall events using improved k-nearest neighbors algorithm (k-NN) used in this study. A simulation day was selected in the month of August. The algorithm steps and resampling with historical data was applied to simulate rainfall events in Kaduna River catchment as a basis for future understanding about the characteristics of the basin. Simulated datasets for the months of April, May, June, July, August, September, and October yielded nearly exact reproduction of the historical data. In the simulation performance, the statistical characteristics such as mean, standard deviation, variance, cumulative probability, covariance, skewness, cross correlation are all preserved by the K-NN model. The results clearly showed that the above Technique can be used for generating future rainfall events that means, it can be used for hydrological investigation about characteristics of a basin for future developments.

Graphical Abstract

A technique for simulating future climate change variable using improved K-nearest neighbors algorithm (k-NN)


• The most critical and important need of Man was always water.
• Global climate change is likely to change precipitation patterns and raise the frequency of extreme events.
• The K-NN algorithm model is a robust tool that can be used in predicting future rainfall values.


Main Subjects

Chinn, T.J., 1993. Physical hydrology of the dry valley lakes. Phys. Biogeochem. Process. Antarct. lakes, 59, 1-51.
Sharif, M., Burn, D.H., 2006. Simulating climate change scenarios using Improved K-nearest neighbour model. J. hydro. 325(1-4), 179-169.
Stott, P., 2016. How climate change affects extreme weather events. Sci., 352(6293), 1517-1518.
Garba, H., Tilli, L.G., Ahmed, S. Ibrahim, A., 2018. Rainfall interpolation analysis on River Kaduna catchment for climate change assessment. Niger. J. Technol., 37(3), 806-812.
Ghosh, S., Mujumdar, P.P., 2008. Statistical downscaling of GCM simulations to stream flow using relevance vector machine. Adv. Water. Resour., 31(1), 132-146.
Yates, D., Gangopadhyay, S., Rajagopolan, B., Strzepek, K., 2003. A technique for generating regional climate scenarios using a nearest- neighbour algorithm. Water. Resour. Res., 39(7) 1-15.
Nicks, A.D., Harp, J.F., 1980. Stochastic generation of temperature and solar radiation data. J. Hydrol., 48(1-2), 1-7.
Richardson, C.W., 1981. Stochastic simulation of daily precipitation temperature and solar radiation. Water. Resour. Res., 17(1) 182-190.
Young, K.C., 1994. multivariate chain model for simulating climate parameters from daily data. J. Appl. Meteorol., 33(6), 661-671.
Rajagopolan, B., Lall, U., 1999. A K-nearest- neighbour simulator for daily precipitation and other variables. Water. Resour. Res., 35(10), 3089-3101.
Buishand, T.A., Brandsma, T., 2001. Multisite simulation of daily precipitation and temperature in the Rhine basin by nearest neighbour resampling. Water. Resour. Res., 37(11)2761-2776.
Lall, U., Sharma, A., 1996. A nearest neighbour bootsrap for time series resampling. Water. Resour. Res., 32(3), 679-693.
Folorunsho, J.O., Iguisi, E.O., Mu’azu, M.B., Garba, S., 2012. Application of adaptive neuro fuzzy inference system (Anfis) in river Kaduna discharge forcasting. Res. J. Appl. Sci. Eng. Technol., 4(21), 4272-4283.
ISSN: 20407459
Sharif, M., Burn, D.H., 2007. Improved K-nearest neighbor weather generating model. J. Hydro. Eng., 12(1), 42-51.