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.
• 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.