Climate change forecasting using data mining algorithms

Abstract

Water is the most important renewable natural resource. Water management is very important for human life sustainability. Rainfall forecasting is one of the most important factors for the water management of an area. A time series is a collection of observations of a variable taken at regular intervals of time. A forecast, on the other hand, is simply a calculation of what happens in the future of the variable of interest based on past information under the assumption that the pattern followed in the past would continue in the future also. This work will aim at obtaining forecasting models for the time series dataset using conventional models and computational models. Varanasi City's annual climate data for a total of 113 years (1906–2018) will be used for the analysis. Initially, the individual model will be considered and used for forecasting. Later, hybrid models will be considered and a comparison between individual models and hybrid models would be obtained. The individual statistical models to be considered are moving average, exponential smoothing with one parameter, and the classical model autoregressive integrated moving average (ARIMA). The forecast is also done individually using the computational model k-nearest neighbor (kNN) and interpolation technique cubic spline.