a combined method of adaline and knn for rainfall forcasting

Rainfall forecasts can greatly prevent rain damage and improve agricultural and horticultural activities, tourism development, and transportation. machine learning and statistical methods are used in precipitation prediction research that neural networks have been widely used to. in this paper, we present a combined method involving the knn (k nearest neighbor) classification and the adaline neural network to predict the amount of monthly rainfall. in this way, using the knn algorithm, we reduce the effect of values with a greater distance from the target value in the training phase and improve the results obtained from the adaline neural network. we use the collected data on the amount of rainfall during 2006-2016 in kota denpasar and predict the amount of precipitation in 2016 and compare its results with the results of the simple adeline neural network method. comparing the results, we conclude that the proposed combined method gives better performance compared to the simple adeline method.