Reservoir inflow forecasting using ID3 and C4.5 decision tree model

Abstract

Decision tree model is one of data mining method for builds classification models in the form of a tree structure. These methods are produced various ways of splitting a data set into branch like segments that call nodes. Today, forecasting method is very importance for every side especially agriculture. Because some farmers who want to predict their crops for each semester. This paper describes about method for forecast daily inflow to reservoir in order to present new method for predication. We prepare 1000 data sets for analysis with reservoir prototype. And then used training set testing ID3 and C4.5 algorithms for choose the best algorithm to create reservoir prototype. The results show that ID3 algorithm is the best way for forecasting data then we will create the reservoir prototype in order to forecasting water pass reservoir, and can indicate level of water in very severe, severe, or less. After that we bring reservoir prototype to test by users, and all of user test reservoir prototype and suggest that 67% satisfy in learning ability, 80% moderately satisfied in control.