Flood routing calculations are of vital importance in estimating the floods occurring in the downstream region and taking all necessary measures to minimize the damages that the flood may cause. The prediction success of the created algorithms in the flood routing analysis was tried to be measured by training the daily flood data with machine learning algorithms. This research trained the daily average flood hydrograph data with regression tree, Gaussian process regression, support vector machine, ANFIS and regression tree ensembles. Then the flood routing calculations were made using these models for the hourly flood hydrograph of 2015. The success of the created machine learning algorithms was compared with statistical criteria such as mean absolute error, the root of mean squares of errors and coefficient of determination (R 2), and visually with Taylor diagrams and boxplots. As a result of the analysis established, the ANFIS model divided the inputs into 5 subsets, and the trim membership function showed good results in flood routing. It has been proved that with limited flow data, floods can be postponed, and loss of life and property can be prevented.