Regional flood analysis by random forest method in the Namak Lake basin

Flood is one of the most devastating natural disasters, causing financial and human losses each year. At the same time, many rivers in Iran's watersheds lack complete and accurate statistics and information. On the other hand, estimating the flow of floods is one of the most important factors for the design and implementation of water structures. In such cases, one of the appropriate solutions to estimate the maximum flow rate with different return periods is flood analysis. In order to conduct the present study, 55 hydrometric stations with a common statistical period of 20 years were considered to perform the work after the statistical deficiencies were eliminated. Then, based on the distribution of the third type of Pearson logo with the lowest error rate and the highest number of first rank as the most suitable fit function, the amount of discharge in different return periods was estimated. The following information was collected on the types of physiography, land use, climate and geology variables. After collecting information about all independent variables using Gamma test, the most important variables affecting the maximum instantaneous flow, including area, drainage density, maximum 24-hour rainfall and watershed environment, were selected and modeled using methods. Random forest modeling and support vector modeling were performed and their efficiency was determined based on statistical indicators With an efficiency coefficient of 74 to 83%, the error of 3.05 to 32.11 m3 and the coefficient of explanation of 76 to 91 are more accurate than the random forest model.