ORIGINAL PAPER Flood hydrograph modeling using artificial neural network and adaptive neuro-fuzzy inference system based on rainfall components Saeid Janizadeh 1 & Mehdi Vafakhah 1 Received: 22 November 2019 /Accepted: 3 February 2021 # Saudi Society for Geosciences 2021 Abstract Different limitations such as the lack of enough hydrometric stations, difficulty in collecting hydrometric data with costly data collection are caused to create hydrologic models for estimating the flood hydrograph. Based on the easy and more access to rainfall statistics, preparing the hydrologic model based on rainfall characteristics and data seems to be the very applicable and logical method. Data-driven models have increasingly been used to describe the behavior of hydrological systems, which can be used to complement or even replace physical-based models. In this study, the efficiency of two data mining models including artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) was evaluated in order to model flood hydrograph characteristics based on rainfall components in Kasilian Watershed, northern Iran. For this purpose, fifteen charac- teristics of rainfall (hyetograph) and eight characteristics of flood hydrograph were respectively considered independent and dependent variables for 60 rainfall-runoff events from 1975 to 2009. ANN with two functions of hyperbolic tangent and sigmoid and ANFIS with grid partitioning and subtractive clustering were used to estimate flood hydrograph. Variance inflation factor (VIF) (for selecting variables that are minimal multicollinearity) were used to select the input variables. ANFIS model with the grid partitioning method performs better than the ANFIS model with the subtractive clustering method. ANFIS with Nash- Sutcliff efficiency (NSE) of 0.87, root mean squared error (RMSE) of 0.38 m 3 /s, and deviation of peak time of observed and estimated hydrographs (DPOT) of 4.33 h was found to be superior to ANN with NSE of 0.40, RMSE of 0.88 m 3 /s, and DPOT of 1.14 h accurately and efficiently for modeling flood hydrograph. Therefore, ANFIS model is proposed for modeling the flood hydrograph based on rainfall characteristics. Keywords Artificial neural network . Adaptive neuro-fuzzy inference system . Flood hydrograph . Modeling . Variance inflation factor Introduction Preparation and implementation of various projects such as development plans, hydrologic and hydraulic structure design, and planning of soil and water conservation need to prepare daily and storm-wise runoff data series. Simulating flood hydrographs and determining their components form an im- portant part of this work. Preparing flood hydrograph for all storm events of a basin is not simple and needs high accuracy, cost, and facilities (Onyando et al. 2003). Several indirect methods have been developed to simulate accurate and com- prehensive estimates of natural hydrological systems. One of these methods is hydrological modeling or simulation. The deterministic and stochastic models in terms of its importance in the watershed, more than any other processes seem to have attracted hydrologists. These processes had the highest chang- es in the range of time and place, and their simulation had many problems in terms of nonlinear nature and high dimen- sions. Today, using intelligent methods such as artificial neu- ral network (ANN), adaptive neuro-fuzzy inference system (ANFIS), fuzzy logic (FL), and genetic algorithm (GA) were Responsible Editor: Biswajeet Pradhan * Mehdi Vafakhah vafakhah@modares.ac.ir Saeid Janizadeh janizadehsaeid@modares.ac.ir 1 Department of Watershed Management Engineering, Faculty of Natural Resources and Marine Sciences, Tarbiat Modares University, Noor, Mazandaran 46414-356, Iran Arabian Journal of Geosciences (2021) 14:344 https://doi.org/10.1007/s12517-021-06683-6