Assessment of Flood Frequency using Statistical and Hybrid Neural Network Method: Mahanadi River Basin, India

Abstract

Flooding is the most common and widespread natural hazard affecting societies around the globe. In this context, forecasting of peak flood discharge is necessary for planning, designing and managing hydraulic structures and is crucial for decision makers to mitigate flooding risks. This study investigates potential of four most frequently used traditional statistical distribution techniques and three neural network algorithms for flood forecasting. Four statistical methods includes Generalized Extreme Value (GEV), Log Pearson-III (LP-III), Gumbel, and Normal. The methods were used for modeling annual maximum discharge at Andhiyarkore, Bamanidhi, Baronda, Kurubhatta gauge station of the river Mahanadi for a period of 60 years (1960 to 2019). In addition, a new hybrid neural network approach (ANFIS-FFA) combining the optimization model i.e. Firefly Algorithm (FFA) with data-driven model Adaptive Neuro Fuzzy Inference System (ANFIS) is adopted to predict flood discharge and compare the obtained results with conventional algorithms. Three statistical constraints MSE, RMSE, WI are employed to find the performance of proposed hybrid model. Result shows that, ANFIS-FFA gives the best values of WI as 0.9604, 0.961, 0.9598 and 0.9615 at Andhiyarkore, Bamanidhi, Baronda, Kurubhatta gauge stations respectively during testing phase. Again regression analysis is done to find the value for coefficient of determination; it gives the best value of R2 as 95.906, 96.014, 96.113, 96.131 at Andhiyarkore, Bamanidhi, Baronda, Kurubhatta gauge stations considering ANFIS-FFA algorithm. Results from this comparative exercise suggest that hybrid ANFIS-FFA gives best performance compared to other statistical and conventional neural network approaches.

Reckoning flood frequency and susceptibility area in the lower Brahmaputra floodplain using geospatial and hydrological approach

“…Recorded sample data sets pose a critical input in the probability estimation, whereas standard norms can be considered 30 years; on the contrary, a lack of temporal data series leads to poor frequency results (Bobee & Robitaille, 1977; Saghafian et al, 2014). However, many studies around the world have been carried out with the probability methods to understand the flood hazard, especially in the data‐scarce area (ungauged stations) or with at least 10 years or above data range (Odunuga & Raji, 2014; Samantaray et al, 2021). Different probability distribution approaches like Gumbel, Log‐Pearson, and Log‐Normal are widely applicable or suitable for frequency analysis at a particular‐site (Hydrological station) or regional level frequency analysis (UI Hassan et al, 2019).…”

Application of Hybrid Support Vector Machine model for Streamflow Prediction in Barak valley, India

“…In 1032 (2022) 012016 IOP Publishing doi:10.1088/1755-1315/1032/1/012016 2 contrast, DD models mathematically capture non-linear or linear interactions amid Qflow and its descriptive variables [8]. DD methods like ANN (artificial neural network), SVM, and ANFIS (adaptive neuro-fuzzy inference system), have been successfully applied by many investigators in hydrological field of study; for example, sediment transport modelling [9,10,11,12], runoff modeling [13,14,15], water table depth prediction [16,17,18], streamflow forecasting [19,20,21]; pan evaporation estimation [22,23]; flood prediction [24,25,26,27,28].…”

A comparative study of probability distribution models for flood discharge estimation

“…FFA can be easily done with the help of many statistical distribution functions, including Normal, Log-Normal, Gumbel, Pearson Type III, Log-Pearson Type III, Weibull, Generalized Extreme Value, and Generalized Logistic functions. There are many studies in the literature in which these distributions are used (Zhang et al, 2017;Farooq et al, 2018;Bhat et al, 2019;Langat et al, 2019;Samantaray and Sahoo, 2021;Sahoo and Ghose, 2021;Umar et al, 2021;Mangukiya et al, 2022).…”