Rainfall-Runoff modeling of river Kosi using SCS-CN method and ANN

Abstract

A rainfall-runoff model is a mathematical model describing the rainfall - runoff relations of a catchment area, drainage basin or watershed. In other words, the model calculates the conversion of rainfall into runoff. There can be used many methods to calculate the runoff among which the methods used in the current report are
• SCS-CN Method
• Artificial Neural Network (ANN)
In rainfall-runoff modeling SCS-CN uses the soil information, rainfall, storm duration, soil texture, type & amount of vegetation cover and conservation practices are considered while a new dimension has been added to the modeling approach through the adoption of the ANN technique as these models possess desirable attributes of universal approximation, and the ability to learn from examples.
The performance comparison of both the models is made with coefficient of determination (R2) which is coming to be 0.82 in case of SCS-CN method and 0.89 in case of ANN. Further a comparison is made of both the models i.e. ANN and SCS-CN for the runoff of river Kosi in year 2009.