14-Project Report on Rainfall-Runoff Modelling Using Artificial Neural Network

Abstract

The runoff means the draining or flowing off of precipitation from a catchment area through a surface channel. There are three types of runoff namely direct runoff, baseflow runoff, and natural flow runoff. The relationship between rainfall-runoff is one of the most complex hydrological phenomena to comprehend the spatial and temporal variability of watershed characteristics and precipitation patterns and also to the number of variable involved in the modelling of the physical process. By ANN modelers the problem of rainfall runoff modelling has received maximum attention in this report, the application of Artificial Neural Network model (ANN) and a model combining the multiple layer regression (MLR) is investigated to make the ANN model using rainfall-runoff data of Hamp river, Chattisgarh. The rainfall in the catchment area Chirapani, Bodla, and Panadariya and the hourly discharge data is used to carry out this research work. The duration of data used is from 1881 to 2009. The RMSE of ANN model during calibration and validation was found to be 0.9721 and 0.9896 respectively, whereas for the MLR model, RMSE value during calibration and validation was 0.9628 and 0.9648 respectively, and also the ANN model efficiency during calibration and validation was 0.9449 and 0.9794 respectively, whereas the MLR model efficiency during calibration and validation was 0.9271 and 0.9307 respectively, indicates a substantial improvement in the model performance.In addition, comparison of the scatter plots of ANN model are more precise than those found by the MLR.