Published Paper Details:

Rainfall-runoff modeling is one of the most important topics in water resources planning, development and management on sustainable basis. The Multilayer Perceptron (MLP) and Multiple Linear Regression (MLR). This study was undertaken to develop and evaluate the applicability of the MLP and MLR models by way of training and testing of developed models during monsoon period (June to September) for Meghalaya district of Assam state of India. The daily data of rainfall, runoff (or stream flow), minimum & maximum temperature and wind speed were used in the study for monsoon season. The daily data were split into two sets: a training data set from 2013 to 2020 and a testing data set from 2021 to 2022 for Meghalaya Assam. The NeuroSolution 6.0 software and Microsoft Excel were used in an analysis and the performance evaluation indices for developed models, respectively. The best input combination of rainfall, runoff minimum & maximum temperature and wind speed were identified using the input-output combination for the simulation of Runoff. On the basis input combination, 10 best models for runoff were selected out of 15 models, respectively with different input combinations. The input pairs in the training data set were applied to the network of a selected architecture and training was performed using back propagation algorithm for MLP models. A number of networks were constructed and each of them was trained separately, and the best network was selected based on the accuracy of the predictions in the testing phase. The following statistical indices such as mean squared error (MSE), coefficient of efficiency (CE), coefficient of determination (R2) and coefficient of correlation (r) were applied to test the performance of the developed MLP and MLR models. The predicted suspended sediment using MLP models were found to be the best performing models for Meghalaya Assam. It was clearly evident that MLR models fit very poorly for the dataset under study. The current day's runoff can be simulated using the data of current day rainfall.