Streamflow Forecasting of Teesta River for a Hilly Sub-Tropical Humid Zone ANN ANFIS Based Models

The stream flow forecasting of Teesta River which flows in a hilly sub-tropical humid zone of north India using artificial neural network (ANN) and adaptive-neuro fuzzy inference system (ANFIS) is the focus of this study. This study relied on four years of daily precipitation, humidity, temperature, and discharge data from the Teesta River in Sikkim. The network is forecasted using a variety of ANN algorithms. In addition, an ANFIS-based model was created for this purpose. For this research, all ANN and ANFIS modelling is performed in the MATLAB environment. In forecasting the Teesta River discharge, the ANFIS model has a correlation value of 87%, whereas the ANN model using the Levenberg-Marquardt algorithm has a correlation value of 83%.