• Mr. Ajay Bansode
• Mr. Rushikesh Shinde
• Mr. Prathamesh Sarpate

This paper highlights the use of Artificial Neural Network (ANN) to forecast the stream flow beforehand by exploitation of the previous values of stream flow and precipitation at a location specifically Gaganbawda region in Kolhapur district, in India. Separate Monthly models were developed for monsoon months from June to September. The potential of various ANN algorithms specifically Levenberg-Marquardt (LM), Conjugate Gradient function (CGF) and Quasi-Newton’s back propagation (BFG) were investigated through varied models in daily stream flow foretelling and to boost the acute flow prediction. All models performed higher except Gregorian calendar month September model. LM, CGF performed higher in extreme flow prediction as compared to other algorithms.

Artificial neural network, stream flow, algorithm, modelling.

"STREAM FLOW FORECASTING USING ARTIFICIAL NEURAL NETWORK", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 5, page no.338-342, May-2019, Available :http://www.jetir.org/papers/JETIRBO06064.pdf

"STREAM FLOW FORECASTING USING ARTIFICIAL NEURAL NETWORK", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 5, page no. pp338-342, May-2019, Available at : http://www.jetir.org/papers/JETIRBO06064.pdf