A STUDY OF RECURRENT NEURAL NETWORKS BASED WATER LEVEL FORECASTING FOR FLOOD CONTROL: CASE STUDY ON KOYANA DAM

Flood control is crucial task that facesfatal hazards due to fast rising peak flows from urbanization. To lower down the future flood damages, it is imperative to construct an on-line accurate model to forecast inundation levels during flood periods. The regions near Koyna and Krishna basins located in Maharashtra region is selected as study area. In this approach first step is the analysis of historical hydrologic data by statistical techniques to identify the time span of rainfall affecting the rise of the water level in the floodwater storage pond (FSP) at the regions. Second step is the effective factors that affect the FSP water level are extracted by the Gamma test. Thirdly, one static artificial neural network (ANN) (Back Propagation Neural Network-BPNN) and two dynamic ANN’