Estimation of Dam Reservoir Volume Using Neural Networks

Abstract

Dam reservoir capacity estimations are important for operation, design and safety assessments of dam structures. In this study, the reservoir capacity of the Stony Brook dam in US state of Massachusetts was tried to be estimated with data taken from US Geological Survey Institute (USGS). Reservoir capacity was estimated by using two types Neural Networks, namely, Artificial Neural Networks (ANN), Generalized Neural Networks (GRNN), and also Multi Linear Regression method (MLR) models. The model results were compared with measurements by calculating Mean Square Error (MSE), Mean Absolute Error (MAE), correlation coefficient statistics.

Keywords

• estimation
• artificial neural networks
• reservoir
• multiple linear regression