Open Access Open Access  Restricted Access Subscription Access

Application of Artificial Neural Networks Intelligence in Forecasting of StreamFlow

Nirmalya Choudhary, Rajneesh Sharma, Dr.Chayan Gupta, Dr.Bhupesh Jain, Rakesh Yadav

Abstract


Forecasting future behaviour of process, by using the key process variables, enables effective decision making in monitoring and operating the process. In the present study, artificial neural networks (ANN) is used for short term streamflow forecasting and its performance characteristics were computed to find out its effectiveness in streamflow forecasting. The daily discharge data for Polavaram Dam of river Godavari at Rajamundry site was taken. For validation of the model 7 years (2001-2007) data is taken and the input matrix is created. The entire model created was run on MATLAB R2013 a version. The network is created and trained as earlier with required number of hidden layers and number of neurons in each layer. The sample matrix created for 7 years data is used for validation of the model and taken as test input matrix. The performance of the model was tested by finding the correlation coefficient(R), Root mean square error (RMSE) and coefficient of determination (R2 ).The ANN model gave good results with R2 value of 0.9182 in validation and reasonably good values in the other two parameters with 0.9667 and 0.9582 values of R in training and validation respectively and 2206.987 and 2253.816 values in RMSE for training and validation respectively.


Full Text:

PDF

References


Sarkar, A., & Kumar, R. (2012). Artificial neural networks for event based rainfall-runoff modeling. Journal of Water Resource and Protection, 4(10), 891.

Wu, C. L., & Chau, K. W. (2010). Data-driven models for monthly streamflow time series prediction. Engineering Applications of Artificial Intelligence, 23(8), 1350-1367.

Egawa, T., Suzuki, K., Ichikawa, Y., Iizaka, T., Matsui, T., & Shikagawa, Y. (2011, July). A water flow forecasting for dam using neural networks and regression models. In 2011 IEEE Power and Energy Society General Meeting (pp. 1-6). IEEE.

Tongal, H. (2013). Nonlinear forecasting of stream flows using a chaotic approach and artificial neural networks. Earth Sciences Research Journal, 17(2), 119-126.

KİŞİ, Ö. (2005). Daily river flow forecasting using artificial neural networks and auto-regressive models. Turkish Journal of Engineering and Environmental Sciences, 29(1), 9-20.

Rezaeianzadeh, M., Tabari, H., Yazdi, A. A., Isik, S., & Kalin, L. (2014). Flood flow forecasting using ANN, ANFIS and regression models. Neural Computing and Applications, 25(1), 25-37.


Refbacks

  • There are currently no refbacks.