Comparison of multi-objective evolutionary neural network, adaptive neuro-fuzzy inference system and bootstrap-based neu
- PDF / 1,197,647 Bytes
- 16 Pages / 595.276 x 790.866 pts Page_size
- 60 Downloads / 167 Views
ORIGINAL ARTICLE
Comparison of multi-objective evolutionary neural network, adaptive neuro-fuzzy inference system and bootstrap-based neural network for flood forecasting Amal Kant • Pranmohan K. Suman • Brijesh K. Giri Mukesh K. Tiwari • Chandranath Chatterjee • Purna C. Nayak • Sawan Kumar
•
Received: 14 September 2011 / Accepted: 25 January 2013 Springer-Verlag London 2013
Abstract Accurate flood forecasting is of utmost importance in mitigating flood disasters. Flood causes severe public and economic loss especially in large river basins. In this study, multi-objective evolutionary neural network (MOENN) model is developed for accurate and reliable hourly water level forecasting at Naraj gauging site in Mahanadi river basin, India. The performance of the developed model is compared with adaptive neuro-fuzzy inference system (ANFIS) and bootstrap-based neural network (BNN) models. The performance of the models is compared in terms of Nash–Sutcliffe efficiency, root mean square error, mean absolute error and percentage deviation in peak (D). The performance of the models in forecasting floods is also evaluated using existing performance evaluation criterion of Central Water Commission, India as well as a multiple linear regression model. A partitioning analysis in conjunction with threshold statistics is carried out to evaluate the performance of the developed models in forecasting floods for low, medium and high water levels. It is found that the performance of MOENN and BNN models is more stable and consistent compared to ANFIS model. For longer lead times, the performance of MOENN model is found to be the best, with its performance in forecasting higher water levels being significantly better compared to ANFIS and BNN models. Overall, it is found
A. Kant P. K. Suman B. K. Giri M. K. Tiwari C. Chatterjee (&) P. C. Nayak S. Kumar Indian Institute of Technology, Kharagpur 721 302, West Bengal, India e-mail: [email protected]; [email protected] P. C. Nayak Deltaic Regional Centre, National Institute of Hydrology, Siddartha Nagar, Kakinada 533 003, Andhra Pradesh, India
that MOENN model has great potential to be applied in flood forecasting. Keywords Neural network Multi-objective evolutionary neural network Neuro-fuzzy inference system Bootstrap-based neural network Flood forecasting
1 Introduction Hydrological forecasting is one of the most important issues in hydrology, and it is essential for proper water resources planning and management. Hourly flood forecasting can be very effective in issuing flood warning so as to reduce flood disaster by taking appropriate evacuation and rehabilitation measures. A testimony to this fact is the overwhelming research that it has attracted from the research community over the last few decades. The processes and parameters that affect the water level for different lead times at some point downstream in a river system are very complex. Several physically based and conceptual models have been applied for flood forecasting. In large
Data Loading...
