Hydrological forecasting Framework

Forecasting is critical in most planning studies and management tasks and so too in hydrological studies where forecasting plays a vital role in a variety of areas viz. flood and drought management, development of early warning systems, sedimentation rate forecasting and other reservoir studies, groundwater trends and climate change impact studies amongst others. However, the complexity of the natural (hydrological and geophysical) process and its variability in time and space makes the task of forecasting very challenging. The natural processes are generally composed of multiple features that are present at different temporal scales but whose individual, scale specific, characteristic details get camouflaged in the integrated observations. Generally, traditional models are seen to lack the capability to recognize and discriminate between features that operate at different scales and are therefore unable to provide satisfactory forecasts. The main aim of this study is to develop a Wavelets based, unified modelling framework that is able to detect the underlying, but individually non-observable, scale specific features in the hope to obtain more efficient forecasts.

References

1.   Quilty, J., Adamowski, J., Khalil, B. and Rathinasamy, M., 2016. Bootstrap rank‐ordered conditional mutual information (broCMI): A nonlinear input variable selection method for water resources modeling. Water Resources Research, 52(3), pp.2299-2326.

2.   Maheswaran, R., Khosa, R., 2015. Wavelet Volterra Coupled Models for forecasting of nonlinear and non-stationary time series. Neurocomputing 149, 1074–1084. https://doi.org/10.1016/j.neucom.2014.07.027

3.   Rathinasamy, M., Khosa, R., Adamowski, J., Ch, S., Partheepan, G., Anand, J. and Narsimlu, B., 2014. Wavelet‐based multiscale performance analysis: An approach to assess and improve hydrological models. Water Resources Research, 50(12), pp.9721-9737.

4.   Sudheer, C., Maheswaran, R., Panigrahi, B.K., Mathur, S., 2014. A hybrid SVM-PSO model for forecasting monthly streamflow. Neural Comput. Appl. 24, 1381–1389. https://doi.org/10.1007/s00521-013-1341-y

5.   Maheswaran, R., Khosa, R., 2014. A Wavelet-Based Second Order Nonlinear Model for Forecasting Monthly Rainfall. Water Resour. Manag. 28, 5411–5431. https://doi.org/10.1007/s11269-014-0809-6

6.   Rathinasamy, M., Adamowski, J., Khosa, R., 2013. Multiscale streamflow forecasting using a new Bayesian Model Average based ensemble multi-wavelet Volterra nonlinear method. J. Hydrol. 507, 186–200. https://doi.org/10.1016/j.jhydrol.2013.09.025

7.   Maheswaran, R., Khosa, R., 2013a. Wavelets-based non-linear model for real-time daily flow forecasting in Krishna River. J. Hydroinformatics 15, 1022–1041. https://doi.org/10.2166/hydro.2013.135

8.   Maheswaran, R., Khosa, R., 2013b. Long term forecasting of groundwater levels with evidence of non-stationary and nonlinear characteristics. Comput. Geosci. 52, 422–436. https://doi.org/10.1016/j.cageo.2012.09.030

9.   Maheswaran, R., Khosa, R., 2012a. Wavelet-Volterra coupled model for monthly stream flow forecasting. J. Hydrol. 450–451, 320–335. https://doi.org/10.1016/j.jhydrol.2012.04.017

10.   Maheswaran, R., Khosa, R., 2012b. Comparative study of different wavelets for hydrologic forecasting. Comput. Geosci. 46, 284–295. https://doi.org/10.1016/j.cageo.2011.12.015

11.   Rathinasamy, M., Khosa, R., 2012. Multiscale nonlinear model for monthly streamflow forecasting: A wavelet-based approach. J. Hydroinformatics 14, 424–442. https://doi.org/10.2166/hydro.2011.130