Open Access Open Access  Restricted Access Subscription or Fee Access

Application of Hybrid Wavelet Packet-ANN in Drought Forecasting

Prabal Das, Paresh Chandra Deka

Abstract


Drought is the most catastrophic natural disaster that has disastrous effect on human beings, environment and ecology. It is the most frequent of all the natural hazards. In this study, an attempt has been made to forecast the drought using Artificial Neural Network (ANN) for a lead time of 1-month and 6-month. Further, the pre-processing of data has been carried out using Wavelet Packet transform (WPT) and then the pre-processed data has also been used as inputs to ANN (WP-ANN). The study has been carried out in Gulbarga is one of the drought prone districts of Karnataka. The mulitemporal Standardized Precipitation Index (SPI) has been used for assessing drought severity. The fine resolution daily gridded data (0.25 x 0.25) from Indian Meteorological Department (IMD) of 21 grid stations within the study area has been used for the analysis. The performance of the models has been accessed on the basis of R2, RMSE and MAE. The results showed that the hybrid techniques showed better forecasting than the normal ANN and the forecasting results deteriorated as the lead time was increased from 1-month to 6-month.

Full Text:

PDF

References


. W. Palmer. Meteorological Drought. Research Paper 45. U.S. Department of Commerce Weather Bureau, Washington DC; 1965.

. D.A. Wilhite (Ed). Drought and Water Crises: Science, Technology, and Management Issues. CRC Press; 2005.

. D.A. Wilhite, M.H. Glantz. Understanding the Drought Phenomenon: The Role of Definitions. Water Int.1985; 10(3): 111-120p.

. A.K. Mishra, V.R. Desai. Drought forecasting using feed-forward recursive neural network. Ecol Modell.2006;198(12): 127-138p.

. S. Modrid, V. Smakhtin, K. Bagherzadeh. Drought forecasting using artificial neural networks and time series of drought indices. Int J Climatol. 2007;27, 2103-2111p.

. T.W. Kim, J.B. Valdes. Nonlinear model for drought forecasting based on a conjunction of wavelet transforms and neural networks. J Hydrol Eng. 2003;8(6):319-328p.

. T.B. McKee, N.J. Doesken, J. Kleist. The Relationship of Drought Frequency and Duration to Time Scales.”Eighth Conference on Applied Climatology, American Meteorological Society, Anaheim, CA; 1993.

. World Meteorological Organization (WMO) and Global Water Partnership (GWP), 2016: Handbook of Drought Indicators and Indices. M. Svoboda, B.A. Fuchs). Integrated Drought Management Programme (IDMP), Integrated Drought Management Tools and Guidelines Series 2. Geneva.

. N. Wanas, G. Auda, M.S. Kamel, F. Karray. On the optimal number of hidden nodes in a neural network.” Proceedings of the 11th IEEE Canadian Conference on Electrical and Computer Engineering (CCECE ’98);1998;918–921p.

. M.K. Tiwari, C. Chatterjee. Development of an accurate and reliable hourly flood forecasting model using wavelet bootstrap-ANN (WB-ANN) hybrid approach. J Hydrol. 2010; 394(3): 458-470p.

. D.E. Rumelhart, G.E. Hinton, R.J. Williams. Learning representations by back-propagating errors. Nature. 1986; 323: 533-536p




DOI: https://doi.org/10.37628/jwre.v3i2.232

Refbacks

  • There are currently no refbacks.