Predicting Monsoon Floods in Rivers Embedding Wavelet Transform, Genetic Algorithm and Neural Network

• Published in: Water resources management Vol. 28; no. 2; pp. 301 - 317
• Main Authors: Sahay, Rajeev Ranjan, Srivastava, Ayush
• Format: Journal Article
• Language: English
• Published: Dordrecht Springer-Verlag 2014; Springer Netherlands; Springer; Springer Nature B.V
• Subjects: Algorithms; Atmospheric Sciences; Civil Engineering; Creeks & streams; Earth and Environmental Science; Earth Sciences; Earth, ocean, space; Engineering and environment geology. Geothermics; Environment; Exact sciences and technology; Floods; Forecasting; Fourier transforms; Freshwater; Genetic algorithms; Geotechnical Engineering & Applied Earth Sciences; Hydrogeology; Hydrology; Hydrology. Hydrogeology; Hydrology/Water Resources; Learning theory; Mathematical models; monsoon season; Monsoons; Natural hazards: prediction, damages, etc; Networks; Neural networks; Optimization techniques; Precipitation; prediction; Rain; Regression analysis; River flow; Rivers; Sediments; Stream flow; Time series; time series analysis; Trends; Water resources; Wavelet transforms; Wind; Asia; Southeast Asia; India; INW, Asia; India, Bihar; ANN; Autoregression; Wavelet transform; Flood forecasting; Rivers; India; rivers; algorithms; floods; models; neural networks; water resource management; autoregression; monsoons
• ISSN: 0920-4741; 1573-1650
• DOI: 10.1007/s11269-013-0446-5

Monsoon floods are recurring hazards in most countries of South-East Asia. In this paper, a wavelet transform-genetic algorithm-neural network model (WAGANN) is proposed for forecasting 1-day-ahead monsoon river flows which are difficult to model as they are characterized by irregularly spaced spiky large events and sustained flows of varying duration. Discrete wavelet transform (DWT) is employed for preprocessing the time series and genetic algorithm (GA) for optimizing the initial parameters of an artificial neural network (ANN) prior to the network training. Depending on different inputs, four WAGANN models are developed and evaluated for predicting flows in two Indian Rivers, the Kosi and the Gandak. These rivers are infamous for carrying large flows during monsoon (June to Sept), making the entire North Bihar of India unsafe for habitation or cultivation. When compared, WAGANN models are found to be better than autoregression models (ARs) and GA-optimized ANN models (GANNs) which use original flow time series (OFTS) for inputs, in simulating river flows during monsoon. In addition, WAGANN models predicted relatively reasonable estimates for the extreme flows, showing little bias for underprediction or overprediction.