Modelling of the monthly and daily behaviour of the runoff of the Xallas river using Box–Jenkins and neural networks methods

• Published in: Journal of hydrology (Amsterdam) Vol. 296; no. 1; pp. 38 - 58
• Main Authors: Castellano-Méndez, Marı́a, González-Manteiga, Wenceslao, Febrero-Bande, Manuel, Manuel Prada-Sánchez, José, Lozano-Calderón, Román
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 20.08.2004; Elsevier Science
• Subjects: Artificial neural networks; Box-Jenkins model; Box–Jenkins models; diurnal variation; Earth sciences; Earth, ocean, space; Exact sciences and technology; floods; Floods forecasting; hydrologic models; Hydrology; Hydrology. Hydrogeology; neural networks; Rainfall-runoff process; rivers; stream flow; temporal variation; Time series; time series analysis; Water resources; watershed hydrology; Spain; Iberian Peninsula; Southern Europe; Galicia Spain; Floods forecasting; Box–Jenkins models; Rainfall-runoff process; Water resources; Artificial neural networks; Time series; time series analysis; rivers; floods; models; rainfall; atmospheric precipitation; Europe; neural networks; daily variations; runoff; monthly variations; water resources; prediction; Box-Jenkins models
• ISSN: 0022-1694; 1879-2707
• DOI: 10.1016/j.jhydrol.2004.03.011

This paper presents a study of the hydrological behaviour of the Xallas river basin in the northwest of Spain, based on modelling the performance of the runoff produced by the river at different temporal scales. For monthly mean runoff as well as mean rainfall forecasting, Box–Jenkins models have been used. For short-term daily flow predictions, two statistical techniques were tested and compared: the classic statistical Box–Jenkins models and artificial neural networks (ANNs). The performance of the ANN was an improvement on the Box–Jenkins results. The neural networks capability of modelling a complex rainfall-runoff relationship has been observed. Although the neural network's performance was not satisfactory for detecting some peak flows, the results were most promising.