Comparison of different methods for reconstruction of instantaneous peak flow data. Issue 1 (2nd January 2017)

• Record Type: Journal Article
• Authors: Fathzadeh, Ali; Jaydari, Azam; Taghizadeh-Mehrjardi, Ruhollah
• Is Part Of: Intelligent automation & soft computing. Volume 23:Issue 1(2017)
• Page Start: 41
• Page End: 49
• Publication Date: 2017-01-02
• Subjects: Peak discharge -- ANFIS -- ANN -- GA -- central part of Iran; Artificial intelligence -- Periodicals; Intelligent control systems -- Periodicals; 003.5
• DOI: 10.1080/10798587.2015.1120991
• Languages: English
• ISSNs: 1079-8587

Abstract

Abstract: In arid and semi-arid regions, documentary data of past floods remain justly rare and highly fragmentary in most cases. Existence of many effective parameters on maximum flood discharge and the complex relationships between them is an important challenge in the reconstruction of these data and hence, it limited the application of traditional methods. In this paper, an alternative approach (i.e. artificial intelligence methods) has been evaluated to determine the interactive relations of them. To this end, flow data was collected from 29 gauging stations in the central part of Iran for the period 1965 to 2007. Following quality and homogeneity controls of the data, reconstruction of instantaneous peak flow time series were made using maximum daily data by four different methods; regression method (REG), artificial neural network (ANN), genetic algorithm (GA) and adaptive neuro-fuzzy inference system (ANFIS). Results showed that in all studied stations, ANFIS reconstructs instantaneous peak flow values with the highest accuracy among the four tested methods.