Evaluation of adaptive neural-based fuzzy inference system approach for estimating saturated soil water content

Abstract

The saturated soil water content (h s ) is an important parameter in hydrological studies. In this paper, adaptive neural-based fuzzy inference system (ANFIS) was used for estimation of soil saturation percentage of some flood spreading areas in Iran. Soil particle size distribution (sand%, silt%, and clay%), bulk density and medium porosity (0.2-30 lm) were used to develop saturated soil water content pedotransfer functions (PTFs). Then, contributions of various member functions (MFs) were assessed on estimation of h s . The results showed that the member function type has an important role in performance of ANFIS approach. In the present investigation, Gaussian curve (gaussmf) was found to be superior over the other MFs in estimating h s . In all of the h s PTFs, correlation between estimations of h s and corresponding observations was the low. R 2 values between measured and PTF-estimated h s using ANFIS approach did not increase as some input predictors were used in the PTFs (from PTF 1 to PTF 5 ). Based on the results, it is suggested that ANFIS model can be applied for reasonable estimation of h s and there is a need for obtain more information of the proposed approach especially for the selection of best member functions. Therefore, a good performance may be obtained when best member function would be selected in addition to the more effective PTF inputs.

A hybrid model for modelling the salinity of the Tafna River in Algeria

“…In recent years, the hybrid systems which combines fuzzy logic and neural networks prove their effectiveness by explaining the most complicated hydrological and environmental phenomena [ALVISI et al 2006;FASHI 2016;KESKIN et al 2006;OPREA et al 2017;SUPARTA, ALHASA 2013;TABARI et al 2012;TALEGHANIA et al 2017]. According to BURAGOHAIN and MAHANTA [2008], MAHABIR et al [2006] and WANG et al [2004] the hybrid model (neuro-fuzzy) "capture" the behaviour of non-linear syssystems quickly and accurately, even more so than other methods.…”