A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Neuro-Fuzzy Approach for Predicting the Infiltration of Soil
Abstract This paper aims to develop an adaptive neuro-fuzzy inference system (ANFIS) approach based model for predicting the infiltration of sandy loam soil. To achieve the objective, cumulative infiltration was observed from prepared soil samples at different moisture contents and different densities with the help of minidisk infiltrometer. Input dataset consists of time, the percentage of sand and clay, moisture content, and bulk density, whereas cumulative infiltration was taken as a target. Different membership functions, i.e., triangular, trapezoidal, Gaussian, and generalized bell-shaped, were implemented in ANFIS-based models. Using statistical performance indices, coefficient of correlation (C.C), root mean square (RMSE), and Nash–Sutcliffe efficiency coefficient (NS) were selected to compare the performance of ANFIS-based models and Kostiakov model. Obtained results suggest that Gaussian-based membership function based on ANFIS model had higher prediction performance than other discussed models.
Neuro-Fuzzy Approach for Predicting the Infiltration of Soil
Abstract This paper aims to develop an adaptive neuro-fuzzy inference system (ANFIS) approach based model for predicting the infiltration of sandy loam soil. To achieve the objective, cumulative infiltration was observed from prepared soil samples at different moisture contents and different densities with the help of minidisk infiltrometer. Input dataset consists of time, the percentage of sand and clay, moisture content, and bulk density, whereas cumulative infiltration was taken as a target. Different membership functions, i.e., triangular, trapezoidal, Gaussian, and generalized bell-shaped, were implemented in ANFIS-based models. Using statistical performance indices, coefficient of correlation (C.C), root mean square (RMSE), and Nash–Sutcliffe efficiency coefficient (NS) were selected to compare the performance of ANFIS-based models and Kostiakov model. Obtained results suggest that Gaussian-based membership function based on ANFIS model had higher prediction performance than other discussed models.
Neuro-Fuzzy Approach for Predicting the Infiltration of Soil
Gautam, Saurabh (author) / Sihag, Parveen (author) / Tiwari, N. K. (author) / Ranjan, Subodh (author)
2019-01-01
8 pages
Article/Chapter (Book)
Electronic Resource
English
Neuro-Fuzzy Approach for Predicting the Infiltration of Soil
| TIBKAT | 2019
Solar radiation analyzing by neuro-fuzzy approach
| Online Contents | 2016
A neuro-fuzzy approach to gear system monitoring
| Tema Archive | 2004