Development of a Predictive Equation for Modelling the Infiltration Process Using Gene Expression Programming

In this study, the soft computing technique of Gene expression programming (GEP) has been employed to generate a predictive equation of infiltration rate ( f p ). Infiltration experiments were conducted at 124 different sites and soil samples were collected to assess various soil properties througho...

Full description

Saved in:
Bibliographic Details
Published in:Water resources management 2021-04, Vol.35 (6), p.1871-1888
Main Authors: Rasool, Tabasum, Dar, A. Q., Wani, M. A.
Format: Article
Language:English
Subjects:
Algorithms
Atmospheric Sciences
Catchment area
Civil Engineering
Comparative analysis
Data
Datasets
Earth and Environmental Science
Earth Sciences
Environment
Feasibility studies
Gene expression
Geotechnical Engineering & Applied Earth Sciences
Hydrogeology
Hydrology/Water Resources
Infiltration
Infiltration rate
Lake catchments
Lakes
Mathematical models
Performance indices
Root-mean-square errors
Soft computing
Soil investigations
Soil properties
Testing
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this study, the soft computing technique of Gene expression programming (GEP) has been employed to generate a predictive equation of infiltration rate ( f p ). Infiltration experiments were conducted at 124 different sites and soil samples were collected to assess various soil properties throughout the Himalayan lake catchment. Parameters determined from observed data using nonlinear-Levenberg Marquardt algorithm were substituted in Horton, Kostiakov and Philip infiltration models and f p were predicted. Using soil data generated by laboratory investigation of soil samples, the GEP model was developed. Training and testing of the GEP model was performed using 70% and 30% of data respectively. Performance of GEP developed functional relationship was evaluated by comparing predictions from it and aforementioned infiltration models with field observed f p , and by applying overall performance index (OPI) computed using Coefficient of Determination (R 2 ), Nash–Sutcliffe Efficiency (E NS ), Willmott’s Index of Agreement (W), Mean Absolute Error (MAE) and Root Mean Square Error (RMSE). Expression developed using GEP indicated feasibility of developed equation with E NS, R 2 , W, RMSE and MAE of 0.84, 0.84, 0.96, 1.9, and 0.8, respectively for training data-set and 0.84, 0.85, 0.95, 1.2, and 0.95, respectively for testing data-set. Comparative analysis revealed that though with a slightly higher OPI value (0.7–0.8), the performance of conventional models is better compared to the GEP model (0.66) but the GEP model having satisfactory performance may be used for f p prediction particularly in absence of observed data.
ISSN:0920-4741
1573-1650
DOI:10.1007/s11269-021-02816-4