Predicting soil infiltration rate using Artificial Neural Network

Simulation of the runoff-rainfall process in forest lands is essential for forest land management. In this research, a hydrologic modelling system (HEC-HMS) and artificial neural network (ANN) were applied to simulate the rainfall-runoff process (RRP) in forest lands of Kasilian watershed with an area of 68 square kilometres. The HMS model was performed using the secondary data of rainfall and discharge at the climatology and hydrometric stations, the Soil Conservation Service (SCS) for simulating a flow hydrograph, the curve number (CN) method for runoff estimation, and lag time method for flow routing. Further, a multilayer perceptron (MLP) network was used for simulating the rainfall-runoff process. HEC-HMS model was used to optimize the initial loss (IL) values in the rainfall-runoff process as an input. IL reflects the conditions of vegetation, soil infiltration, and antecedent moisture condition (AMC) in soil. Then, IL values and also incremental rainfall were applied as inputs into ANN to simulate the runoff values. The comparison of the results of simulating the RRP in two scenarios, using IL and without IL, showed that the IL parameter has a high effect in increasing the simulation performance of the rainfall-runoff process. Moreover, ANN predictions were more precise in comparison with those of the HMS model. Further, forest lands can significantly increase IL values and decrease runoff generation.

Download Full-text

Optimization of the Conceptual Model of Green-Ampt Using Artificial Neural Network Model (ANN) and WMS to Estimate Infiltration Rate of Soil (Case Study: Kakasharaf Watershed, Khorram Abad, Iran)

Journal of Water Resource and Protection ◽

10.4236/jwarp.2014.65047 ◽

2014 ◽

Vol 06 (05) ◽

pp. 473-480 ◽

Cited By ~ 4

Author(s):

Ali Haghizadeh ◽

Leila Soleimani ◽

Hossein Zeinivand

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Conceptual Model ◽

Network Model ◽

Neural Network Model ◽

Artificial Neural Network Model ◽

Infiltration Rate ◽

Artificial Neural

Download Full-text

Using Reflectance Spectroscopy and Artificial Neural Network to Assess Water Infiltration Rate into the Soil Profile

Applied and Environmental Soil Science ◽

10.1155/2012/439567 ◽

2012 ◽

Vol 2012 ◽

pp. 1-9 ◽

Cited By ~ 8

Author(s):

Naftali Goldshleger ◽

Alexandra Chudnovsky ◽

Eyal Ben-Dor

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Spectral Properties ◽

Clay Content ◽

Soil Surface ◽

Infiltration Rate ◽

Water Infiltration ◽

Morphological Properties ◽

Pls Regression ◽

Artificial Neural

We explored the effect of raindrop energy on both water infiltration into soil and the soil's NIR-SWIR spectral reflectance (1200–2400 nm). Seven soils with different physical and morphological properties from Israel and the US were subjected to an artificial rainstorm. The spectral properties of the crust formed on the soil surface were analyzed using an artificial neural network (ANN). Results were compared to a study with the same population in which partial least-squares (PLS) regression was applied. It was concluded that both models (PLS regression and ANN) are generic as they are based on properties that correlate with the physical crust, such as clay content, water content and organic matter. Nonetheless, better results for the connection between infiltration rate and spectral properties were achieved with the non-linear ANN technique in terms of statistical values (RMSE of 17.3% for PLS regression and 10% for ANN). Furthermore, although both models were run at the selected wavelengths and their accuracy was assessed with an independent external group of samples, no pre-processing procedure was applied to the reflectance data when using ANN. As the relationship between infiltration rate and soil reflectance is not linear, ANN methods have the advantage for examining this relationship when many soils are being analyzed.

Download Full-text