Analysis of Geo-environmental parameters and gully erosion susceptibility mapping in toroud watershed using data-driven Evidential Belief Function method

Document Type : Research Paper

Authors

1 kharazmi university

2 tehran university

Abstract

Gully erosion is one of the erosive processes that mostly change the shape of the earth surface and has severe environmental and economic damages. The aim of this research is modeling between geo-environmental parameters effective in gully erosion and gully occurrence in the study area and gully erosion susceptibility mapping using evidential belief function (EBF) data driven model in toroud watershed that has high susceptibility to gully erosion. At first, a gully erosion inventory map is prepared, using extensive field surveys and 80 gullies which have been identified, 70 percentage (56 gully location) randomly selected to modeling, while the remaining 30 percentage (24 gully location) are used to validation. In modeling, if there was high correlation among parameters, reduce accuracy of model, thus has done multi-collinearity test among independent variables. Tolerance and the variance inflation factor (VIF) are two important indexes for multi-collinearity diagnosis. Finally 15 parameters including geomorphological, geological, environmental and hydrological are selected for modeling. In evidential belief function model four relationships were calculated: belief (Bel), disbelief (Dis), uncertainty (Unc), and plausibility (Pls) and belief function are used for gully erosion susceptibility mapping. Area under the curve are used for model validation. According to results, EBF model with prediction rate (1) and success rate (0.959) had excellent accuracy and capability in identification of prone areas to gully erosion in study area. The results indicates that 21.79 percentage (90.84 km2) in study area located in high and very high susceptibility class.

Keywords

Journal of Range and Watershed Managment
Volume 71, Issue 1
June 2018
Pages 97-114

Files

History

  • Receive Date: 23 October 2017
  • Revise Date: 02 June 2018
  • Accept Date: 19 May 2018
  • First Publish Date: 22 May 2018

Share

How to cite

Statistics