Abstract

Gully erosion is an environmental problem in arid and semi-arid areas. Gullies threaten the soil and water resources and cause off- and on-site problems. In this research, a new hybrid model combines the index-of-entropy (IoE) model with the weight-of-evidence (WoE) model. Remote sensing and GIS techniques are used to map gully-erosion susceptibility in the watershed of the Bastam district of Semnan Province in northern Iran. The performance of the hybrid model is assessed by comparing the results with from models that use only IoE or WoE. Three hundred and three gullies were mapped in the study area and were randomly classified into two groups for training (70% or 212 gullies) and validation (30% or 91 gullies). Eighteen topographical, hydrological, geological, and environmental conditioning factors were considered in the modeling process. Prediction-rate curves (PRCs) and success-rate curves (SRCs) were used for validation. Results from the IoE model indicate that drainage density, slope, and rainfall factors are the most important factors promoting gullying in the study area. Validation results indicate that the ensemble model performed better than either the IoE or WoE models. The hybrid model predicted that 38.02 percent of the study area has either high or very high susceptible to gullying. Given the high accuracy of the novel hybrid model, this scientific methodology may be very useful for land use management decisions and for land use planning in gully-prone regions. Our research contributes to achieve Land Degradation Neutrality as will help to design remediation programs to control non-sustainable soil erosion rates.

Highlights

  • Soil erosion in arid and semi-arid regions is one of the important factors that should be taken into consideration in land use planning [1,2,3]

  • After determining the relative weights of the Gully Erosion Conditioning Factors (GECFs) using IoE model and the spatial relationships between GECFs and gullies in the study area using the WoE model, the two models are integrated to improve performance and decrease the disadvantages of each so that, relative weight of GECFs obtained by IoE multiple with weight of GECF classes obtained by WoE using Equation (14): GESMWoE−IoE = WoEElevation × ElevationIoE + WoESlope × SlopeIoE +

  • The area-under-the-curve under-the-curve receiver-operating characteristic (AUROC) graphs graphs were created created for the the training dataset dataset curve) and for for the AUROC graphs were were created for for the training training dataset (success-rate and and for the the validation dataset(prediction-rate(Figure (Figure 9a,b)

Read more

Summary

Introduction

Soil erosion in arid and semi-arid regions is one of the important factors that should be taken into consideration in land use planning [1,2,3]. Soil erosion is a major consequence of environmental and ecological change [4,5,6]. Among the types of erosion, gully erosion most threatens numerous environmental resources and land use sustainability. This threat is not limited to soil degradation, changes in the landscape and/or landcover, limitations of agricultural activities, or the economic exploitation of natural resources. Erosion promotes the initiation and expansion of badlands, promotes floods, lowering of water tables, desertification, and production and transportation of significant volumes of sediments along the watersheds to the coastal and lowlands [8,9,10]

Results
Discussion
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call