Abstract

Gully erosion is one of the most important types of water erosion that causes the destruction of agricultural and range lands in arid and semiarid areas. The main purpose of this study was to produce gully erosion susceptibility maps (GESMs) using R-based data-mining linear discriminant analysis (LDA) and quadratic discriminant analysis (QDA) models and to compare their performances in Shahroud Watershed, Semnan Province, Iran. The important input factors for gully erosion susceptibility assessment were obtained from different sources such as literature reviews and field surveys. First, 172 gully erosion locations were obtained using Google Earth images and extensive field surveys. Then, the gully inventory map was randomly classified into two datasets: 70% (121 gully locations) for training the models and 30% (51 gully locations) for validation purposes. Second, 12 gully erosion conditioning factors, including elevation, slope degree, slope aspect, plan curvature, distance from river, drainage density, convergence index, topography wetness index, distance from road, land use/land cover, normalized difference vegetation index, and lithology were selected. Subsequently, GESMs created using LDA and QDA models in R statistical software and they were divided into four classes including low, moderate, high, and very high. Finally, the validation dataset, which was not used in the modeling process, was considered to validate GESMs using the receiver operating characteristics curve. Results of validation showed that LDA and QDA models with area under the curve values of 0.875 and 0.8620 are good predictors for gully erosion susceptibility mapping. Also, the results indicate that in LDA and QDA models, 13.44% and 22.61% of total area is located in the very high susceptibility class to soil erosion, respectively. The outcome of this research could represent a fundamental tool for sustainable land use planning, protecting the land from water-related soil erosion processes, and gully erosion hazard mitigation in the study area.

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

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.