Prediction of gully erosion and identifying its effective factors in the Khasuyeh watershed in Fars province

Document Type : Research Paper

Authors

1 Assistant Professor, Department of Physical Geography, Faculty of Geographical Sciences and Planning, University of Isfahan, Isfahan, Iran. E-mail: r.zakerinejad@geo.ui.ac.ir.

2 Department of Physical Geography, Faculty of Geographical Sciences and Planning,University of Isfahan, Isfahan, Iran. Email: A.Kahrani@geo.ui.ac.ir

10.22034/gp.2025.65173.3342

Abstract

Water erosion has affected about 99 billion ha of land in the world and is considered as one of the most widespread soil threatening factors in terms of quantity and quality. The aim of this research is to identify the factors affecting the occurrence of gully erosion, assessment and zoning the probability of the Khasyoueh watershed in Fars province using TreeNet models. In this research, first, the location of existing gullies were recorded using satellite images, Google Earth software, and Global Positioning System (GPS), and then the influencing variables in the study area, including topographical indicators (elevation, slope, slope direction, slope length, stream power index, flow depth, topographic wetness index and longitudinal curvature), from the digital elevation model (TanDEM) with a spatial resolution of 12 meters in ArcGIS10.8 and SAGA-GIS software have been extracted and prepared. Other indicators related to vegetation density (NDVI) and land use were prepared using data from satellites data in GIS software. After assigning the values related to the independent indicators to the points taken from the gullies, modeling was done for predicting the areas prone to gully erosion. The TreeNet model has been applied for the prediction of gully erosion. In the modeling process, 70% of the data are considered as training data and 30% of the data are considered as test data. The AUC index for validation of the TreeNet model was recorded as 0.776 for the training data and 0.756 for the test data, which indicates the high accuracy of the model to prediction of susceptible area into gully erosion in the Khasyoueh watershed.

Keywords

Main Subjects