Prediction of Gully Erosion and identifying factors affecting it using the Maximum Entropy Model and BCC-CSM2-MR climate change models for the years 2020-2040 (case study: Alamarvdasht watershed)

Gully erosion is one of the most dangerous types of water erosion that destroys land and disrupts the balance of biological resources and the environment. In this study, the effective factors in gully erosion, prediction and zoning of gully erosion were investigated using the maximum entropy model in Alamarvdasht watershed in Fars province. First, the location of the ditches was prepared through field surveys, aerial photographs and using Google Earth software images, and then the digital layer of the ditches was prepared in point form in the GIS software environment, and in the next step, the basin's physiographic indicators was prepared from in ARC GIS software. In this research, a soil texture map was prepared in GIS software with field operations in the study area and soil sampling and testing, and a land use map and vegetation density was prepared using Landsat satellite images, and then each of the indicators was The ditches were added in the GIS environment. To implement the maximum entropy model, 70% of the data were used for model training and 30% for model testing. In this study, the effect of each other indicators was determined using the Jack Knife test, and finally the most effective indicators were introduced. In order to validate the model, the direction of zoning of gully erosion in the studied area was evaluated using curve (ROC) and area under the curve (AUC). The results of this research showed that climate index, slope, geology, land use, direction of slope and height are the most influential indicators in creating ditch erosion and the AUC=0.997 is at an excellent level.