Susceptibility to Gully Erosion: Applying Random Forest (RF) and Frequency Ratio (FR) Approaches to a Small Catchment in Ethiopia

Abstract

Soil erosion by gullies in Ethiopia is causing environmental and socioeconomic problems. A sound soil and water management plan requires accurately predicted gully erosion hotspot areas. Hence, this study develops a gully erosion susceptibility map (GESM) using frequency ratio (FR) and random forest (RF) algorithms. A total of 56 gullies were surveyed, and their extents were derived by digitizing Google Earth imagery. Literature review and a multicollinearity test resulted in 14 environmental variables for the final analysis. Model prediction potential was evaluated using the area under the curve (AUC) method. Results showed that the best prediction accuracy using the FR and RF models was obtained by using the top four most important gully predictor factors: drainage density, elevation, land use, and groundwater table. The notion that the groundwater table is one of the most important gully predictor factors in Ethiopia is a novel and significant quantifiable finding and is critical to the design of effective watershed management plans. Results from separate variable importance analyses showed land cover for Nitisols and drainage density for Vertisols as leading factors determining gully locations. Factors such as texture, stream power index, convergence index, slope length, and plan and profile curvatures were found to have little significance for gully formation in the studied catchment.

Effect of Land Use Change on Gully Erosion Density in the Black Soil Region of Northeast China From 1965 to 2015: A Case Study of the Kedong County

“…While land use/cover change is demonstrably an important factor in gully erosion (Arabameri et al, 2018,Amare et al, 2021, and affects the spatial distribution of erosion, research on how land use change impacts gully erosion intensity is less common. Following classification, validation and field verification of Landsat/TM images for 1965, 2005, and 2015, and this paper presents a detailed assessment of land use changes and its impact on soil erosion for a 50-year period in the black soil area in northeast China.…”

Designing grazing susceptibility to land degradation index (GSLDI) in hilly areas

“…Numerous studies have used random forest (RF) models to evaluate erosion process (e.g., 90 – 92 , gully erosion susceptibility (e.g., 56 – 58 , 93 , floods mapping (e.g., 55 , 94 ) and groundwater nitrate concentration susceptibility 95 . Random decision forests were first introduced by Ho 96 who added randomness in the decision trees with increased accuracy for both training and unseen datasets.…”

Predicting the dust events frequency around a degraded ecosystem and determining the contribution of their controlling factors using gradient boosting-based approaches and game theory

“…Selecting non-correlated attributes that affect the target attribute is one of the main steps before the modeling procedure that helps to reduce the prediction error (Adeboye et al 2014). The tolerance coefficient (TC) is one of the most common techniques used to remove strongly correlated variables and to select non-correlated variables (Amare et al 2021), which was applied in this study. The TC>0.1 indicates a weak correlation between a variable with other predictor variables.…”