Abstract
Gully formation through water-induced soil erosion and related to devastating land degradation is often a quasi-normal threat to human life, as it is responsible for huge loss of surface soil. Therefore, gully erosion susceptibility (GES) mapping is necessary in order to reduce the adverse effect of land degradation and diminishes this type of harmful consequences. The principle goal of the present research study is to develop GES maps for the Garhbeta I Community Development (C.D.) Block; West Bengal, India, by using a machine learning algorithm (MLA) of boosted regression tree (BRT), bagging and the ensemble of BRT-bagging with K-fold cross validation (CV) resampling techniques. The combination of the aforementioned MLAs with resampling approaches is state-of-the-art soft computing, not often used in GES evaluation. In further progress of our research work, here we used a total of 20 gully erosion conditioning factors (GECFs) and a total of 199 gully head cut points for modelling GES. The variables’ importance, which is responsible for gully erosion, was determined based on the random forest (RF) algorithm among the several GECFs used in this study. The output result of the model’s performance was validated through a receiver operating characteristics-area under curve (ROC-AUC), sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) statistical analysis. The predicted result shows that the ensemble of BRT-bagging is the most well fitted for GES where AUC value in K-3 fold is 0.972, whereas the value of AUC in sensitivity, specificity, PPV and NPV is 0.94, 0.93, 0.96 and 0.93, respectively, in a training dataset, and followed by the bagging and BRT model. Thus, from the predictive performance of this research study it is concluded that the ensemble of BRT-Bagging can be applied as a new approach for further studies in spatial prediction of GES. The outcome of this work can be helpful to policy makers in implementing remedial measures to minimize damages caused by gully erosion.
Highlights
Erosion is one of the major environmental problems throughout the world, especially in subtropical areas where population pressure and induced activities are severe, and vegetation can often be fairly limited and inadequate in protecting the soil surface from heavy rainfall due to high rate of surface runoff [1]
The findings suggest that the slope, drainage density, profile curvature, geomorphology and soil texture with their values of 76.85 (K2-Fold), 66.71 (K4-Fold), 55.44 (K2-Fold), 52.48 (K4-Fold) and 25.34 (K3-Fold) respectively, are of the greater importance in gully development and their formation, while the rest of the other variables, iron oxide, stream power index (SPI), distance to drainage and lineament density with their value of 0.64 (K4-Fold), 2.21 (K3-Fold), 4.21 (K3-Fold) and 6.41 (K1-Fold) respectively, are of less importance in the occurrence of gullies and their expansion
Stronger knowledge of the conditioning factors impacting the frequency of gully erosion is important for the sustainability of areas prone to soil erosion
Summary
Erosion is one of the major environmental problems throughout the world, especially in subtropical areas where population pressure and induced activities are severe, and vegetation can often be fairly limited and inadequate in protecting the soil surface from heavy rainfall due to high rate of surface runoff [1] It is an essential aspect of soil erosion and land erosion, as well as a significant source of sediment transferred to streams that challenge the sustainable development of the world [2]. A gully is generally described as an erosional deep stream feature formed by running water with a cross-sectional area of >1 ft, which is too wide to be damaged by traditional tillage, and most often occurred in lateritic soils and comparatively in weak rocks of weathered materials [3] This process is regulated by a combination of several important factors, including subsurface movement of water, pipe roof collapse, and overland flow [4]. The bagging ensemble has been used to create a classifier between
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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
