Gully Head-Cut Distribution Modeling Using Machine Learning Methods—A Case Study of N.W. Iran

Abstract

To more effectively prevent and manage the scourge of gully erosion in arid and semi-arid regions, we present a novel-ensemble intelligence approach-bagging-based alternating decision-tree classifier (bagging-ADTree)-and use it to model a landscape's susceptibility to gully erosion based on 18 gully-erosion conditioning factors. The model's goodness-of-fit and prediction performance are compared to three other machine learning algorithms (single alternating decision tree, rotational-forest-based alternating decision tree (RF-ADTree), and benchmark logistic regression). To achieve this, a gully-erosion inventory was created for the study area, the Chah Mousi watershed, Iran by combining archival records containing reports of gully erosion, remotely sensed data from Google Earth, and geolocated sites of gully head-cuts gathered in a field survey. A total of 119 gully head-cuts were identified and mapped. To train the models' analysis and prediction capabilities, 83 head-cuts (70% of the total) and the corresponding measures of the conditioning factors were input into each model. The results from the models were validated using the data pertaining to the remaining 36 gully locations (30%). Next, the frequency ratio is used to identify which conditioning-factor classes have the strongest correlation with gully erosion. Using random-forest modeling, the relative importance of each of the conditioning factors was determined. Based on the random-forest results, the top eight factors in this study area are distance-to-road, drainage density, distance-to-stream, LU/LC, annual precipitation, topographic wetness index, NDVI, and elevation. Finally, based on goodness-of-fit and AUROC of the success rate curve (SRC) and prediction rate curve (PRC), the results indicate that the bagging-ADTree ensemble model had the best performance, with SRC (0.964) and PRC (0.978). RF-ADTree (SRC = 0.952 and PRC = 0.971), ADTree (SRC = 0.926 and PRC = 0.965), and LR (SRC = 0.867 and PRC = 0.870) were the subsequent best performers. The results also indicate that bagging and RF, as meta-classifiers, improved the performance of the ADTree model as a base classifier. The bagging-ADTree model's results indicate that 24.28% of the study area is classified as having high and very high susceptibility to gully erosion. The new ensemble model accurately Water 2020, 12, 16 2 of 26 identified the areas that are susceptible to gully erosion based on the past patterns of formation, but it also provides highly accurate predictions of future gully development. The novel ensemble method introduced in this research is recommended for use to evaluate the patterns of gullying in arid and semi-arid environments and can effectively identify the most salient conditioning factors that promote the development and expansion of gullies in erosion-susceptible environments.

Machine Learning-Based Gully Erosion Susceptibility Mapping: A Case Study of Eastern India

“…Our results are rational as the tree-based machine learning algorithms minimized bias, variance, and overfitting issues in GES modeling. This is confirmed by Arabameri et al [88], Pourghasemi et al [89], Hembram et al [87], and Gayen et al [90].…”

Evaluation of Recent Advanced Soft Computing Techniques for Gully Erosion Susceptibility Mapping: A Comparative Study

“…Land use underpins geomorphological and hydrological processes by affecting runoff generation, sediment dynamics, and overland flows [89]. LU/LC analysis showed that agricultural and bare landscapes, where soil is often disturbed, where surface water is often concentrated [90][91][92][93], and where the surface is often unprotected by vegetation [88], had the highest susceptibility to GE in our study region. Because GE depends on the lithology of materials at or just below the surface [5] the spatial patterns of sediment origins were evaluated.…”

Landslide Susceptibility Evaluation and Management Using Different Machine Learning Methods in The Gallicash River Watershed, Iran

“…The area under receiver operating characteristics (AUROC) curve was used to test the various models. The AUROC curve is a threshold-independent tool for the measurement of predictive performance [101][102][103][104][105][106]. The AUROC indicates the model's predictive accuracy.…”