The Most Important Hydro-Environmental Drivers Affecting Gully Erosion Occurrence Through Wrapper Methods

This study aimed to draw connections between gully erosion occurrences and hydro-environmental factors in watershed areas that illustrate relationships. For this aim, feature elimination methods help diagnose the most key drivers. So, three Wrapper methods of Sequential Forward Selection (SFS), Sequential Backward Selection (SBS), and Exhaustive Feature Selection (EFS) were taken to account for feature extraction, by considering the Random Forest model as an estimator. Considering the results of the models, the most important identified variables were aspect, drainage density, elevation, distance to road, landuse, and slope. The outcomes of this research procure insights for watershed managers to know how should face gully erosion.

[1]  Ankur Miglani,et al.  Internal Leakage Detection in a Hydraulic Pump using Exhaustive Feature Selection and Ensemble Learning , 2021, 2021 International Conference on Maintenance and Intelligent Asset Management (ICMIAM).

[2]  Richard M. Cruse,et al.  Gully Erosion Susceptibility Mapping in Highly Complex Terrain Using Machine Learning Models , 2021, ISPRS Int. J. Geo Inf..

[3]  Wei Chen,et al.  GIS-Based Machine Learning Algorithms for Gully Erosion Susceptibility Mapping in a Semi-Arid Region of Iran , 2020, Remote. Sens..

[4]  Wei Chen,et al.  GIS-Based Gully Erosion Susceptibility Mapping: A Comparison of Computational Ensemble Data Mining Models , 2020, Applied Sciences.

[5]  Thomas Blaschke,et al.  Machine Learning-Based Gully Erosion Susceptibility Mapping: A Case Study of Eastern India , 2020, Sensors.

[6]  T. Blaschke,et al.  Gully erosion susceptibility mapping (GESM) using machine learning methods optimized by the multi‑collinearity analysis and K-fold cross-validation , 2020 .

[7]  S. V. Razavi-Termeh,et al.  Gully erosion susceptibility mapping using artificial intelligence and statistical models , 2020 .

[8]  H. Pourghasemi,et al.  Gully erosion susceptibility assessment and management of hazard-prone areas in India using different machine learning algorithms. , 2019, The Science of the total environment.

[9]  Hamid Reza Pourghasemi,et al.  Comparison of differences in resolution and sources of controlling factors for gully erosion susceptibility mapping , 2018, Geoderma.

[10]  Chunhua Yan,et al.  Quantitative detection of harmful elements in alloy steel by LIBS technique and sequential backward selection-random forest (SBS-RF) , 2017 .

[11]  M. Conforti,et al.  Geomorphology and GIS analysis for mapping gully erosion susceptibility in the Turbolo stream catchment (Northern Calabria, Italy) , 2011 .

[12]  D. Andina,et al.  Feature selection using Sequential Forward Selection and classification applying Artificial Metaplasticity Neural Network , 2010, IECON 2010 - 36th Annual Conference on IEEE Industrial Electronics Society.

[13]  Ferat Sahin,et al.  A survey on feature selection methods , 2014, Comput. Electr. Eng..