Sign up Log in
rjees logo



Gully Erosion Susceptibility Mapping using Machine Learning Techniques in Ihioma Community, Imo State, Nigeria

Authors: *Abiodun, O.E., Ohikhueme A.I. And Alabi, A.O.

DOI Info: http://doi.org/10.5281/zenodo.18062130

ABSTRACT

Gully erosion poses significant environmental and socio-economic challenges in many regions worldwide, including the Ihioma community in Imo State, Nigeria. This study employs Machine Learning techniques to predict and map gully erosion susceptibility in the Ihioma community, contributing to the understanding of erosion processes and informing targeted mitigation strategies. Environmental factors such as rainfall, elevation, slope, topographic indices, vegetation cover, and land use/land cover are analyzed to identify primary drivers of erosion vulnerability. The Extreme Gradient Boosting and Random Forest algorithms were compared for their effectiveness in predicting erosion susceptibility, with Random Forest demonstrating superior performance with accuracy of 79.8% and recall of 90.4%. Feature Importance analysis ranked elevation, Normalized Difference Vegetation Index (NDVI), and rainfall in that order as critical variables influencing erosion susceptibility. Using each algorithm, susceptibility maps were created that indicated locations that are likely to experience gully erosion. From the results presented, about 35% of the study area have high susceptibility to gully erosion. The susceptibility map produced could serve as basis for proper planning in a way to reduce the negative impact of gully erosion in the study area.


Affiliations: Department of Surveying and Geoinformatics, University of Lagos, Akoka, Yaba, Lagos, Nigeria.
Keywords: Erosion, Susceptibility, Extreme Gradient Boosting, Random Forest, Mapping
Published date: 2025/12/30

Download Full Text

SUBMIT A MANUSCRIPT

ISSN: 2635-3342 (Print)

ISSN: 2635-3350 (Online)

DOI: In progress

ISI Impact Factor: In progress

Indexing & Abstracting
AR Index google scholar Directory of research journal indexing JIFactor Info base index scientific journal impact factor

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License



(+234) 806 927 5563

Chemical Engineering Department, Faculty of Engineering, University of Benin, PMB 1154, Ugbowo, Benin City, Edo State, Nigeria.