Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Recurso digital |
| Language: | |
| Published: |
Zenodo
2025
|
| Online Access: | https://doi.org/10.5281/zenodo.18062130 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866901561387515904 |
|---|---|
| author | Abiodun, O.E. Ohikhueme A.I. Alabi, A.O. |
| author_facet | Abiodun, O.E. Ohikhueme A.I. Alabi, A.O. |
| contents | <p><em><span>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%.<span> </span>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, </span></em><em><span>about 35% of the study area have high susceptibility to gully erosion. <span>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.</span></span></em></p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_18062130 |
| institution | Zenodo |
| language | |
| publishDate | 2025 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | Gully Erosion Susceptibility Mapping using Machine Learning Techniques in Ihioma Community, Imo State, Nigeria Abiodun, O.E. Ohikhueme A.I. Alabi, A.O. <p><em><span>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%.<span> </span>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, </span></em><em><span>about 35% of the study area have high susceptibility to gully erosion. <span>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.</span></span></em></p> |
| title | Gully Erosion Susceptibility Mapping using Machine Learning Techniques in Ihioma Community, Imo State, Nigeria |
| url | https://doi.org/10.5281/zenodo.18062130 |