Spatial Prediction and Mapping of Gully Erosion Susceptibility Using Machine Learning Techniques in a Degraded Semi-Arid Region of Kenya

Kennedy Were (), Syphyline Kebeney, Harrison Churu, James Mumo Mutio, Ruth Njoroge, Denis Mugaa, Boniface Alkamoi, Wilson Ng’etich and Bal Ram Singh ()
Additional contact information
Kennedy Were: Kenya Agricultural and Livestock Research Organization, Kenya Soil Survey, P.O. Box 14733, Nairobi 00800, Kenya
Syphyline Kebeney: School of Agriculture and Biotechnology, University of Eldoret, P.O. Box 1125, Eldoret 30100, Kenya
Harrison Churu: School of Agriculture and Biotechnology, University of Eldoret, P.O. Box 1125, Eldoret 30100, Kenya
James Mumo Mutio: School of Agriculture and Biotechnology, University of Eldoret, P.O. Box 1125, Eldoret 30100, Kenya
Ruth Njoroge: School of Agriculture and Biotechnology, University of Eldoret, P.O. Box 1125, Eldoret 30100, Kenya
Denis Mugaa: School of Agriculture and Biotechnology, University of Eldoret, P.O. Box 1125, Eldoret 30100, Kenya
Boniface Alkamoi: School of Agriculture and Biotechnology, University of Eldoret, P.O. Box 1125, Eldoret 30100, Kenya
Wilson Ng’etich: School of Agriculture and Biotechnology, University of Eldoret, P.O. Box 1125, Eldoret 30100, Kenya
Bal Ram Singh: Faculty of Environmental Sciences and Natural Resource Management, Norwegian University of Life Sciences, P.O. Box 5003, 1432 Ås, Norway

Land, 2023, vol. 12, issue 4, 1-19

Abstract: This study aimed at (i) developing, evaluating and comparing the performance of support vector machines (SVM), boosted regression trees (BRT), random forest (RF) and logistic regression (LR) models in mapping gully erosion susceptibility, and (ii) determining the important gully erosion conditioning factors (GECFs) in a Kenyan semi-arid landscape. A total of 431 geo-referenced gully erosion points were gathered through a field survey and visual interpretation of high-resolution satellite imagery on Google Earth, while 24 raster-based GECFs were retrieved from the existing geodatabases for spatial modeling and prediction. The resultant models exhibited excellent performance, although the machine learners outperformed the benchmark LR technique. Specifically, the RF and BRT models returned the highest area under the receiver operating characteristic curve (AUC = 0.89 each) and overall accuracy (OA = 80.2%; 79.7%, respectively), followed by the SVM and LR models (AUC = 0.86; 0.85 & OA = 79.1%; 79.6%, respectively). In addition, the importance of the GECFs varied among the models. The best-performing RF model ranked the distance to a stream, drainage density and valley depth as the three most important GECFs in the region. The output gully erosion susceptibility maps can support the efficient allocation of resources for sustainable land management in the area.

Keywords: soil erosion; land degradation; sustainable land management; landscape restoration; spatial prediction; machine learning (search for similar items in EconPapers)
JEL-codes: Q15 Q2 Q24 Q28 Q5 R14 R52 (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://www.mdpi.com/2073-445X/12/4/890/pdf (application/pdf)
https://www.mdpi.com/2073-445X/12/4/890/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jlands:v:12:y:2023:i:4:p:890-:d:1124317

Access Statistics for this article

Land is currently edited by Ms. Carol Ma

More articles in Land from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().