Wilson Ng’eTich
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Wilson Ng’eTich has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Boniface Alkamoi
Department of Seed, Crops and Horticultural Sciences, University of Eldoret, P.O. Box 1125-30100, Eldoret, Kenya
2 shared publications - Denis Mugaa
Department of Soil Science University of Eldoret Kenya
2 shared publications - James Mumo Mutio
Department of Soil Science University of Eldoret Kenya
2 shared publications - Ruth Njoroge
Department of Soil Science University of Eldoret Kenya
2 shared publications - Bal Ram Singh
Norwegian University of Life Sciences
1 shared publication - Fred Wamalwa
Department of Agricultural Economics and Rural Development University of Eldoret Kenya
1 shared publication
Latest Publications
- Open Access
- 7 February 2025
- Published by Agricultural Research Communication Center in Indian Journal Of Agricultural Research
- No. Of
Agropastoralist Community-led Restoration of Degraded Drylands: Factors Influencing Adoption of Soil Conservation Practices in Semi-arid Regions of Kenya
Background: The conventional approach of soil conservation practices in degraded drylands has shown little success. Lack of knowledge on factors influencing inhabitants of such regions to adopt appropriate conservation practices is the primary cause of low adoption. This is because the disseminators of conservation practices assume a one-fit-all design, resulting in a disconnect between them and farmers. Thus, this study aimed to understand factors influencing soil conservation practices in agropastoral dryland communities of semi-arid lowland West Pokot, with a particular interest in terraces. Methods: A concurrent mixed-method approach embedded in a cross-sectional survey was used and data were collected through semi-structured questionnaires, focus group discussions and field measurements of existing terrace attributes. Data were subjected to descriptive analysis, Spearman’s rho correlation, Kruskal Wallis and Chi-Square Test of Independence. Result: The community-driven approaches, gender, size of land and topography are key factors contributing to terrace adoption. Sixty percent of farmers living in degraded high-sloped lands have portions of their farms terraced with average terrace dyke volumes of 103.8±21.45 m³, 105.89±33.13 m³ and 129.6±15.97 m³ for highly sloped, relatively flat and moderately sloppy areas respectively. The study further established terrace dyke sedimentation and limited terrace embarkment reinforcement options as the major challenges facing terracing adoption in the region.
- 7 February 2025
- Published by Agricultural Research Communication Center in Indian Journal Of Agricultural Research
- No. Of
Open AccessAgropastoralist Community-led Restoration of Degraded Drylands: Factors Influencing Adoption of Soil Conservation Practices in Semi-arid Regions of Kenya
Background: The conventional approach of soil conservation practices in degraded drylands has shown little success. Lack of knowledge on factors influencing inhabitants of such regions to adopt appropriate conservation practices is the primary cause of low adoption. This is because the disseminators of conservation practices assume a one-fit-all design, resulting in a disconnect between them and farmers. Thus, this study aimed to understand factors influencing soil conservation practices in agropastoral dryland communities of semi-arid lowland West Pokot, with a particular interest in terraces. Methods: A concurrent mixed-method approach embedded in a cross-sectional survey was used and data were collected through semi-structured questionnaires, focus group discussions and field measurements of existing terrace attributes. Data were subjected to descriptive analysis, Spearman’s rho correlation, Kruskal Wallis and Chi-Square Test of Independence. Result: The community-driven approaches, gender, size of land and topography are key factors contributing to terrace adoption. Sixty percent of farmers living in degraded high-sloped lands have portions of their farms terraced with average terrace dyke volumes of 103.8±21.45 m³, 105.89±33.13 m³ and 129.6±15.97 m³ for highly sloped, relatively flat and moderately sloppy areas respectively. The study further established terrace dyke sedimentation and limited terrace embarkment reinforcement options as the major challenges facing terracing adoption in the region.
- Open Access
Spatial Prediction and Mapping of Gully Erosion Susceptibility Using Machine Learning Techniques in a Degraded Semi-Arid Region of Kenya
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.
Open AccessSpatial Prediction and Mapping of Gully Erosion Susceptibility Using Machine Learning Techniques in a Degraded Semi-Arid Region of Kenya
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.