Találati lista | Tudóstér

001-es BibID:	BIBFORM102406
035-os BibID:	(WoS)000794114200001 (Scopus)85129824995
Első szerző:	Ebhuoma Osadolor
Cím:	Soil Erosion Vulnerability Mapping in Selected Rural Communities of uThukela Catchment, South Africa, Using the Analytic Hierarchy Process / Osadolor Ebhuoma, Michael Gebreslasie, Njoya Silas Ngetar, Kwanele Phinzi, Shwarnali Bhattacharjee
Dátum:	2022
ISSN:	2509-9426 2509-9434
Megjegyzések:	Soil erosion remains one of the main causes of land degradation, affecting many countries across the globe including South Africa. In rural communities with much reliance on agriculture, soil erosion is an important threat to food security. Therefore, mapping erosion-prone areas is an essential step towards adopting appropriate erosion mitigation and soil conservation measures. The objectives of this study were to (i) assess and model soil erosion vulnerability based on the Analytic Hierarchy Process (AHP) approach in Hoffenthal and KwaMaye communities within the uThukela Catchment, South Africa; and (ii) identify the relevant sustainable interventions and remedial strategies to combat soil erosion in the study area. The AHP was employed to map soil erosion vulnerability and derive the percentage weights of geo-environmental parameters contributing to soil erosion: rainfall, slope, drainage density, soil type, vegetation cover, and land use/land cover. The AHP model showed that slope, vegetation cover, and rainfall had the most considerable influence on soil erosion with factor weights of 29, 23, and 18%, respectively, in the study area. Further, this study revealed that high-risk soil erosion areas occupy 21% of the total study area, while very high-risk areas are about 14%, and the east and central areas are most vulnerable to soil erosion. Validation of the AHP model (overall accuracy = 85%; kappa coefficient = 0.70) results suggests that the predictive capacity of the model was satisfactory. Therefore, the developed soil erosion vulnerability model can serve as an important planning tool to prioritize areas for soil conservation and erosion management approaches like sustainable agriculture and bioengineering interventions.
Tárgyszavak:	Természettudományok Földtudományok idegen nyelvű folyóiratközlemény külföldi lapban folyóiratcikk
Megjelenés:	Earth Systems and Environment. - 6 (2022), p. 851-864. -
További szerzők:	Gebreslasie, Michael Ngetar Njoya Silas Phinzi, Kwanele (1989-) Bhattacharjee, Shwarnali
Internet cím:	Szerző által megadott URL DOI Intézményi repozitóriumban (DEA) tárolt változat
Borító:
Saját polcon:

001-es BibID:	BIBFORM115323
035-os BibID:	(WoS)001086503900002 (Scopus)85174061140
Első szerző:	Phinzi, Kwanele
Cím:	Understanding the role of training sample size in the uncertainty of high-resolution LULC mapping using random forest / Kwanele Phinzi, Njoya Silas Ngetar, Quoc Bao Pham, Gashaw Gismu Chakilu, Szilárd Szabó
Dátum:	2023
ISSN:	1865-0473 1865-0481
Megjegyzések:	High-resolution sensors onboard satellites are generally reputed for rapidly producing land-use/land-cover (LULC) maps with improved spatial detail. However, such maps are subject to uncertainties due to several factors, including the training sample size. We investigated the effects of different training sample sizes (from 1000 to 12,000 pixels) on LULC classification accuracy using the random forest (RF) classifier. Then, we analyzed classification uncertainties by determining the median and the interquartile range (IQR) of the overall accuracy (OA) values through repeated k-fold cross-validation. Results showed that increasing training pixels significantly improved OA while minimizing model uncertainty. Specifically, larger training samples, ranging from 9000 to 12,000 pixels, exhibited narrower IQRs than smaller samples (1000-2000 pixels). Furthermore, there was a significant variation (Chi2 = 85.073; df = 11; p < 0.001) and a significant trend (J-T = 4641, p < 0.001) in OA values across various training sample sizes. Although larger training samples generally yielded high accuracies, this trend was not always consistent, as the lowest accuracy did not necessarily correspond to the smallest training sample. Nevertheless, models using 9000-11,000 pixels were effective (OA > 96%) and provided an accurate visual representation of LULC. Our findings emphasize the importance of selecting an appropriate training sample size to reduce uncertainties in high-resolution LULC classification.
Tárgyszavak:	Természettudományok Földtudományok idegen nyelvű folyóiratközlemény külföldi lapban folyóiratcikk High-resolution sensor LULC Training sample size Random forest Classification uncertainty
Megjelenés:	Earth Science Informatics. - 16 : 4 (2023), p. 3667-3677. -
További szerzők:	Ngetar Njoya Silas Pham, Quoc Bao Chakilu, Gashaw Gismu Szabó Szilárd (1974-) (geográfus)
Pályázati támogatás:	K138079 Egyéb K138503 Egyéb
Internet cím:	Szerző által megadott URL DOI Intézményi repozitóriumban (DEA) tárolt változat
Borító:
Saját polcon:

001-es BibID:	BIBFORM087952
Első szerző:	Phinzi, Kwanele
Cím:	Comparison of Rusle and Supervised Classification Algorithms for Identifying Erosion-Prone Areas in a Mountainous Rural Landscape / Kwanele Phinzi, Njoya Silas Ngetar, Osadolor Ebhuoma, Szilárd Szabó
Dátum:	2020
Megjegyzések:	The identification of erosion prone areas with reasonably high accuracy is a prerequisite for formulating relevant soil conservation measures especially in rural areas where there is much reliance on subsistence agriculture. The aim of this paper was to compare and exploit the complementary advantage of fusing three independent methods including the Revised Universal Soil Loss Equation (RUSLE) and two supervised image classification algorithms: Random Forest (RF) and Maximum Likelihood (ML). All analyses were conducted using a GIS proprietary software, ArcGIS. The results indicated that RF was the best with the highest overall accuracy (OA), producer's accuracy (PA), and user's accuracy (UA) of 87%, 78%, and 95%, respectively. RUSLE poorly performed relative to other methods, scoring the lowest PA (34%) and OA (66%), but slightly outperformed ML in terms of UA. From the user's perspective, the performance of individual methods was satisfactory with each method achieving an UA of greater than 90% although ML and RUSLE were not satisfactory from the producer's perspective, recording respective PAs of 56% and 34%. When the results from individual methods were fused, the accuracy increased above 90% across all accuracy indices, which is far above the 85% acceptable level for planning and management purposes.
Tárgyszavak:	Természettudományok Földtudományok idegen nyelvű folyóiratközlemény külföldi lapban folyóiratcikk RUSLE supervised classification random forest maximum likelihood soil erosion
Megjelenés:	Carpathian Journal of Earth and Environmental Science. - 15 : 2 (2020), p. 405-413. -
További szerzők:	Ngetar Njoya Silas Ebhuoma Osadolor Szabó Szilárd (1974-) (geográfus)
Pályázati támogatás:	TKP - Thematic Excellence Programme of the Ministry for Innovation and Technology in Hungary (ED 18-1-2019-0028) Egyéb
Internet cím:	Szerző által megadott URL DOI Intézményi repozitóriumban (DEA) tárolt változat
Borító:
Saját polcon:

001-es BibID:	BIBFORM086812
Első szerző:	Phinzi, Kwanele
Cím:	Soil erosion risk assessment in the Umzintlava catchment (T32E), Eastern Cape, South Africa, using RUSLE and random forest algorithm / Phinzi Kwanele, Ngetar Njoya Silas, Ebhuoma Osadolor
Dátum:	2021
ISSN:	0373-6245 2151-2418
Megjegyzések:	The Revised Universal Soil Loss Equation (RUSLE), based on remotely sensed data, is an important tool for assessing erosion prone areas and serves as a guide towards soil conservation efforts. Besides being a crucial data source from which RUSLE parameters can be derived, remotely sensed data can also be used independently to delineate erosion features. This study aims to assess soil erosion risk in the Umzintlava catchment using two independent methods, i.e. RUSLE and Random Forest (RF), and explore the relationship between soil loss and erosion factors as represented by different RUSLE parameters. To achieve this, rainfall, soil, digital elevation, and satellite data were used. The results indicate that a considerable portion (>90%) of the catchment area is of ♭very low' to ♭low' erosion risk, while the remainder suffers ♭moderate' to ♭extremely high' erosion risk. Among erosion factors, the LS-factor (slope length and steepness) showed strong correlation with soil erosion (p < 0.001; R2 = 0.954). This suggests that areas with steep slopes are the most vulnerable to hillslope erosion, whereas gully erosion is prominent in areas with gentle to nearly flat slopes. The integration of RUSLE-derived soil loss and RF-derived erosion features successfully delineated the spatial patterns of soil erosion across the Umzintlava catchment, providing useful information on erosion risk at least costs. This information is instrumental in targeted management interventions to combat soil erosion within the catchment.
Tárgyszavak:	Természettudományok Földtudományok idegen nyelvű folyóiratközlemény külföldi lapban folyóiratcikk Soil erosion risk
Megjelenés:	South African Geographical Journal. - 103 : 2 (2021), p. 139-1624. -
További szerzők:	Ngetar Njoya Silas Ebhuoma Osadolor
Internet cím:	Szerző által megadott URL DOI Intézményi repozitóriumban (DEA) tárolt változat
Borító:
Saját polcon: