High-resolution soil erodibility K-factor estimation using machine learning generated soil dataset and soil pH levels
Soil Erodibility Factor (K-factor) is a crucial component of a widely used equation for soil erosion assessment known as the USLE (Universal Soil Loss Equation) or its revised version – RUSLE. It reflects the potential of the soil of being detached due to rainfalls or runoffs. So far, an extensive n...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Polish Academy of Sciences
2021-07-01
|
| Series: | Geodesy and Cartography |
| Subjects: | |
| Online Access: | https://journals.pan.pl/Content/120363/PDF/04_Mammadli_Gojamanov.pdf |
| _version_ | 1798041028738940928 |
|---|---|
| author | Nurlan Mammadli Magsad Gojamanov |
| author_facet | Nurlan Mammadli Magsad Gojamanov |
| author_sort | Nurlan Mammadli |
| collection | DOAJ |
| description | Soil Erodibility Factor (K-factor) is a crucial component of a widely used equation for soil erosion assessment known as the USLE (Universal Soil Loss Equation) or its revised version – RUSLE. It reflects the potential of the soil of being detached due to rainfalls or runoffs. So far, an extensive number of researches provide different approaches and techniques in the evaluation of K-factor. This study applies soil erodibility estimation in the soils of the South Caucasian region using soil data prepared by the International Soil Reference and Information Centre (ISRIC) with 250 m resolution, whereas the recent K-factor estimation implemented in the EU scale was with 500 m resolution. Soil erodibility was assessed using an equation involving soil pH levels. The study utilises Trapesoidal equation of soil data processing and preparation, as suggested by ISRIC, for various layers of surface soil data with up to 0-30 cm depth. Both usage of SoilGrids data and its processing as well as estimation of K-factor applying soil pH levels have demonstrated sufficient capacity and accuracy in soil erodibility assessment. The final output result has revealed the K-factor values varying from 0.037 and more than 0.060 t ha h/MJ mm within the study area. |
| first_indexed | 2024-04-11T22:15:46Z |
| format | Article |
| id | doaj.art-cbe7ead1ebad43fcb866c78a5ed5253a |
| institution | Directory Open Access Journal |
| issn | 2300-2581 |
| language | English |
| last_indexed | 2024-04-11T22:15:46Z |
| publishDate | 2021-07-01 |
| publisher | Polish Academy of Sciences |
| record_format | Article |
| series | Geodesy and Cartography |
| spelling | doaj.art-cbe7ead1ebad43fcb866c78a5ed5253a2022-12-22T04:00:23ZengPolish Academy of SciencesGeodesy and Cartography2300-25812021-07-01vol. 70No 1https://doi.org/10.24425/gac.2021.136679High-resolution soil erodibility K-factor estimation using machine learning generated soil dataset and soil pH levelsNurlan Mammadli0https://orcid.org/0000-0002-8594-5702Magsad Gojamanov1Azerbaijan National Academy Sciences, Baku, AzerbaijanBaku State University, Baku, AzerbaijanSoil Erodibility Factor (K-factor) is a crucial component of a widely used equation for soil erosion assessment known as the USLE (Universal Soil Loss Equation) or its revised version – RUSLE. It reflects the potential of the soil of being detached due to rainfalls or runoffs. So far, an extensive number of researches provide different approaches and techniques in the evaluation of K-factor. This study applies soil erodibility estimation in the soils of the South Caucasian region using soil data prepared by the International Soil Reference and Information Centre (ISRIC) with 250 m resolution, whereas the recent K-factor estimation implemented in the EU scale was with 500 m resolution. Soil erodibility was assessed using an equation involving soil pH levels. The study utilises Trapesoidal equation of soil data processing and preparation, as suggested by ISRIC, for various layers of surface soil data with up to 0-30 cm depth. Both usage of SoilGrids data and its processing as well as estimation of K-factor applying soil pH levels have demonstrated sufficient capacity and accuracy in soil erodibility assessment. The final output result has revealed the K-factor values varying from 0.037 and more than 0.060 t ha h/MJ mm within the study area.https://journals.pan.pl/Content/120363/PDF/04_Mammadli_Gojamanov.pdfsoil erodibilityruslesoilgridsk factorsoil ph |
| spellingShingle | Nurlan Mammadli Magsad Gojamanov High-resolution soil erodibility K-factor estimation using machine learning generated soil dataset and soil pH levels Geodesy and Cartography soil erodibility rusle soilgrids k factor soil ph |
| title | High-resolution soil erodibility K-factor estimation using machine learning generated soil dataset and soil pH levels |
| title_full | High-resolution soil erodibility K-factor estimation using machine learning generated soil dataset and soil pH levels |
| title_fullStr | High-resolution soil erodibility K-factor estimation using machine learning generated soil dataset and soil pH levels |
| title_full_unstemmed | High-resolution soil erodibility K-factor estimation using machine learning generated soil dataset and soil pH levels |
| title_short | High-resolution soil erodibility K-factor estimation using machine learning generated soil dataset and soil pH levels |
| title_sort | high resolution soil erodibility k factor estimation using machine learning generated soil dataset and soil ph levels |
| topic | soil erodibility rusle soilgrids k factor soil ph |
| url | https://journals.pan.pl/Content/120363/PDF/04_Mammadli_Gojamanov.pdf |
| work_keys_str_mv | AT nurlanmammadli highresolutionsoilerodibilitykfactorestimationusingmachinelearninggeneratedsoildatasetandsoilphlevels AT magsadgojamanov highresolutionsoilerodibilitykfactorestimationusingmachinelearninggeneratedsoildatasetandsoilphlevels |