Geo-statistical based susceptibility mapping of soil erosion and optimization of its causative factors: A conceptual framework
Soil erosion hazard is the second biggest environmental challenges after population growth causing land degradation, desertification and water deterioration. Its impacts on watersheds include loss of soil nutrients, reduced reservoir capacity through siltation which may lead to flood risk, landslide...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Published: |
Taylor's University
2017
|
| Online Access: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85034579883&partnerID=40&md5=25a35002f1f5621122ff21f62d9ea19a http://eprints.utp.edu.my/19674/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Soil erosion hazard is the second biggest environmental challenges after population growth causing land degradation, desertification and water deterioration. Its impacts on watersheds include loss of soil nutrients, reduced reservoir capacity through siltation which may lead to flood risk, landslide, high water turbidity, etc. These problems become more pronounced in human altered mountainous areas through intensive agricultural activities, deforestation and increased urbanization among others. However, due to challenging nature of soil erosion management, there is great interest in assessing its spatial distribution and susceptibility levels. This study is thus intend to review the recent literatures and develop a novel framework for soil erosion susceptibility mapping using geo-statistical based support vector machine (SVM), remote sensing and GIS techniques. The conceptual framework is to bridge the identified knowledge gaps in the area of causative factors’ (CFs) selection. In this research, RUSLE model, field studies and the existing soil erosion maps for the study area will be integrated for the development of inventory map. Spatial data such as Landsat 8, digital soil and geological maps, digital elevation model and hydrological data shall be processed for the extraction of erosion CFs. GIS-based SVM techniques will be adopted for the establishment of spatial relationships between soil erosion and its CFs, and subsequently for the development of erosion susceptibility maps. The results of this study include evaluation of predictive capability of GIS-based SVM in soil erosion mapping and identification of the most influential CFs for erosion susceptibility assessment. This study will serve as a guide to watershed planners and to alleviate soil erosion challenges and its related hazards. © School of Engineering, Taylor’s University. |
|---|