期刊
ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION
卷 9, 期 11, 页码 -出版社
MDPI
DOI: 10.3390/ijgi9110667
关键词
PESERA; USLE; soil erosion; Hungary; land use and land cover; CORINE Land Cover; Random Forest
资金
- National Research, Development and Innovation Office [NKFIH] [KH-126725]
- Higher Education Institutional Excellence Program [NKFIH] [1150-6/2019, 1159-6/2019]
- [EFOP-3.6.1-16-2016-0016]
As soil erosion is still a global threat to soil resources, the estimation of soil loss, particularly at a spatiotemporal setting, is still an existing challenge. The primary aim of our study is the assessment of changes in soil erosion potential in Hungary from 1990 to 2018, induced by the changes in land use and land cover based on CORINE Land Cover data. The modeling scheme included the application and cross-valuation of two internationally applied methods, the Universal Soil Loss Equation (USLE) and the Pan-European Soil Erosion Risk Assessment (PESERA) models. Results indicate that the changes in land cover resulted in a general reduction in predicted erosion rates, by up to 0.28 t/ha/year on average. Analysis has also revealed that the combined application of the two models has reduced the occurrence of extreme predictions, thus, increasing the robustness of the method. Random Forest regression analysis has revealed that the differences between the two models are mainly driven by their sensitivity to slope and land cover, followed by soil parameters. The resulting spatial predictions can be readily applied for qualitative spatial analysis. However, the question of extreme predictions still indicates that quantitative use of the output results should only be carried out with sufficient care.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据