Assessing land use–land cover change and soil erosion potential using a combined approach through remote sensing, RUSLE and random forest algorithm

Abstract

Land use–land cover (LULC) change and the associated risk of soil erosion have become a global environmental concern. We herein presented a geospatial analysis to detect LULC changes (1984–2010) in a Canadian watershed by using object-based classification of Landsat satellite images. We found that the watershed experienced a substantial increase in forest clear cutting and built-up areas. The detected LULC changes were implemented into the Revised Universal Soil Loss Equation (RUSLE) to examine the soil erosion potential. We divided the soil erosion risk into five classes ranging from very low (<6 ton ha⁻¹ year⁻¹) to severe (33 ton ha⁻¹ year⁻¹) levels. The random forest algorithm was then implemented and detected that the topography and LULC conditions of 1999 and 2010 had the most influence on the erosion in 2010. The findings of this study will support efficient LULC management to reduce soil erosion and the consequent degradation of water quality.

Keywords:

• Industrial expansion
• Landsat
• object-based classification
• RUSLEFAC
• watershed

Disclosure statement

No potential conflict of interest was reported by the authors.