Partial least-squares regression for linking land-cover patterns to soil erosion and sediment yield in watersheds

There are strong ties between land cover patterns and soil erosion and sediment yield in watersheds. The spatial configuration of land cover has recently become an important aspect of the study of geomorphological processes related to erosion within watersheds. Many studies have used multivariate regression techniques to explore the response of soil erosion and sediment yield to land cover patterns in watersheds. However, many landscape metrics are highly correlated and may result in redundancy, which violates the assumptions of a traditional least-squares approach, thus leading to singular solutions or otherwise biased parameter estimates and confidence intervals. Here, we investigated the landscape patterns within watersheds in the Upper Du River watershed (8973 km2) in China and examined how the spatial patterns of land cover are related to the soil erosion and sediment yield of watersheds using hydrological modeling and partial least-squares regression (PLSR). The results indicate that the watershed soil erosion and sediment yield are closely associated with the land cover patterns. At the landscape level, landscape characteristics, such as Shannon’s diversity index (SHDI), aggregation index (AI), largest patch index (LPI), contagion (CONTAG), and patch cohesion index (COHESION), were identified as the primary metrics controlling the watershed soil erosion and sediment yield. The landscape characteristics in watersheds could account for as much as 65% and 74% of the variation in soil erosion and sediment yield, respectively. Greater interspersion and an increased number of patch land cover types may significantly accelerate soil erosion and increase sediment export. PLSR can be used to simply determine the relationships between land-cover patterns and watershed soil erosion and sediment yield, providing quantitative information to allow decision makers to make better choices regarding landscape planning. With readily available remote sensing data and rapid developments in geographic information system (GIS) technology, this practical and simple PLSR approach could be applied to a variety of other watersheds.