Nonlinear relationships of runoff and sediment yield with natural and anthropogenic factors at event scale

• Published in: Hydrological processes Vol. 36; no. 10
• Main Authors: Huang, Xuan, She, Dongli
• Format: Journal Article
• Language: English
• Published: Hoboken, USA John Wiley & Sons, Inc 01.10.2022; Wiley Subscription Services, Inc
• Subjects: Agricultural land; Antecedent precipitation; Antecedent precipitation index; Anthropogenic factors; boosted regression tree model; Erosion control; event scale; Grasses; Hydrologic processes; Hydrology; loess plateau; nonlinear relationships; Plant cover; Precipitation; Reforestation; Regression analysis; Regression models; Reservoirs; Runoff; Runoff variations; Sediment; Sediment yield; Sediments; Soil erosion; Vegetation; Vegetation cover; Watershed management; Watershed runoff; Watersheds; Loess Plateau
• ISSN: 0885-6087; 1099-1085
• DOI: 10.1002/hyp.14715

Understanding how natural and anthropogenic factors affects the watershed runoff and sediment yield at event scale can provide useful insights into watershed hydrological processes to guide watershed management. This article investigates the nonlinear relationships between natural and anthropogenic factors and event runoff and sediment yield with a boosted regression tree (BRT) model for 38 watersheds within the Loess Plateau in China during 2006 to 2016. The BRT model captures the relative importance of each natural and anthropogenic factors to the variability in runoff and sediment yield. The results show that these relationships are complex and highly nonlinear. The event runoff was most related to NDVI in the grass land (NDVI_g), with a 21.3% contribution, followed by 3‐day antecedent precipitation index (AP3), 10‐day antecedent precipitation index (AP10), precipitation (P), and 7‐day antecedent precipitation index (AP7). For event sediment yield, the strongest factor is AP3, with contribution of 33.3%, followed by P, NDVI in the forest land (NDVI_f), AP7, and NDVI in the crop land (NDVI_c). The marginal effect curves produced by the BRT are often characterized by thresholds. For instance, NDVI_f has the greatest effect on event sediment yield reduction when NDVI_f = 0.42, suggesting that a very intense green coverage is not necessary to achieve maximal soil erosion control. Vegetation coverage and meteorological factors can explain 54.7% of event runoff variation and 55.6% of event sediment yield variation. Our study identify the nonlinear relationships between runoff and sediment yield with vegetation cover and meteorological factors and provide scientific support for the planning of subsequent reforestation projects in the Loess Plateau. Runoff was largely determined by NDVI of grass land. The marginal effect curves test the thresholds of environmental factors. Environmental factors explain 54.7% and 55.6% of event runoff and sediment variation.