Evaluation of USLE and RUSLE estimated soil loss on rangeland.
Abstract
The Universal Soil Loss Equation (USLE) and the Revised Universal Soil Loss Equation (RUSLE 1.06) were evaluated with rainfall simulation data from a diverse set of rangeland vegetation types (8 states, 22 sites, 132 plots). Dry, wet, and very-wet rainfall simulation treatments were applied to the study plots within a 2-day period. The rainfall simulation rate was 65mm/hr for the dry and wet simulation treatments and alternated between 65-130 mm/hr for the very-wet treatment. Average soil loss for all plots for the representative simulation runs were: 0.011 kg/m2, 0.007 kg/m2, and 0.035 kg/m2 for the dry, wet, and very-wet simulation treatments, respectively. The Nash-Sutcliffe Model efficiencies (R2eff) of the USLE for the dry, wet, very-wet simulation treatments and sum of all soil loss measured in the three composite simulation treatments (pooled data) were negative. This indicates that the observed mean measured soil loss from the field rainfall simulations is better than predicted USLE soil loss. The USLE tended to consistently overpredict soil loss for all 3 rainfall simulation treatments. As the USLE predicted values increased in magnitude, the error variance between predicted and observed soil loss increased. Nash-Sutcliffe model efficiency for the RUSLE was also negative, except for the dry run simulation treatment [R2eff = 0.16 using RUSLE cover management (C) subfactor parameters from the RUSLE manual (C(table)), NRCS soil erodibility factor (K); and R2eff = 0.17 with C(table) and K estimated from the soil-erodibility nomograph]. In comparison to the USLE, there was less error between observed and RUSLE predicted soil loss. The RUSLE error variances showed a consistent trend of underpredicted soil loss among the 3 rainfall simulation treatments. When actual field measured root biomass, plant production and soil random roughness values were used in calculating the RUSLE C subfactors: the R2eff values for the dry, wet, very-wet rainfall simulation treatments and the pooled data were all negative.
DOI:10.2458/azu_jrm_v56i3_spaeth