Potential crop yield loss due to early-season weed competition is an important risk associated with postemergence weed management programs. WeedSOFT is a weed management decision support system that has the potential to greatly reduce such risk. Previous research has shown that weed emergence time can greatly affect the accuracy of corn yield loss predictions by WeedSOFT, but our understanding of its predictive accuracy for soybean yield loss as affected by weed emergence time is limited. We conducted experiments at several sites across the Midwestern United States to assess accuracy of WeedSOFT predictions of soybean yield loss associated with mixed-species weed communities established at emergence (VE), cotyledon (VC), first-node (V1), or third-node (V3) soybean. Weed communities across research sites consisted mostly of annual grass species and moderately competitive annual broadleaf species. Soybean yield loss occurred in seven of nine site-years for weed communities established at VE soybean, four site-years for weed communities established at VC soybean, and one site-year for weed communities established at V1 soybean. No soybean yield loss was associated with weed communities established at the V3 stage. Nonlinear regression analyses of predicted and observed soybean yield data pooled over site-years showed that predicted yields were less than observed yields at all soybean growth stages, indicating overestimation of soybean yield loss. Pearson correlation analyses indicated that yield loss functions overestimated the competitive ability of high densities of giant and yellow foxtail with soybean, indicating that adjustments to competitive index values or yield loss function parameters for these species may improve soybean yield loss prediction accuracy and increase the usefulness of WeedSOFT as a weed management decision support system.

Glyphosate applied POST can provide a high level of efficacy on many weed species in soybean, but delayed application beyond optimal weed growth stages might fail to fully protect yield potential. Further, we do not have a good understanding of the extent to which delayed glyphosate application and its associated yield loss is occurring on-farm. Our goal was to characterize on-farm weed communities in glyphosate-resistant soybean just prior to glyphosate application and estimate potential yield loss associated with early-season soybean-weed competition. In field surveys conducted across 64 site-yr in southern Wisconsin in 2008 and 2009, common lambsquarters, velvetleaf, dandelion, Polygonum spp., and Amaranthus spp. were the five most abundant broadleaf weed species across site-years, present in 92, 69, 64, 42, and 50% of all fields, respectively, at average densities of 14, 5, 5, 14, and 10 plants m−2, respectively. Average height of these species was 21 cm or less at or near the time of glyphosate application. Grass and sedge species occurred in 95% of fields at an average density of 41 plants m−2 and height of 21 cm. The mean and median values of total weed density across site-years were 101 and 41 plants m−2, with heights of 19 and 17 cm, respectively. Recommended height for treatment is 15 cm. Glyphosate application occurred on average at V3 to V4 soybean growth stage, which is later than V2 soybean typically targeted to protect yield. Average yield loss predicted by WeedSOFT® was 5% with a mean economic loss of $47 ha−1. Predicted yield loss was greater than 5% on one-fourth of the site-years, all of which were treated at V4 soybean or later. The maximum predicted yield loss was 27%. These results suggest that glyphosate was applied at weed height and soybean growth stages that were greater than optimal to protect yield in many fields across southern Wisconsin. A soil-residual herbicide applied PRE, or a more timely POST application of glyphosate would alleviate the majority of these losses.