Sedimentation in storm sewers strongly depends on velocity at limit of deposition. This study provides application of a novel stochastic-based model to predict the densimetric Froude number in sewer pipes. In this way, the generalized likelihood uncertainty estimation (GLUE) is used to develop two parametric equations, called GLUE-based four-parameter and GLUE-based two-parameter (GBTP) models to enhance the prediction accuracy of the velocity at the limit of deposition. A number of performance indices are calculated in training and testing phases to compare the developed models with the conventional regression-based equations available in the literature. Based on the obtained performance indices and some graphical techniques, the research findings confirm that a significant enhancement in prediction performance is achieved through the proposed GBTP compared with the previously developed formulas in the literature. To make a quantified comparison between the established and literature models, an index, called improvement index (IM), is computed. This index is a resultant of all the selected indices, and this indicator demonstrates that GBTP is capable of providing the most performance improvement in both training (IMtrain = 9.2%) and testing (IMtrain = 11.3%) phases, comparing with a well-known formula in this context.