Assessment of Roughness Characterization Methods for Data-Driven Predictions

Abstract

AbstractA comparative analysis is undertaken to explore the impact of various roughness characterization methods as input variables on the performance of data-driven predictive models for estimating the roughness equivalent sand-grain size $$k_s$$ k s . The first type of model, denoted as $$\text {ENN}_\text {PS}$$ ENN PS , incorporates the roughness height probability density function (p.d.f.) and power spectrum (PS), while the second type of model, $$\text {ENN}_\text {PA}$$ ENN PA , utilizes a finite set of 17 roughness statistical parameters as input variables. Furthermore, a simplified parameter-based model, denoted as $$\text {ENN}_\text {PAM}$$ ENN PAM , is considered, which features only 6 input roughness parameters. The models are trained based on identical databases and evaluated using roughness samples similar to the training databases as well as an external testing database based on literature. While the predictions based on p.d.f. and PS achieves a stable error level of around 10% among all considered testing samples, a notable deterioration in performance is observed for the parameter-based models for the external testing database, indicating a lower extrapolating capability to diverse roughness types. Finally, the sensitivity analysis on different types of roughness confirms an effective identification of distinct roughness effects by $$\text {ENN}_\text {PAM}$$ ENN PAM , which is not observed for $$\text {ENN}_\text {PA}$$ ENN PA . We hypothesize that the successful training of $$\text {ENN}_\text {PAM}$$ ENN PAM is attributed to the enhanced training efficiency linked to the lower input dimensionality.