TY - JOUR
T1 - Assessment of Roughness Characterization Methods for Data-Driven Predictions
AU - Yang, Jiasheng
AU - Stroh, Alexander
AU - Lee, Sangseung
AU - Bagheri, Shervin
AU - Frohnapfel, Bettina
AU - Forooghi, Pourya
N1 - Publisher Copyright:
© The Author(s) 2024.
PY - 2024/8
Y1 - 2024/8
N2 - A 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 ks. The first type of model, denoted as ENNPS, incorporates the roughness height probability density function (p.d.f.) and power spectrum (PS), while the second type of model, ENNPA, utilizes a finite set of 17 roughness statistical parameters as input variables. Furthermore, a simplified parameter-based model, denoted as ENNPAM, 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 ENNPAM, which is not observed for ENNPA. We hypothesize that the successful training of ENNPAM is attributed to the enhanced training efficiency linked to the lower input dimensionality.
AB - A 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 ks. The first type of model, denoted as ENNPS, incorporates the roughness height probability density function (p.d.f.) and power spectrum (PS), while the second type of model, ENNPA, utilizes a finite set of 17 roughness statistical parameters as input variables. Furthermore, a simplified parameter-based model, denoted as ENNPAM, 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 ENNPAM, which is not observed for ENNPA. We hypothesize that the successful training of ENNPAM is attributed to the enhanced training efficiency linked to the lower input dimensionality.
KW - Machine learning
KW - Roughness
KW - Turbulence
UR - http://www.scopus.com/inward/record.url?scp=85191996825&partnerID=8YFLogxK
U2 - 10.1007/s10494-024-00549-z
DO - 10.1007/s10494-024-00549-z
M3 - Journal article
AN - SCOPUS:85191996825
SN - 1386-6184
VL - 113
SP - 275
EP - 292
JO - Flow, Turbulence and Combustion
JF - Flow, Turbulence and Combustion
IS - 2
ER -