EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Reliability of Prediction Intervals for Local Pier Scour under Distribution Shift: A Comparison of Split Conformal and Conformalized Quantile Regression

Taeyoon Kim, Giryung Kang, Sang-Yeop Lee, Woo-Dong Lee

Journal of Ocean Engineering and Technology · 31.10.2026 · 40 (5) · 588-596

DOI: 10.26748/ksoe.2026.043 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Ocean Engineering and Technology, erschienen am 31.10.2026. Verfasst von Taeyoon Kim und 3 weiteren Autor:innen. Die Arbeit nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Korea Agency for Infrastructure Technology Advancement, Ministry of Land, Infrastructure and Transport.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Point-estimate accuracy for local pier scour has improved; however, bridge-foundation design also requires prediction intervals that achieve nominal coverage. Conformal prediction provides finite-sample marginal coverage under exchangeability, but this guarantee may fail when evaluation conditions extend beyond the training range. This study analyzed 1,152 field records from the U.S. Geological Survey pier-scour database, partitioned at the 70% quantile of flow intensity to create a controlled covariate shift. Split conformal, which produces fixed-width intervals, and conformalized quantile regression (CQR), which produces input-dependent intervals, were compared using an extreme gradient boosting model configured for quantile regression over five random seeds. Both methods achieved coverage close to the target levels in the in-distribution region. In the shifted region, at the 90% target, the coverage of split conformal fell to 0.783 (11.7 percentage points below the target), whereas CQR maintained 0.898. The mean CQR interval width increased from 1.116 to 1.432 because of a larger base quantile spread rather than the calibration term. The higher shifted-region coverage of CQR remained consistent across split ratios of 0.6–0.9. Because neither method retains a theoretical guarantee under distribution shift, CQR's higher coverage is empirical and reflects wider intervals rather than improved physical extrapolation.

Förderung

  • Korea Agency for Infrastructure Technology Advancement
  • Ministry of Land, Infrastructure and Transport

Zitieren

APA

Kim, T., Kang, G., Lee, S., & Lee, W. (2026). Reliability of Prediction Intervals for Local Pier Scour under Distribution Shift: A Comparison of Split Conformal and Conformalized Quantile Regression. Journal of Ocean Engineering and Technology, 40(5), 588-596. https://doi.org/10.26748/ksoe.2026.043

Vancouver

Kim T, Kang G, Lee S, Lee W. Reliability of Prediction Intervals for Local Pier Scour under Distribution Shift: A Comparison of Split Conformal and Conformalized Quantile Regression. Journal of Ocean Engineering and Technology. 2026;40(5):588-596. doi:10.26748/ksoe.2026.043

BibTeX
@article{Kim2026,
  author = {Kim, Taeyoon and Kang, Giryung and Lee, Sang-Yeop and Lee, Woo-Dong},
  title = {Reliability of Prediction Intervals for Local Pier Scour under Distribution Shift: A Comparison of Split Conformal and Conformalized Quantile Regression},
  journal = {Journal of Ocean Engineering and Technology},
  year = {2026},
  volume = {40},
  number = {5},
  pages = {588--596},
  doi = {10.26748/ksoe.2026.043}
}
Kostenlos starten →