Application of at-site peak-streamflow frequency analyses for very low annual exceedance probabilities

Scientific Investigations Report 2017-5038
Prepared in cooperation with the U.S. Nuclear Regulatory Commission
By: , and 



The U.S. Geological Survey (USGS), in cooperation with the U.S. Nuclear Regulatory Commission, has investigated statistical methods for probabilistic flood hazard assessment to provide guidance on very low annual exceedance probability (AEP) estimation of peak-streamflow frequency and the quantification of corresponding uncertainties using streamgage-specific data. The term “very low AEP” implies exceptionally rare events defined as those having AEPs less than about 0.001 (or 1 × 10–3 in scientific notation or for brevity 10–3). Such low AEPs are of great interest to those involved with peak-streamflow frequency analyses for critical infrastructure, such as nuclear power plants. Flood frequency analyses at streamgages are most commonly based on annual instantaneous peak streamflow data and a probability distribution fit to these data. The fitted distribution provides a means to extrapolate to very low AEPs. Within the United States, the Pearson type III probability distribution, when fit to the base-10 logarithms of streamflow, is widely used, but other distribution choices exist. The USGS-PeakFQ software, implementing the Pearson type III within the Federal agency guidelines of Bulletin 17B (method of moments) and updates to the expected moments algorithm (EMA), was specially adapted for an “Extended Output” user option to provide estimates at selected AEPs from 10–3 to 10–6. Parameter estimation methods, in addition to product moments and EMA, include L-moments, maximum likelihood, and maximum product of spacings (maximum spacing estimation). This study comprehensively investigates multiple distributions and parameter estimation methods for two USGS streamgages (01400500 Raritan River at Manville, New Jersey, and 01638500 Potomac River at Point of Rocks, Maryland). The results of this study specifically involve the four methods for parameter estimation and up to nine probability distributions, including the generalized extreme value, generalized log-normal, generalized Pareto, and Weibull. Uncertainties in streamflow estimates for corresponding AEP are depicted and quantified as two primary forms: quantile (aleatoric [random sampling] uncertainty) and distribution-choice (epistemic [model] uncertainty). Sampling uncertainties of a given distribution are relatively straightforward to compute from analytical or Monte Carlo-based approaches. Distribution-choice uncertainty stems from choices of potentially applicable probability distributions for which divergence among the choices increases as AEP decreases. Conventional goodness-of-fit statistics, such as Cramér-von Mises, and L-moment ratio diagrams are demonstrated in order to hone distribution choice. The results generally show that distribution choice uncertainty is larger than sampling uncertainty for very low AEP values.

Suggested Citation

Asquith, W.H., Kiang, J.E., and Cohn, T.A., 2017, Application of at-site peak-streamflow frequency analyses for very low annual exceedance probabilities: U.S. Geological Survey Scientific Investigation Report 2017–5038, 93 p.,

ISSN: 2328-0328 (online)

Table of Contents

  • Author Roles and Acknowledgments
  • Abstract
  • Introduction
  • Background on Peak-Streamflow Frequency Estimation
  • Methods of Probability Distribution Selection and Estimation
  • At-Site Peak-Streamflow Frequency Analyses for Very Low Annual Exceedance Probabilities
  • Summary
  • Selected References
  • Appendixes
Publication type Report
Publication Subtype USGS Numbered Series
Title Application of at-site peak-streamflow frequency analyses for very low annual exceedance probabilities
Series title Scientific Investigations Report
Series number 2017-5038
DOI 10.3133/sir20175038
Year Published 2017
Language English
Publisher U.S. Geological Survey
Publisher location Reston, VA
Contributing office(s) Office of Surface Water
Description ix, 93 p.
Online Only (Y/N) Y
Google Analytic Metrics Metrics page
Additional publication details