Historic flood reconstructions for a safer future: The use of three types of surrogate models

A. Bomers, S.J.M.H. Hulscher, B. van der Meulen, R.M.J. Schielen

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review


Design discharges corresponding to large return periods are generally highly uncertain because of the relatively short data set of measured discharges. The uncertainty in these discharge predictions can be decreased by extending the data set of annual maximum discharges with historic flood events. However, efficient model approaches, in terms of computational times and model accuracy, are required to reconstruct historic flood events. In this study, the suitability of three data-driven surrogate models are evaluated, namely: a linear regression model, an artificial neural network and a support vector machine. The Rhine river flood event of 1809 is used as a case study. Although all types of surrogate models are capable of reproducing the maximum discharge during the 1809 flood event, the use of an artificial neural network resulted in the smallest 95% uncertainty interval.
Original languageEnglish
Title of host publicationRiver Flow 2020
Subtitle of host publicationProceedings of the 10th Conference on Fluvial Hydraulics
EditorsW. Uijttewaal, M.J. Franca, D. Valero, V. Chavarrias, C.Y. Arbos, R. Schielen, A. Crosato
Place of PublicationLondon
PublisherCRC Press / Balkema - Taylor & Francis Group
Number of pages6
ISBN (Electronic)978-1-003-11095-8
ISBN (Print)978-0-367-62773-7
Publication statusPublished - 2020
EventRiver Flow 2020: The 10th Conference on Fluvial Hydraulics - Delft, Netherlands
Duration: 7 Jul 202010 Jul 2020


ConferenceRiver Flow 2020


  • Surrogate modelling
  • historic flood reconstruction
  • discharge prediction
  • uncertainty interval


Dive into the research topics of 'Historic flood reconstructions for a safer future: The use of three types of surrogate models'. Together they form a unique fingerprint.

Cite this