EGU24-16427, updated on 09 Mar 2024
EGU General Assembly 2024
© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.

Development of a river breakup prediction model

Marie Sæteren1, Kolbjørn Engeland1,2, Ånund S. Kvambekk2, and Lena M. Tallaksen1
Marie Sæteren et al.
  • 1University of Oslo, The Faculty of Mathematics and Natural Science, Department of Geosciences, Norway
  • 2The Norwegian Water Resources and Energy Directorate, Oslo, Norway

The dynamic breakup of river ice can initiate ice runs where large masses of ice floes accumulate as ice jams. These ice jams can cause severe inundation and infrastructure damage. Several Norwegian rivers are prone to ice run events, however there are currently no models available in Norway for predicting this specific hydrological phenomenon. Ice-related problems are often dealt with on a site-to-site basis and rely heavily on local knowledge. Other countries, such as Canada and Sweden, have implemented statistical, machine learning and process-based modelling approaches. Being able to accurately predict the timing and severity of ice run and ice jam events improves the ability to take suitable mitigation measures and limit negative consequences. The aim of this work is to develop a model to predict ice run events in two Norwegian rivers, the Beiarn River and the Stjørdal River, and thereby address the need for predicting this hydrological hazard.

The work presented here is part of a master thesis study that will be completed by May 2023. Both Stjørdal and Beiarn River have been monitored by NVE in the latter half of the 20th century, and the timing and severity of historical ice run events are obtained from this data. The predictors are given by hydrometeorological and ice thickness data, both observed and modelled. The Distance Distribution Dynamics (DDD) model developed by NVE is used for simulating daily discharge, and a simple ice growth model from NVE is used for modelling ice thickness. The prediction model itself is a work in progress, initially taking a logistic regression approach. If time allows, other approaches within machine learning such as random forest will be attempted. The dataset is severely imbalanced given the rarity of ice run events and the limited length of the observed series. Different methods are evaluated in terms of their ability to deal with this issue. The ultimate objective of this project is to develop a model providing daily probabilistic forecasts of the likelihood of ice run events in the coming days.

How to cite: Sæteren, M., Engeland, K., Kvambekk, Å. S., and Tallaksen, L. M.: Development of a river breakup prediction model, EGU General Assembly 2024, Vienna, Austria, 14–19 Apr 2024, EGU24-16427,, 2024.