A data-centric perspective on the information needed for hydrological uncertainty predictions
Abstract. Uncertainty estimates are fundamental to assess the reliability of predictive models in hydrology. We use the framework of conformal prediction to investigate the impact of temporal and spatial information on uncertainty estimates within hydrological predictions. Integrating recent information significantly enhances overall uncertainty predictions, even with substantial gaps between updates. While local information yields good results on average, it proves to be insufficient for peak-flow predictions. Incorporating global information improves the accuracy of peak-flow bounds, corroborating findings from related studies. Overall, the study underscores the importance of continuous data updates and the integration of global information for robust and efficient uncertainty estimation.
Authors
- Frederik Kratzert (ORCID: https://orcid.org/0000-0002-8897-7689)
- Sepp Hochreiter (ORCID: https://orcid.org/0000-0001-7449-2528)
- Daniel Klotz (ORCID: https://orcid.org/0000-0002-9843-6798)
- Martin Gauch (ORCID: https://orcid.org/0000-0002-4587-898X)
- Grey Nearing (ORCID: https://orcid.org/0000-0001-7031-6770)
- Andreas Auer (ORCID: https://orcid.org/0000-0002-4387-8353)
Institutions
- Johannes Kepler University of Linz (AT)
- Google (United States) (US)
- Helmholtz Centre for Environmental Research (DE)
- Google (Switzerland) (CH)
Publication Details
- Journal
- Hydrology and earth system sciences
- Published
- 2024-09-12
- DOI
- https://doi.org/10.5194/hess-28-4099-2024
- Citations
- 9
- Primary Topic
- Hydrology and Watershed Management Studies
- Type
- article
- Field-Weighted Citation Impact
- 1.81
Funders
- Nvidia
- European Commission
- Austrian Science Fund
- University of Waterloo
- China Scholarship Council
- Österreichische Forschungsförderungsgesellschaft
- Borealis
- Horizon 2020 Framework Programme
- Horizon 2020