Abstract
Abstract. Flooding is predicted to become more frequent in the coming decades because of global climate change. Recent literature has highlighted the importance of river morphodynamics in controlling flood hazards at the local scale. Abrupt and short-term geomorphic changes can occur after major flood-inducing storms. However, there is still a widespread lack of ability to foresee where and when substantial geomorphic changes will occur, as well as their ramifications for future flood hazards. This study sought to gain an understanding of the implications of major storm events for future flood hazards. For this purpose, we developed self-organizing maps (SOMs) to predict post-storm changes in stage–discharge relationships, based on storm characteristics and watershed properties at 3101 stream gages across the contiguous United States (CONUS). We tested and verified a machine learning (ML) model and its feasibility to (1) highlight the variability of geomorphic responses to flood-inducing storms across various climatic and geomorphologic regions across CONUS and (2) understand the impact of these storms on the stage–discharge relationships at gaged sites as a proxy for changes in flood hazard. The established model allows us to select rivers with stage–discharge relationships that are more prone to change after flood-inducing storms, for which flood recurrence intervals should be revised regularly so that hazard assessment can be up to date with the changing conditions. Results from the model show that, even though post-storm changes in channel conveyance are widespread, the impacts on flood hazard vary across CONUS. The influence of channel conveyance variability on flood risk depends on various hydrologic, geomorphologic, and atmospheric parameters characterizing a particular landscape or storm. The proposed framework can serve as a basis for incorporating channel conveyance adjustments into flood hazard assessment.