<p>Flood and drought events can lead to severe socio-economic impact and damages. Thus, there is a need for early warnings of such extreme events, especially for decision-makers in sectors like hydropower production, navigation and transportation, agriculture, and hazard management. To improve the predictability of sub-seasonal streamflow, we propose the approach of a hybrid forecasting system, where a conceptual hydrological model PREVAH is combined with a machine learning (ML) model. The PREVAH model provides catchment level hydrological forecasts and the role of the ML model is to emulate a runoff routing scheme. Such a hybrid setup allows the forecasting system to benefit from the statistical power of ML while maintaining the understanding of physical processes from the hydrological model.</p><p>The objective of this study is to investigate the predictability of a hybrid forecasting system to provide monthly streamflow predictions for three recent extreme events. These include the drought event in summer 2018, the drought event in spring 2020, and the flood event in summer 2021 in selected large Swiss rivers. We also investigate different predictability drivers by considering additional input features to the ML model, such as initial streamflow, European weather regime indices, and a hydropower proxy.</p><p>We demonstrate that the proposed hybrid forecasting system has the potential to provide skillful monthly forecasts of the interested events. Informed ML models with additional input features achieve better performance than results obtained using hydrological model outputs only. This study sheds light on using hybrid forecasting for sub-seasonal hydrological predictions to provide useful information for medium-term planning at a monthly time horizon and reduce the impact of flood and drought events.</p>
<p>Switzerland and the nearby alpine countries are not commonly associated with the occurrence of droughts, but in recent years, Switzerland has experienced several unprecedented drought events. As many sectors in the European Alps depend heavily on the water resources, e.g. for hydropower production, navigation and transportation, agriculture, and tourism, it is important for decision makers to have early warnings of drought. Machine learning (ML) approaches have shown potential to compete with traditional hydro-meteorological models. By combining a traditional hydrological model and a ML model in a hybrid setup, the forecasting system is able to benefit from the statistical power of ML while maintaining the understanding of physical processes from the traditional model.</p><p>The objective of this study is to investigate the predictability of a hybrid forecasting system composed of a traditional hydrological model PREVAH and an ensemble of ML algorithms to provide sub-seasonal streamflow and lake level predictions for major rivers and lakes in Switzerland. Uncertainty of the hydro-meteorological prediction chain is accounted for by using 51 hydrological ensemble members,&#160;and the ML uncertainty is accounted for by performing different rounds of initial randomization. We also investigate different drivers of the drought predictability by considering input features such as initial conditions, European weather regime forecasts and a hydropower proxy.</p><p>We are able to demonstrate that the proposed hybrid forecasting system is able to perform runoff routing scheme and provide sub-seasonal forecasts of streamflow and lake level for Swiss basins. Informed ML models with additional input features achieve better performance than those obtained using hydrological model outputs only. In the first half of the forecast period (weeks 1 and 2), model performance is improved by the initial conditions and in the second half (weeks 3 and 4) by the hydropower proxy. Lake level prediction shows promising skill for different basin sizes, whereas the streamflow prediction skill is linked to basin size. This study shines light on the use of hybrid forecasting for sub-seasonal drought prediction to provide useful information for medium- to long-term planning from an integrated risk management perspective.</p>
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.