Votre recherche
Résultats 2 ressources
-
Abstract In water resources applications (e.g., streamflow, rainfall‐runoff, urban water demand [UWD], etc.), ensemble member selection and ensemble member weighting are two difficult yet important tasks in the development of ensemble forecasting systems. We propose and test a stochastic data‐driven ensemble forecasting framework that uses archived deterministic forecasts as input and results in probabilistic water resources forecasts. In addition to input data and (ensemble) model output uncertainty, the proposed approach integrates both ensemble member selection and weighting uncertainties, using input variable selection and data‐driven methods, respectively. Therefore, it does not require one to perform ensemble member selection and weighting separately. We applied the proposed forecasting framework to a previous real‐world case study in Montreal, Canada, to forecast daily UWD at multiple lead times. Using wavelet‐based forecasts as input data, we develop the Ensemble Wavelet‐Stochastic Data‐Driven Forecasting Framework, the first multiwavelet ensemble stochastic forecasting framework that produces probabilistic forecasts. For the considered case study, several variants of Ensemble Wavelet‐Stochastic Data‐Driven Forecasting Framework, produced using different input variable selection methods (partial correlation input selection and Edgeworth Approximations‐based conditional mutual information) and data‐driven models (multiple linear regression, extreme learning machines, and second‐order Volterra series models), are shown to outperform wavelet‐ and nonwavelet‐based benchmarks, especially during a heat wave (first time studied in the UWD forecasting literature). , Key Points A stochastic data‐driven ensemble framework is introduced for probabilistic water resources forecasting Ensemble member selection and weighting uncertainties are explicitly considered alongside input data and model output uncertainties Wavelet‐based model outputs are used as input to the framework for an urban water demand forecasting study outperforming benchmark methods
-
Abstract Over the past 20 years, the Hydrological Ensemble Prediction Experiment (HEPEX) international community of practice has advanced the science and practice of hydrological ensemble prediction and its application in impact- and risk-based decision-making, fostering innovations through cutting-edge techniques and data that enhance water-related sectors. Here, we present insights from those 20 years on the key priorities for (co)creating broadly applicable hydrological forecasting systems that add value across spatial scales and time horizons. We highlight the advancement of hydrological forecasting chains through rigorous data management that incorporates diverse, high-quality data sources, data assimilation techniques, and the application of artificial intelligence (AI) to improve predictive accuracy. HEPEX has played a critical role in enhancing the reliability of water resources and water-related risk management globally by standardizing ensemble forecasting. This effort complements HEPEX’s broader initiative to strengthen research to operations, making innovative forecasting solutions both practical and accessible. Additionally, efforts have been made toward supporting the United Nations Early Warnings for All initiative through developing robust and reliable early warning systems by means of global training, education and capacity development, and the sharing of technology. Finally, we note that the integration of advanced science, user-centric methods, and global collaboration can provide a solid framework for improving the prediction and management of hydrological extremes, aligning forecasting systems with the dynamic needs of water resource and risk management in a changing climate. To effectively meet future demands, it is crucial to accelerate the integration of innovative science within operational frameworks, fostering adaptable and resilient hydrological forecasting systems globally.