Votre recherche

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. Real time operational flood forecasting most often concentrates on issuing streamflow predictions at specific points along the rivers of a watershed. Those points often coincide with gauging stations, and the forecasts can eventually be compared with the corresponding observations for post-event analysis. We are now witnessing an increasing number of studies aimed at also including flood mapping as part of the forecasting system, by feeding the forecasted streamflow to a hydraulics model. While this additional new information (flood extent, depth, velocity, etc.) can potentially be useful for decision makers, it also has the potential to be overwhelming. This is especially true for probabilistic and ensemble forecasting systems. While ensemble streamflow forecasts for a given point in space can be visualized relatively easily, the visualization and communication of probabilistic forecasts for water depth and extent brings additional challenges. The uncertainty becomes three dimensional and it becomes difficult to convey all the important information to support decision-making, while a confusion that could arise from too much information, counter-intuitive interpretation, or simply too much complexity in the representation of the forecast. In this paper, we synthesize the results of a large-scale survey across multiple categories of users of hydrological forecasts (28 government representatives, 52 municipalities, 9 organizations, 37 citizens and farmers, for a total of 139 persons) regarding their preferences in terms of visualizing probabilistic flood forecasts over an entire river reach. Those users have different roles and realities, which influence their needs and preferences. The survey was performed through individual and group interviews during which the interviewees were asked about their needs in terms of hydrological forecasting and their preferences in terms of communication and visualization of the information. In particular, we presented the interviewees with four prototypes representing alternative visualizations of the same probabilistic forecast in order to understand their preferences in terms of colour maps, wording, and the representation of uncertainty. Our results highlight several issues related to the understanding of probabilities in the specific context of visualizing forecasted flood maps. We propose several suggestions for visualizing probabilistic flood maps in order to convey all the relevant information while limiting the confusion of decision makers, and also describe several potential adaptations for different categories of end users.

Abstract. Hybrid hydroclimatic forecasting systems employ data-driven (statistical or machine learning) methods to harness and integrate a broad variety of predictions from dynamical, physics-based models – such as numerical weather prediction, climate, land, hydrology, and Earth system models – into a final prediction product. They are recognized as a promising way of enhancing the prediction skill of meteorological and hydroclimatic variables and events, including rainfall, temperature, streamflow, floods, droughts, tropical cyclones, or atmospheric rivers. Hybrid forecasting methods are now receiving growing attention due to advances in weather and climate prediction systems at subseasonal to decadal scales, a better appreciation of the strengths of AI, and expanding access to computational resources and methods. Such systems are attractive because they may avoid the need to run a computationally expensive offline land model, can minimize the effect of biases that exist within dynamical outputs, benefit from the strengths of machine learning, and can learn from large datasets, while combining different sources of predictability with varying time horizons. Here we review recent developments in hybrid hydroclimatic forecasting and outline key challenges and opportunities for further research. These include obtaining physically explainable results, assimilating human influences from novel data sources, integrating new ensemble techniques to improve predictive skill, creating seamless prediction schemes that merge short to long lead times, incorporating initial land surface and ocean/ice conditions, acknowledging spatial variability in landscape and atmospheric forcing, and increasing the operational uptake of hybrid prediction schemes.

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.