Charles Perrin

To improve hydrological uncertainty estimation, recent studies have explored machine learning (ML)-based post-processing approaches that enable both enhanced predictive performance and hydrologically informed probabilistic streamflow predictions. Among these, random forests (RF) and their probabilistic extension, quantile random forests (QRF), are increasingly used for their balance between interpretability and performance. However, the application of QRF in regional post-processing settings remains unexplored. In this study, we develop a hydrologically informed QRF post-processor trained in a multi-site setting and compare its performance against a locally (at-site) trained QRF using probabilistic evaluation metrics. The QRF framework leverages simulations and state variables from the GR6J process-based hydrological model, along with readily available catchment descriptors, to predict daily streamflow uncertainty. Our results show that the regional QRF approach is beneficial for hydrological uncertainty estimation, particularly in catchments where local information is insufficient. The findings highlight that multi-site learning enables effective information transfer across hydrologically similar catchments and is especially advantageous for high-flow events. However, the selection of appropriate catchment descriptors is critical to achieving these benefits.

Reliable transferability of hydrological model parameters across time and space remains a challenge for large‑scale water resources assessment. In this study, we investigate whether a differentiable hybrid framework can identify robust and physically coherent parameter sets for annual streamflow modeling across a large‑sample dataset of 3,044 catchments from eight countries. To focus on temporal and spatial transferability analysis, we work at the annual time scale using what we consider to be the simplest possible model: an annual anomaly model of climate elasticities, coupled with the Turc–Mezentsev formulation for the long-term streamflow mean (MQ). A dense neural network is trained in an end‑to‑end fashion to map catchment descriptors to the four model parameters, with gradients propagated through the entire modeling chain. We evaluate the framework using three cross‑validation settings inspired by Klemeš (1986): temporal, spatial, and combined temporal–spatial cross-validation. As a benchmark, we compare the hybrid model against local, catchment‑by‑catchment linear regressions under temporal cross-validation. Our results show that, for temporal transferability, our parameter learning approach outperforms local calibration, yielding higher Nash-Sutcliffe efficiency (NSE) values while producing elasticity coefficients that remain within plausible physical ranges, despite lacking explicit parameter constraints. By contrast, spatial transferability reveals a marked limitation: the anomaly component extrapolates well spatially, but regionalizing MQ from descriptors proves difficult, with MQ errors dominating the loss of performance in spatial and spatiotemporal cross-validation. Experiments with random descriptors further show that our parameter learning uses attributes mainly as catchment identifiers in temporal cross-validation but relies on their physical content to sustain spatial transfer, particularly for MQ. Overall, the study demonstrates that simple differentiable hybrid annual models can learn robust and interpretable anomaly parameters, while highlighting MQ regionalization as the main remaining bottleneck for spatially transferable annual streamflow predictions.

A large transient multi-scenario and multi-model ensemble of future streamflow and groundwater projections in France developed in a national project named Explore2 was recently made available. The main objective of Explore2 is to provide rich and spatially-consistent information for the future evolution of hydrological (surface and groundwater) resources and extremes in France to support adaptation strategies. The Explore2 dataset was obtained using a nested multi-scenario multi-model approach to estimate future uncertainty and to assess local climate at the catchment scale: three greenhouse gas (GHG) emission scenarios, a set of 17 combinations of Global Climate Models and Regional Climate Models (GCM/RCM), and two bias correction methods provide the meteorological forcing for nine surface hydrology models and four groundwater hydrology models (one to simulate groundwater recharge and three to simulate groundwater level). In this paper, we present the methodology underlying the dataset, the evaluation of the hydrological models against daily observations of streamflow and groundwater level, and the key messages on the impact of climate change on both mean river flows and groundwater recharge. This large set of hydrological projections shows a high model agreement on the decrease in seasonal flows in the South of France under the RCP8.5 high-emission scenario, confirming its hotspot status. The surface hydrological models agree on the decrease in summer flows across France under the RCP8.5 scenario, with the exception of northern part France. This area may indeed benefit from more active winter recharge that may counterbalance decrease in summer precipitation and increase in evapotranspiration. In addition to northern France, annual groundwater recharge is projected to increase slightly in the north-east while remaining unchanged elsewhere by the end of the century, according to the RCP8.5 scenario. In the mountainous areas, winter flows will increase as a result of higher air temperature and the high degree of agreement between the models holds regardless of the RCP considered. Unsurprisingly, the higher the GHG emission scenario, the higher the median changes. Most of these changes are organised in France along a north-south gradient, regardless of the RCP considered.

Reliable transferability of hydrological model parameters across time and space remains a challenge for large‑scale water resources assessment. In this study, we investigate whether a differentiable hybrid framework can identify robust and physically coherent parameter sets for annual streamflow modeling across a large‑sample dataset of 3,044 catchments from eight countries. To focus on temporal and spatial transferability analysis, we work at the annual time scale using what we consider to be the simplest possible model: an annual anomaly model of climate elasticities, coupled with the Turc–Mezentsev formulation for the long-term streamflow mean (MQ). A dense neural network is trained in an end‑to‑end fashion to map catchment descriptors to the four model parameters, with gradients propagated through the entire modeling chain. We evaluate the framework using three cross‑validation settings inspired by Klemeš (1986): temporal, spatial, and combined temporal–spatial cross-validation. As a benchmark, we compare the hybrid model against local, catchment‑by‑catchment linear regressions under temporal cross-validation. Our results show that, for temporal transferability, our parameter learning approach outperforms local calibration, yielding higher Nash-Sutcliffe efficiency (NSE) values while producing elasticity coefficients that remain within plausible physical ranges, despite lacking explicit parameter constraints. By contrast, spatial transferability reveals a marked limitation: the anomaly component extrapolates well spatially, but regionalizing MQ from descriptors proves difficult, with MQ errors dominating the loss of performance in spatial and spatiotemporal cross-validation. Experiments with random descriptors further show that our parameter learning uses attributes mainly as catchment identifiers in temporal cross-validation but relies on their physical content to sustain spatial transfer, particularly for MQ. Overall, the study demonstrates that simple differentiable hybrid annual models can learn robust and interpretable anomaly parameters, while highlighting MQ regionalization as the main remaining bottleneck for spatially transferable annual streamflow predictions.

Reliable transferability of hydrological model parameters across time and space remains a challenge for large‑scale water resources assessment. In this study, we investigate whether a differentiable hybrid framework can identify robust and physically coherent parameter sets for annual streamflow modeling across a large‑sample dataset of 3,044 catchments from eight countries. To focus on temporal and spatial transferability analysis, we work at the annual time scale using what we consider to be the simplest possible model: an annual anomaly model of climate elasticities, coupled with the Turc–Mezentsev formulation for the long-term streamflow mean (MQ). A dense neural network is trained in an end‑to‑end fashion to map catchment descriptors to the four model parameters, with gradients propagated through the entire modeling chain. We evaluate the framework using three cross‑validation settings inspired by Klemeš (1986): temporal, spatial, and combined temporal–spatial cross-validation. As a benchmark, we compare the hybrid model against local, catchment‑by‑catchment linear regressions under temporal cross-validation. Our results show that, for temporal transferability, our parameter learning approach outperforms local calibration, yielding higher Nash-Sutcliffe efficiency (NSE) values while producing elasticity coefficients that remain within plausible physical ranges, despite lacking explicit parameter constraints. By contrast, spatial transferability reveals a marked limitation: the anomaly component extrapolates well spatially, but regionalizing MQ from descriptors proves difficult, with MQ errors dominating the loss of performance in spatial and spatiotemporal cross-validation. Experiments with random descriptors further show that our parameter learning uses attributes mainly as catchment identifiers in temporal cross-validation but relies on their physical content to sustain spatial transfer, particularly for MQ. Overall, the study demonstrates that simple differentiable hybrid annual models can learn robust and interpretable anomaly parameters, while highlighting MQ regionalization as the main remaining bottleneck for spatially transferable annual streamflow predictions.

Accurate streamflow forecasts are essential for flood risk management and impact mitigation. In recent years, the coupling of hydrological models with machine learning techniques has gained increasing attention to improve forecast skill, with post-processing emerging among the various existing approaches to correct systematic model errors. However, the interaction between machine learning post-processing, data assimilation and calibration strategies remains insufficiently explored. In this study, we assess the contribution of machine learning-based post-processing to hourly streamflow forecasts across 687 catchments in metropolitan France, covering a wide range of hydroclimatic conditions. Streamflow forecasts are generated using the GR5H-RI hydrological model under three forecasting approaches that differ in calibration strategy and use of data assimilation. Two machine learning models, Random Forest and Multilayer Perceptron, are applied to post-process raw forecasts at lead times of 3, 6, 12 and 24 hours. Forecast performance is evaluated using both continuous skill metrics relative to persistence and threshold-based metrics for flood event detection. Results show that post-processing consistently improves forecast skill at short lead times, especially for catchments with slower hydrological responses. The largest relative gains are observed for open-loop forecasts (i.e., without data assimilation), indicating that post-processing can mitigate the absence of state updating, although it does not fully replace it. Neural network-based post-processing slightly outperforms tree-based models in continuous metrics, while differences are more limited for event detection. Overall, results highlight the complementary roles of data assimilation and machine learning post-processing and demonstrate the potential of such frameworks for operational flood forecasting.

Improving droughts forecasting - whether meteorological, agricultural, or hydrological - is a major challenge for the protection of natural ecosystems and for many economic sectors, including agriculture, energy production, drinking water supply, navigation, and tourism. To provide public water managers with robust low-flow forecasting tools in a context of climate change, the French Office for Biodiversity (OFB) and the Water and Biodiversity Direction (DEB) have supported, since 2011, an initiative aimed at developing a national operational low-flow forecasting platform. This platform, known as PREMHYCE, is the result of a long-term scientific and technical collaboration between INRAE, Météo-France, the University of Lorraine, BRGM, and EDF (Tilmant et al., 2023).PREMHYCE relies on five hydrological models and ensembles of meteorological scenarios to produce probabilistic streamflow forecasts, enabling the estimation of risks of falling below low-flow thresholds (typically vigilance, alert, reinforced alert, or crisis levels). Forecast lead times range from a few days to several weeks, depending on management objectives and catchments considered. The platform provides daily streamflow forecasts at more than 1,300 gauging stations across the French hydrographic network, with lead times of up to 90 days. These forecasts are made available to more than fifty operational services across mainland France and Réunion Island. They are used to anticipate low-flow periods within local and national decision-making bodies.In recent years, the PREMHYCE platform has evolved and been upgraded as part of a research project (ANR CIPRHES, 2021–2025), including developments in meteorological forecasting, hydrological modelling, uncertainty quantification, and improvements of the user interface in close collaboration with end users.This communication aims to present the PREMHYCE forecasting chain, its main functionalities, its range of applications, and its recent developments. Key words: low-flow forecasting, water management, hydrological modelling Reference: Tilmant, F., Bourgin, F., François, D., Le Lay, M., Perrin, C., Rousset, F., Vergnes, J.-P., Willemet, J.-M., Magand, C., and Morel, M. (2023). - PREMHYCE, une plateforme nationale pour la prévision des étiages. Sciences Eaux & Territoires. 42, 17–21, https://doi.org/10.20870/Revue-SET.2023.42.7297. Acknowledgements:This work was financially supported by the French National Research Agency (ANR) (grant ANR-20-CE04-0009) within the CIPRHES project, by the French Office for Biodiversity (OFB) and by the Water and Biodiversity Direction (DEB, at the Ministry for ecology).

Reliable transferability of hydrological model parameters across time and space remains a challenge for large‑scale water resources assessment. In this study, we investigate whether a differentiable hybrid framework can identify robust and physically coherent parameter sets for annual streamflow modeling across a large‑sample dataset of 3,044 catchments from eight countries. To focus on temporal and spatial transferability analysis, we work at the annual time scale using what we consider to be the simplest possible model: an annual anomaly model of climate elasticities, coupled with the Turc–Mezentsev formulation for the long-term streamflow mean (MQ). A dense neural network is trained in an end‑to‑end fashion to map catchment descriptors to the four model parameters, with gradients propagated through the entire modeling chain. We evaluate the framework using three cross‑validation settings inspired by Klemeš (1986): temporal, spatial, and combined temporal–spatial cross-validation. As a benchmark, we compare the hybrid model against local, catchment‑by‑catchment linear regressions under temporal cross-validation. Our results show that, for temporal transferability, our parameter learning approach outperforms local calibration, yielding higher Nash-Sutcliffe efficiency (NSE) values while producing elasticity coefficients that remain within plausible physical ranges, despite lacking explicit parameter constraints. By contrast, spatial transferability reveals a marked limitation: the anomaly component extrapolates well spatially, but regionalizing MQ from descriptors proves difficult, with MQ errors dominating the loss of performance in spatial and spatiotemporal cross-validation. Experiments with random descriptors further show that our parameter learning uses attributes mainly as catchment identifiers in temporal cross-validation but relies on their physical content to sustain spatial transfer, particularly for MQ. Overall, the study demonstrates that simple differentiable hybrid annual models can learn robust and interpretable anomaly parameters, while highlighting MQ regionalization as the main remaining bottleneck for spatially transferable annual streamflow predictions.

To improve hydrological uncertainty estimation, recent studies have explored machine learning (ML)-based post-processing approaches that enable both enhanced predictive performance and hydrologically informed probabilistic streamflow predictions. Among these, random forests (RF) and their probabilistic extension, quantile random forests (QRF), are increasingly used for their balance between interpretability and performance. However, the application of QRF in regional post-processing settings remains unexplored. In this study, we develop a hydrologically informed QRF post-processor trained in a multi-site setting and compare its performance against a locally (at-site) trained QRF using probabilistic evaluation metrics. The QRF framework leverages simulations and state variables from the GR6J hydrological model, along with readily available catchment descriptors, to predict daily streamflow uncertainty. Our results show that the regional QRF approach is beneficial for hydrological uncertainty estimation, particularly in catchments where local information is insufficient. The findings highlight that multi-site learning enables effective information transfer across hydrologically similar catchments and is especially advantageous for high-flow events. However, the selection of appropriate catchment descriptors is critical to achieving these benefits.