The past few years have witnessed the rise of neural networks (NNs) applications for hydrological time series modeling. By virtue of their capabilities, NN models can achieve unprecedented levels of performance when learning how to solve increasingly complex rainfall-runoff processes via data, making them pivotal for the development of computational hydrologic tasks such as flood predictions. The NN models should, to be considered practical, provide a probabilistic understanding of the model mechanisms and predictions and hints on what could perturb the model. In this paper, we developed two NN models, i.e., Neural Hierarchical Interpolation for Time Series Forecasting (N-HiTS) and Network-Based Expansion Analysis for Interpretable Time Series Forecasting (N-BEATS) with a probabilistic multi-quantile objective and benchmarked them with long short-term memory (LSTM) for flood prediction across two headwater streams in Georgia and North Carolina, USA. To generate a probabilistic prediction, a Multi-Quantile Loss was used to assess the 95th percentile prediction uncertainty (95 PPU) of multiple flooding events. Extensive experiments demonstrated the advantages of hierarchical interpolation and interpretable architecture, where both N-HiTS and N-BEATS provided an average accuracy improvement of ∼ 5 % over the LSTM benchmarking model. On a variety of flooding events, both N-HiTS and N-BEATS demonstrated significant performance improvements over the LSTM benchmark and showcased their probabilistic predictions by specifying a likelihood objective.

The hydrological processes within the catchment are generally influenced by both climate change (CC) and land use/land cover (LULC) change. However, most of the studies are focused on their individual impact on the catchment’s hydrology, while their combined effects have received little attention. This study employs the physically based distributed hydrological model, MIKE SHE, to study the separate and combined effect of climate and LULC change on the hydrology of a mesoscale catchment in the near future (2050s). An Artificial Neural Network–Cellular Automata (ANN-CA) based prediction model was trained to simulate the future LULC map. The future meteorological data under four CC scenarios was obtained from the Royal Netherlands Meteorological Institute (KNMI). The model results showed that the combined effects of CC with LULC changes did not significantly differ from the individual impact of CC on the catchment scale. However, on the local scale, the changes in LULC can significantly influence the variations in groundwater table, soil moisture, and actual evapotranspiration ranging from approximately–6–15%,–9–27%, and–30–10% respectively, depending on the specific change in LULC class and season. In summary, this research provides valuable insights into the complex interactions between LULC changes, CC, and hydrology.

This article presents a methodology for designing and assessing drought-related Nature-Based Solutions (NBS) adaptation strategies on a catchment scale using an integrated hydrological model that simultaneously provides surface water and groundwater results. The Aa of Weerijs catchment, shared between Belgium and the Netherlands, was used for demonstrating the methodology. The model was developed with the MIKE SHE modelling system, using a combination of globally available and local data. Different types of NBS (ditch blocking, infiltration ponds, wetland restoration and heathland restoration) were combined spatially to develop two adaptation strategies with different spatial extents. Their design was based on drought-related Key Performance Indicators (KPIs) linked with water management actions by key stakeholders (bans on water extraction), both on the surface and groundwater. The KPI values were obtained by model simulations under current and future climate conditions, and with the implementation of the two adaptation strategies. The results show that the strategy with a larger spatial extent gives better KPI values, almost eliminating days with no groundwater availability in the downstream part of the catchment, reaching the goal of increased infiltration and groundwater recharge. Additionally, our results show that there is significant accumulation of positive effects from upstream to downstream.

In recent years, numerous flood events have caused loss of life, widespread disruption, and damage across the globe. These devastating impacts highlight the importance of a better understanding of flood generating processes, their impacts, and their variability under climate and landscape changes. Here, we argue that the ability to better model flooding is underpinned by the grand challenge of understanding flood generation mechanisms and potential impacts. To address this challenge, the World Meteorological Organization-Global Energy and Water Exchanges (GEWEX) Hydrometeorology Panel (GHP) aims to establish a Global Flood Crosscutting project to propagate flood modeling and research knowledge across regions and to synthesize results at the global scale. This paper outlines a framework for understanding the dynamics and impacts of runoff generation processes and a rationale for the role of a Global Flood Crosscutting project to address these challenges. Within this Global Flood Crosscutting project, we will establish a common terminology and methods to enable the global research community to exchange knowledge and experiences, and to design experiments toward developing actionable recommendations for more effective flood management practices and policies for improved resilience. This harmonization of rich perspectives across disciplines will foster the co-production of knowledge primed to advance flood research, particularly in the current period of heightened climate variability and rapid change. It will create a new transdisciplinary paradigm for flood science, wherein different dimensions of mechanistic understanding and processes are rigorously considered alongside socioeconomic impacts, early warning communications, and longer-term adaptation to alleviate flood risks in society.