Abstract Flood assessment in coastal river areas is subject to complex dependencies and interactions between flood drivers. In addition, are especially vulnerable climate change, thus its effects should be considered the evaluation of future hazard. present study, we propose a methodology for robust historical flooding areas. It follows continuous simulation approach which hydrologic‐hydraulic modeling cascade run several years, driven by simultaneous series The method differs from other...

The present study was conducted in the Machángara Alto and Chulco rivers, which belong to Paute basin provinces of Azuay Cañar southern Ecuador. Andean watersheds are important providers water supply for human consumption, food supply, energy generation, industrial use, ecosystem services functions many cities Ecuador rest South America. In these regions, accurate quantification prediction flow is challenging, mainly due significant climatic variability sparse monitoring networks. context...

Abstract Accurate hourly streamflow prediction is crucial for managing water resources, particularly in smaller basins with short response times. This study evaluates six deep learning (DL) models, including Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Convolutional Neural Network (CNN), and their hybrids (CNN-LSTM, CNN-GRU, CNN-Recurrent (RNN)), across two Northwest Spain over a ten-year period. Findings reveal that GRU models excel, achieving Nash-Sutcliffe Efficiency (NSE)...

Urban pluvial floods are characterised by a number of features such as the high spatial and temporal resolution needed to capture their dynamics, complexity dual drainage systems lack sewer data availability, which make them very different from other types floods, like coastal or fluvial increase difficulty modelling them. As consequence, most flood management plans do not include rigorous evaluation urban risk. In this paper, we give comprehensive view current state modelling, restricted...

Study Region: The present study was conducted in 24 watersheds located the region of Galicia, northwest Spain, covering an extension approximately 13,000 km2. focus: This is focused on application and evaluation different schemes for streamflow Prediction Ungauged Basins (PUB). MHIA model (Spanish acronym Modelo HIdrológico Agregado), first used to reproduce observed time series discharge several gauged basins. Then, six regionalisation are applied transfer hydrological parameters ungauged...

Abstract Ensemble modelling is a numerical technique used to combine the results of number different individual models in order obtain more robust, better-fitting predictions. The main drawback ensemble modeling identification that can be efficiently combined. present study proposes strategy based on Random-Restart Hill-Climbing algorithm build ANN-based hydrological models. proposed applied case study, using three criteria for identifying model combinations, ensemble, and two ANN training...

Distributed hydrological models based on shallow water equations have gained popularity in recent years for the simulation of storm events, due to their robust and physically routing surface runoff through whole catchment, including hill slopes streams. However, significant challenges arise calibration relatively high computational cost extensive parameter space. This study presents a surrogate-assisted evolutionary algorithm (SA-EA) distributed model 2D equations. A surrogate is used reduce...

<p>Hydrological models are widely used for flood forecasting, continuous streamflow simulation and water resources management. The success of a hydrological model depends on different factors such as its formulation, data availability parameter optimization. There many approaches to identify the optimal sets, which can be categorized in 1) Local search methods 2) Global methods. In group global methods, swarm intelligence could provide an alternative improve application...

<p>In recent years, the application of model ensembles has received increasing attention in hydrological modelling community due to interesting results reported several studies carried out different parts world. The main idea these approaches is combine same or a number models order obtain more robust, better-fitting models, reducing at time uncertainty predictions. techniques for combining range from simple such as averaging simulations, complex least squares, genetic...