In the Yangtze River basin of China. We applied a recently popular deep learning (DL) algorithm, Transformer (TSF), and two commonly used DL methods, Long-Short-Term Memory (LSTM) Gated Recurrent Unit (GRU), to evaluate performance TSF in predicting runoff basin. also add main structure TSF, Self-Attention (SA), LSTM GRU models, namely LSTM-SA GRU-SA, investigate whether inclusion SA mechanism can improve prediction capability. Seven climatic observations (mean temperature, maximum...

In comparison to lentic systems, the species composition and community structure of phytoplankton in lotic habitats are still poorly understood. We investigated spatial temporal dynamics a German lowland river, Kielstau catchment, relationships with environmental variables. Among 125 taxa observed, Desmodesmus communis, Pediastrum duplex Discostella steligera were dominant at sites while Tabellaria flocculosa, Euglena sp., Planothidium lanceolatum, Cocconeis placentula Fragilaria biceps...

Summary Global environmental change entails not only climatic alterations, but also changes in land use. Freshwater ecosystems are particularly sensitive to both of these changes, and their sustainable management requires better information on likely responses. To examine the effects climate use freshwater community, distributions stream macroinvertebrates Changjiang catchment south‐east China were modelled. The present 72 taxa predicted using variables generated by regional climate,...

Abstract The classical ‘decoupled’ approach for fluvial flooding makes use of hydrographs as input boundary conditions. catchment hydrology is determined by empirical semi‐distributed rainfall–runoff models, the flood processes hydrodynamic models. However, urban floods, distributed rainfall set directly (‘direct modelling’ – DRM) to elements 2D model. This ‘integrated approach’ aims include hydrological and hydraulic in one single In this study, both modelling approaches are applied...

Abstract Hydrological models need to be adapted specific hydrological characteristics of the catchment in which they are applied. In lowland region northern Germany, tile drains and depressions prominent features landscape though often neglected modelling on scale. It is shown how these can implemented into Soil Water Assessment Tool (SWAT). For obtaining necessary input data, results from a GIS method derive location artificial drainage areas have been used. Another has developed evaluate...

Abstract Aim Highly complex interactions between the hydrosphere and biosphere, as well multifactorial relationships, characterize interconnecting role of streams rivers different elements a landscape. Applying species distribution models ( SDM s) in these ecosystems requires special attention because are linear systems their abiotic biotic conditions structured fashion with significant influences from upstream/downstream or lateral adjacent areas. Our aim was to develop modelling framework...

A large number of 2D models were originally developed as 1D for the calculation water levels along main course a river. Due to their development distributed models, majority have added precipitation source term. The can now be used quasi-2D hydrodynamic rainfall–runoff (‘HDRRM’). Within direct rainfall method (‘DRM’), there is an approach, referred ‘rain-on-grid’, in which input applied entire catchment area. study contains systematic analysis model behavior HEC-RAS (‘Hydrologic Engineering...

In the Yangtze River basin of China. The emerging Explainable Artificial Intelligence (XAI) methods provide us an opportunity to understand nonlinear relationship that Deep Learning(DL) model learned inside. construction Three Gorges Dam (TGD) has successfully minimized likelihood flooding in basin. XAI can help know behind it. We apply Long Short Term Memory (LSTM) network, conjunction with two methods, SHapley Additive exPlanation (SHAP) and Expected Gradient (EG), do our work.In DL model,...

ABSTRACT Willingness to participate (WP) in community-based management depends on various factors such as a sense of community, perceptions, beliefs, and demographic characteristics. This study first evaluates the WP locals (n = 100) water Ba River Basin – Highlands Vietnam, where ethnic minority groups are living working agricultural sector. The multivariable linear regression model is applied explain through including community (SC), dependance river (DW), perceptions current resource...

Abstract. Lowland areas are characterised by specific properties, such as flat topography, low hydraulic gradients, shallow groundwater, and high potential for water retention in peatland lakes. The investigated mesoscale catchments Stör, Treene Kielstau located Northern Germany within lowland areas. Covering from 50 to 517 km2, these rural have sandy, loamy peaty soils drained fraction open ditches tile drainage. Using the river basin model SWAT, sensitivity analyses were carried out...

The last several years in southern Germany brought below average precipitation and high temperatures, leading to considerable challenges water resource management. Deriving a plausible baseflow estimate is important as it affects aspects of integrated management such usage low flow predictions. aim this study representative catchment the German mountain range identify suitable estimation methods for region. Several different separation methods, including digital filters, mass balance filter...

Abstract Lowland areas are characterized by specific properties, such as flat topography, low hydraulic gradients, shallow groundwater, and high potential for water retention in peatland lakes. These characteristics their dominating hydrological processes have to be assessed considered the analysis modelling of balances lowland catchments. The capabilities challenges mesoscale river basins with SWAT model presented. investigated catchments Stör, Treene Kielstau located northern Germany...

Abstract This study shows a comprehensive simulation of water and sediment fluxes from the catchment to reach scale. We describe application modelling cascade in well researched through connecting stateof- the-art public domain models ArcGIS. Three are used consecutively: (1) hydrological model SWAT evaluate balances, input fields tile drains as function characteristics; (2) onedimensional hydraulic HEC-RAS depict channel erosion sedimentation along 9 km onedimensionally; (3) two-dimensional...