Rainfall–runoff modelling is one of the key challenges in the field of hydrology. Various approaches exist, ranging from physically based over conceptual to fully data-driven models. In this paper, we propose a novel data-driven approach, using the Long Short-Term Memory (LSTM) network, a special type of recurrent neural network. The advantage of the LSTM is its ability to learn long-term dependencies between the provided input and output of the network, which are essential for modelling storage effects in e.g. catchments with snow influence. We use 241 catchments of the freely available CAMELS data set to test our approach and also compare the results to the well-known Sacramento Soil Moisture Accounting Model (SAC-SMA) coupled with the Snow-17 snow routine. We also show the potential of the LSTM as a regional hydrological model in which one model predicts the discharge for a variety of catchments. In our last experiment, we show the possibility to transfer process understanding, learned at regional scale, to individual catchments and thereby increasing model performance when compared to a LSTM trained only on the data of single catchments. Using this approach, we were able to achieve better model performance as the SAC-SMA + Snow-17, which underlines the potential of the LSTM for hydrological modelling applications.

Very large and comprehensive datasets are increasingly used in the field of hydrology. Large-sample studies provide insights into the hydrological cycle that might not be available with small-scale studies. LamaH-CE (LArge-SaMple DAta for Hydrology and Environmental Sciences for Central Europe, LamaH for short; the geographical extension “-CE” is omitted in the text and the dataset) is a new dataset for large-sample studies and comparative hydrology in Central Europe. It covers the entire upper Danube to the state border of Austria–Slovakia, as well as all other Austrian catchments including their foreign upstream areas. LamaH covers an area of about 170 000 km² in nine countries, ranging from lowland regions characterized by a continental climate to high alpine zones dominated by snow and ice. Consequently, a wide diversity of properties is present in the individual catchments. We represent this variability in 859 gauged catchments with over 60 catchment attributes, covering topography, climatology, hydrology, land cover, vegetation, soil and geological properties. LamaH further contains a collection of runoff time series as well as meteorological time series. These time series are provided with a daily and hourly resolution. All meteorological and the majority of runoff time series cover a span of over 35 years, which enables long-term analyses with a high temporal resolution. The runoff time series are classified by over 20 attributes including information about human impacts and indicators for data quality and completeness. The structure of LamaH is based on the well-known CAMELS (Catchment Attributes and MEteorology for Large-sample Studies) datasets. In contrast, however, LamaH does not only consider independent basins, covering the full upstream area. Intermediate catchments are covered as well, which allows together with novel attributes the considering of the hydrological network and river topology in applications. We not only describe the basic datasets used and methodology of data preparation but also focus on possible limitations and uncertainties. LamaH contains additionally results of a conceptual hydrological baseline model for checking plausibility of the inputs as well as benchmarking. Potential applications of LamaH are outlined as well, since it is intended to serve as a uniform data basis for further research. LamaH is available at https://doi.org/10.5281/zenodo.4525244 (Klingler et al., 2021).

Various environmental factors influence the outbreak and spread of epidemic or even pandemic events which, in turn, may cause feedbacks on the environment. The novel coronavirus disease (COVID-19) was declared a pandemic on 13 March 2020 and its rapid onset, spatial extent and complex consequences make it a once-in-a-century global disaster. Most countries responded by social distancing measures and severely diminished economic and other activities. Consequently, by the end of April 2020, the COVID-19 pandemic has led to numerous environmental impacts, both positive such as enhanced air and water quality in urban areas, and negative, such as shoreline pollution due to the disposal of sanitary consumables. This study presents an early overview of the observed and potential impacts of the COVID-19 on the environment. We argue that the effects of COVID-19 are determined mainly by anthropogenic factors which are becoming obvious as human activity diminishes across the planet, and the impacts on cities and public health will be continued in the coming years.

Water temperature in rivers is a crucial environmental factor with the ability to alter hydro-ecological as well as socio-economic conditions within a catchment. The development of modelling concepts for predicting river water temperature is and will be essential for effective integrated water management and the development of adaptation strategies to future global changes (e.g. climate change). This study tests the performance of six different machine-learning models: step-wise linear regression, random forest, eXtreme Gradient Boosting (XGBoost), feed-forward neural networks (FNNs), and two types of recurrent neural networks (RNNs). All models are applied using different data inputs for daily water temperature prediction in 10 Austrian catchments ranging from 200 to 96 000 km² and exhibiting a wide range of physiographic characteristics. The evaluated input data sets include combinations of daily means of air temperature, runoff, precipitation and global radiation. Bayesian optimization is applied to optimize the hyperparameters of all applied machine-learning models. To make the results comparable to previous studies, two widely used benchmark models are applied additionally: linear regression and air2stream. With a mean root mean squared error (RMSE) of 0.55 ^∘C, the tested models could significantly improve water temperature prediction compared to linear regression (1.55 ^∘C) and air2stream (0.98 ^∘C). In general, the results show a very similar performance of the tested machine-learning models, with a median RMSE difference of 0.08 ^∘C between the models. From the six tested machine-learning models both FNNs and XGBoost performed best in 4 of the 10 catchments. RNNs are the best-performing models in the largest catchment, indicating that RNNs mainly perform well when processes with long-term dependencies are important. Furthermore, a wide range of performance was observed for different hyperparameter sets for the tested models, showing the importance of hyperparameter optimization. Especially the FNN model results showed an extremely large RMSE standard deviation of 1.60 ^∘C due to the chosen hyperparameters. This study evaluates different sets of input variables, machine-learning models and training characteristics for daily stream water temperature prediction, acting as a basis for future development of regional multi-catchment water temperature prediction models. All preprocessing steps and models are implemented in the open-source R package wateRtemp to provide easy access to these modelling approaches and facilitate further research.

This paper analyses the influence of climate change and land development on future flood risk for selected Austrian flood-prone municipalities. As part of an anticipatory micro-scale risk assessment we simulated four different inundation scenarios for current and future 100- and 300-year floods (which included a climate change allowance), developed scenarios of future settlement growth in floodplains and evaluated changes in flood damage potentials and flood risk until the year 2030. Findings show that both climate change and settlement development significantly increase future levels of flood risk. However, the respective impacts vary strongly across the different cases. The analysis indicates that local conditions, such as the topography of the floodplain, the spatial allocation of vulnerable land uses or the type of land development (e.g. residential, commercial or industrial) in the floodplain are the key determinants of the respective effects of climate change and land development on future levels of flood risk. The case study analysis highlights the general need for a more comprehensive consideration of the local determinants of flood risk in order to increase the effectiveness of an adaptive management of flood risk dynamics.