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).

Nitrous oxide (N₂O) is a long-lived greenhouse gas that contributes to global warming. Emissions of N₂O mainly stem from agricultural soils. This review highlights the principal factors from peer-reviewed literature affecting N₂O emissions from agricultural soils, by grouping the factors into three categories: environmental, management and measurement. Within these categories, each impact factor is explained in detail and its influence on N₂O emissions from the soil is summarized. It is also shown how each impact factor influences other impact factors. Process-based simulation models used for estimating N₂O emissions are reviewed regarding their ability to consider the impact factors in simulating N₂O. The model strengths and weaknesses in simulating N₂O emissions from managed soils are summarized. Finally, three selected process-based simulation models (Daily Century (DAYCENT), DeNitrification-DeComposition (DNDC), and Soil and Water Assessment Tool (SWAT)) are discussed that are widely used to simulate N₂O emissions from cropping systems. Their ability to simulate N₂O emissions is evaluated by describing the model components that are relevant to N₂O processes and their representation in the model.

Nearest neighbor (NN) techniques are commonly used in remote sensing, pattern recognition, and statistics to classify objects into a predefined number of categories based on a given set of predictors. These techniques are particularly useful in those cases exhibiting a highly nonlinear relationship between variables. In most studies, the distance measure is adopted a priori. In contrast, we propose a general procedure to find Euclidean metrics in a low-dimensional space (i.e., one in which the number of dimensions is less than the number of predictor variables) whose main characteristic is to minimize the variance of a given class label of all those pairs of points whose distance is less than a predefined value. k-NN is used in each embedded space to determine the possibility that a query belongs to a given class label. The class estimation is carried out by an ensemble of predictions. To illustrate the application of this technique, a typical land cover classification using a Landsat-5 Thematic Mapper scene is presented. Experimental results indicate substantial improvement with regard to the classification accuracy as compared with approaches such as maximum likelihood, linear discriminant analysis, standard k-NN, and adaptive quasi-conformal kernel k-NN.

The main objective of this study was to calibrate and validate the eco-hydrological model Soil and Water Assessment Tool (SWAT) with satellite-based actual evapotranspiration (AET) data from the Global Land Evaporation Amsterdam Model (GLEAM_v3.0a) and from the Moderate Resolution Imaging Spectroradiometer Global Evaporation (MOD16) for the Ogun River Basin (20 292 km²) located in southwestern Nigeria. Three potential evapotranspiration (PET) equations (Hargreaves, Priestley–Taylor and Penman–Monteith) were used for the SWAT simulation of AET. The reference simulations were the three AET variables simulated with SWAT before model calibration took place. The sequential uncertainty fitting technique (SUFI-2) was used for the SWAT model sensitivity analysis, calibration, validation and uncertainty analysis. The GLEAM_v3.0a and MOD16 products were subsequently used to calibrate the three SWAT-simulated AET variables, thereby obtaining six calibrations–validations at a monthly timescale. The model performance for the three SWAT model runs was evaluated for each of the 53 subbasins against the GLEAM_v3.0a and MOD16 products, which enabled the best model run with the highest-performing satellite-based AET product to be chosen. A verification of the simulated AET variable was carried out by (i) comparing the simulated AET of the calibrated model to GLEAM_v3.0b AET, which is a product that has different forcing data than the version of GLEAM used for the calibration, and (ii) assessing the long-term average annual and average monthly water balances at the outlet of the watershed. Overall, the SWAT model, composed of the Hargreaves PET equation and calibrated using the GLEAM_v3.0a data (GS1), performed well for the simulation of AET and provided a good level of confidence for using the SWAT model as a decision support tool. The 95 % uncertainty of the SWAT-simulated variable bracketed most of the satellite-based AET data in each subbasin. A validation of the simulated soil moisture dynamics for GS1 was carried out using satellite-retrieved soil moisture data, which revealed good agreement. The SWAT model (GS1) also captured the seasonal variability of the water balance components at the outlet of the watershed. This study demonstrated the potential to use remotely sensed evapotranspiration data for hydrological model calibration and validation in a sparsely gauged large river basin with reasonable accuracy. The novelty of the study is the use of these freely available satellite-derived AET datasets to effectively calibrate and validate an eco-hydrological model for a data-scarce catchment.