Search

Wetlands play a key role in hydrological and biogeochemical cycles and provide multiple ecosystem services to society. However, reliable data on the extent of global inundated areas and the magnitude of their contribution to local hydrological dynamics remain surprisingly uncertain. Global hydrological models and land surface models (LSMs) include only the most major inundation sources and mechanisms; therefore, quantifying the uncertainties in available data sources remains a challenge. We address these problems by taking a leading global data product on inundation extents (Global Inundation Extent from Multi-Satellites, GIEMS) and matching against predictions from a global hydrodynamic model (Catchment-based Macro-scale Floodplain – CaMa-Flood) driven by runoff data generated by a land surface model (Joint UK Land and Environment Simulator, JULES). The ability of the model to reproduce patterns and dynamics shown by the observational product is assessed in a number of case studies across the tropics, which show that it performs well in large wetland regions, with a good match between corresponding seasonal cycles. At a finer spatial scale, we found that water inputs (e.g. groundwater inflow to wetland) became underestimated in comparison to water outputs (e.g. infiltration and evaporation from wetland) in some wetlands (e.g. Sudd, Tonlé Sap), and the opposite occurred in others (e.g. Okavango) in our model predictions. We also found evidence for an underestimation of low levels of inundation in our satellite-based inundation data (approx. 10 % of total inundation may not be recorded). Additionally, some wetlands display a clear spatial displacement between observed and simulated inundation as a result of overestimation or underestimation of overbank flooding upstream. This study provides timely information on inherent biases in inundation prediction and observation that can contribute to our current ability to make critical predictions of inundation events at both regional and global levels. [ABSTRACT FROM AUTHOR] more...

Neural networks have been shown to be extremely effective rainfall-runoff models, where the river discharge is predicted from meteorological inputs. However, the question remains: what have these models learned? Is it possible to extract information about the learned relationships that map inputs to outputs, and do these mappings represent known hydrological concepts? Small-scale experiments have demonstrated that the internal states of long short-term memory networks (LSTMs), a particular neural network architecture predisposed to hydrological modelling, can be interpreted. By extracting the tensors which represent the learned translation from inputs (precipitation, temperature, and potential evapotranspiration) to outputs (discharge), this research seeks to understand what information the LSTM captures about the hydrological system. We assess the hypothesis that the LSTM replicates real-world processes and that we can extract information about these processes from the internal states of the LSTM. We examine the cell-state vector, which represents the memory of the LSTM, and explore the ways in which the LSTM learns to reproduce stores of water, such as soil moisture and snow cover. We use a simple regression approach to map the LSTM state vector to our target stores (soil moisture and snow). Good correlations (R2>0.8) between the probe outputs and the target variables of interest provide evidence that the LSTM contains information that reflects known hydrological processes comparable with the concept of variable-capacity soil moisture stores. The implications of this study are threefold: (1) LSTMs reproduce known hydrological processes. (2) While conceptual models have theoretical assumptions embedded in the model a priori, the LSTM derives these from the data. These learned representations are interpretable by scientists. (3) LSTMs can be used to gain an estimate of intermediate stores of water such as soil moisture. While machine learning interpretability is still a nascent field and our approach reflects a simple technique for exploring what the model has learned, the results are robust to different initial conditions and to a variety of benchmarking experiments. We therefore argue that deep learning approaches can be used to advance our scientific goals as well as our predictive goals. [ABSTRACT FROM AUTHOR] more...

A regional coupled approach to water cycle prediction is demonstrated for the 4‐month period from November 2013 to February 2014. This provides the first multi‐component analysis of precipitation, soil moisture, river flow and coastal ocean simulations produced by an atmosphere‐land‐ocean coupled system focussed on the United Kingdom (UK), running with horizontal grid spacing of around 1.5 km across all components. The Unified Model atmosphere component, in which convection is explicitly simulated, reproduces the observed UK rainfall accumulation (r2 of 0.95 for water day accumulation), but there is a notable bias in its spatial distribution—too dry over western upland areas and too wet further east. The JULES land surface model soil moisture state is shown to be in broad agreement with a limited number of cosmic‐ray neutron probe observations. A comparison of observed and simulated river flow shows the coupled system is useful for predicting broad scale features, such as distinguishing high and low flow regions and times during the period of interest but are less accurate than optimized hydrological models. The impact of simulated river discharge on NEMO model simulations of coastal ocean state is explored in the coupled modelling framework, with comparisons provided relative to experiments using climatological river input and no river input around the UK coasts. Results show that the freshwater flux around the UK contributes of order 0.2 psu to the mean surface salinity, and comparisons to profile observations give evidence of an improved vertical structure when applying simulated flows. This study represents the first assessment of the coupled system performance from a hydrological perspective, with priorities for future model developments and challenges for evaluation of such systems discussed. [ABSTRACT FROM AUTHOR] more...

Long short-term memory (LSTM) models are recurrent neural networks from the field of deep learning (DL) which have shown promise for time series modelling, especially in conditions when data are abundant. Previous studies have demonstrated the applicability of LSTM-based models for rainfall–runoff modelling; however, LSTMs have not been tested on catchments in Great Britain (GB). Moreover, opportunities exist to use spatial and seasonal patterns in model performances to improve our understanding of hydrological processes and to examine the advantages and disadvantages of LSTM-based models for hydrological simulation. By training two LSTM architectures across a large sample of 669 catchments in GB, we demonstrate that the LSTM and the Entity Aware LSTM (EA LSTM) models simulate discharge with median Nash–Sutcliffe efficiency (NSE) scores of 0.88 and 0.86 respectively. We find that the LSTM-based models outperform a suite of benchmark conceptual models, suggesting an opportunity to use additional data to refine conceptual models. In summary, the LSTM-based models show the largest performance improvements in the north-east of Scotland and in south-east of England. The south-east of England remained difficult to model, however, in part due to the inability of the LSTMs configured in this study to learn groundwater processes, human abstractions and complex percolation properties from the hydro-meteorological variables typically employed for hydrological modelling. [ABSTRACT FROM AUTHOR] more...

Increasingly, the application of models in urban hydrology has undergone a shift toward integrated structures that recognize the interconnected nature of the urban landscape and both the natural and engineered water cycles. Improvements in computational processing during the past few decades have enabled the application of multiple, connected model structures that link previously disparate systems together, incorporating feedbacks and connections. Many applications of integrated models look to assess the impacts of environmental change on physical dynamics and quality of landscapes. Whilst these integrated structures provide a more robust representation of natural dynamics, they often place considerable data requirements on the user, whereby data are required at contrasting spatial and temporal scales which can often transcend multiple disciplines. Concomitantly, our ability to observe complex, natural phenomena at contrasting scales has improved considerably with the advent of increasingly novel monitoring technologies. This has provided a pathway for reducing model uncertainty and improving our confidence in modeled outputs by implementing suitable monitoring regimes. This commentary assesses how component models of an exemplar integrated model have advanced over the past few decades, with a critical focus on the role of monitoring technologies that have enabled better identification of the key physical process. This reduces the uncertainty of processes at contrasting spatial and temporal scales, through a better characterization of feedbacks which then enhances the utility of integrated model applications. WIREs Water 2017, 4:e1177. doi: 10.1002/wat2.1177 For further resources related to this article, please visit the . [ABSTRACT FROM AUTHOR] more...