Applying Non-Parametric Bayesian Network to estimate monthly maximum river discharge: potential and challenges

Abstract. Non-Parametric Bayesian Networks (NPBNs) are graphical tools for statistical inference widely used for reliability analysis and risk assessment. However, few hydrological applications can be found in the literature. We therefore explore here the potential of NPBNs to reproduce catchment-scale hydrological dynamics by investigating 240 catchments with contrasting climate across the United States from the CAMELS dataset. First, two networks, one unsaturated (UN-1) and one saturated network (SN-1) based on hydro-meteorological variables are used to generate monthly maximum river discharge considering the catchment as a single element. Then, the saturated network SN-C, based on SN-1 but additionally including physical catchments attributes, is used to model a group of catchments and infer monthly maximum river discharge in ungauged basins based on the attributes similarity. The results indicate that the UN-1 model is suitable for catchments with a positive dependence between precipitation and river discharge, while the SN-1 model can reproduce discharge also in catchments with negative dependence. Furthermore, in ~40 % of the catchments analysed the SN-1 model can reproduce statistical characteristics of discharge, tested via the Kolmogorov-Smirnov (KS) statistic, and Nash-Sutcliffe Efficiencies (NSE) ≥ 0.5. Such catchments receive precipitation mainly in winter and are located in energy-limited regions at low to moderate elevation. Further, the SN-C model, in which the inference process benefits from catchment similarity, can reproduce river discharge statistics in ~10 % of the catchments analysed. However, in these catchments a common dominant physical attribute was not identified. In this study, we show that, once a NPBNs is defined, it is straightforward to infer discharge, when the remaining variables are known. We also show that it is possible to extend the network itself with additional variables, i.e. going from SN-1 to SN-C. Despite these advantages, the results also suggest that there are considerable challenges in defining a suitable NPBN, in particular for predictions in ungauged basins. These are mainly due to the discrepancies in the time scale of the different physical processes generating discharge, the presence of a “memory” in the system, and the Gaussian-copula assumption used by NPBNs for modelling multivariate dependence.

Download Full-text

Non-Parametric Bayesian Networks for Hydrological Studies

10.5194/egusphere-egu2020-13723 ◽

2020 ◽

Author(s):

Elisa Ragno ◽

Markus Hrachowitz ◽

Oswaldo Morales-Nápoles

Keyword(s):

United States ◽

Risk Assessment ◽

Bayesian Networks ◽

River Discharge ◽

The United States ◽

Catchment Scale ◽

New Information ◽

Discharge Estimation ◽

Hydrological Applications ◽

Non Parametric

<p>Non-Parametric Bayesian Networks (NPBNs) are graphical tools for statistical inference when new information become available. They have been widely used for reliability analysis and risk assessment. However, few hydrological applications can be found in the literature. Consequently, we explore the potential of NPBNs for maximum river discharge estimation by investigating a number of catchments with contrasting climate across the United States. Different networks schematizing river discharge generation processes at the catchment scale are built and analysed. Hydro-meteorological forcings and catchment's attributes are retrieved from Catchment Attributes for Large-Sample Studies (CAMELS). We highlight the benefits but also the challenges encountered in the application of NPBNs for river discharge estimation. Finally, we provide insights on how to overcome some of the difficulties met.</p>

Download Full-text

The importance of geology when estimating catchment-scale streamflow characteristics: Application of a new technique for hydrologic similarity and regionalization

10.5194/egusphere-egu21-13979 ◽

2021 ◽

Author(s):

Joseph Janssen ◽

Ali Ameli

Keyword(s):

Research Area ◽

Scientific Understanding ◽

Laboratory Scale ◽

Hydrological Processes ◽

Climate Change Scenarios ◽

Large Set ◽

Ungauged Basins ◽

Catchment Scale ◽

Hydrological Variable ◽

Predictions In Ungauged Basins

<p>Expanding the scientific understanding of global hydrological processes is a key research area for hydrologists. Research in this area can allow hydrologists to make better predictions in ungauged basins and catchments under climate change scenarios. Though hydrological processes are largely understood at a laboratory-scale, catchment-scale processes are much more complex and unknown. Previous studies at the catchment-scale have shown catchment geology is largely irrelevant in determining components of streamflow. Laboratory-scale experiments, however, have revealed that this is unlikely. This contradiction indicates the current techniques for determining hydrological variable importance in the literature are insufficient. In this paper, we quantify the influence of the interaction amongst climatic, geological, and topographical features on a large set of hydrological signatures in snow-dominated regions across North America, using Stable Extrapolative Marginal Contribution Feature Importance. The preliminary results show that when we consider interaction effects among climatic and geophysical features, and remove the influence of correlation, geological features show considerable importance at the catchment scale. We contend that this study contributes to the scientific understanding of catchment-scale hydrological processes, especially in cold, ungauged basins.</p>

Download Full-text

Application of distributed hydrological models for predictions in ungauged basins: a method to quantify predictive uncertainty

Hydrological Processes ◽

10.1002/hyp.9721 ◽

2013 ◽

Vol 28 (4) ◽

pp. 2033-2045 ◽

Cited By ~ 26

Author(s):

R. Cibin ◽

P. Athira ◽

K. P. Sudheer ◽

I. Chaubey

Keyword(s):

Hydrological Models ◽

Ungauged Basins ◽

Predictive Uncertainty ◽

Distributed Hydrological Models ◽

Predictions In Ungauged Basins

Download Full-text

Runoff Predictions in Ungauged Basins Using Sequence-to-Sequence Models

Journal of Hydrology ◽

10.1016/j.jhydrol.2021.126975 ◽

2021 ◽

pp. 126975

Author(s):

Hanlin Yin ◽

Zilong Guo ◽

Xiuwei Zhang ◽

Jiaojiao Chen ◽

Yanning Zhang

Keyword(s):

Ungauged Basins ◽

Predictions In Ungauged Basins

Download Full-text

Estimation of baseflow parameters of variable infiltration capacity model with soil and topography properties for predictions in ungauged basins

Hydrology and Earth System Sciences Discussions ◽

10.5194/hessd-8-7017-2011 ◽

2011 ◽

Vol 8 (4) ◽

pp. 7017-7053 ◽

Cited By ~ 4

Author(s):

Z. Bao ◽

J. Liu ◽

J. Zhang ◽

G. Fu ◽

G. Wang ◽

...

Keyword(s):

Goodness Of Fit ◽

Model Simulation ◽

Parameters Estimation ◽

Model Parameters ◽

Ungauged Basins ◽

Variable Infiltration Capacity ◽

Infiltration Capacity ◽

Ungauged Catchments ◽

Vic Model ◽

Predictions In Ungauged Basins

Abstract. Equifinality is unavoidable when transferring model parameters from gauged catchments to ungauged catchments for predictions in ungauged basins (PUB). A framework for estimating the three baseflow parameters of variable infiltration capacity (VIC) model, directly with soil and topography properties is presented. When the new parameters setting methodology is used, the number of parameters needing to be calibrated is reduced from six to three, that leads to a decrease of equifinality and uncertainty. This is validated by Monte Carlo simulations in 24 hydro-climatic catchments in China. Using the new parameters estimation approach, model parameters become more sensitive and the extent of parameters space will be smaller when a threshold of goodness-of-fit is given. That means the parameters uncertainty is reduced with the new parameters setting methodology. In addition, the uncertainty of model simulation is estimated by the generalised likelihood uncertainty estimation (GLUE) methodology. The results indicate that the uncertainty of streamflow simulations, i.e., confidence interval, is lower with the new parameters estimation methodology compared to that used by original calibration methodology. The new baseflow parameters estimation framework could be applied in VIC model and other appropriate models for PUB.

Download Full-text

Data-driven catchment classification: application to the PUB problem

Hydrology and Earth System Sciences Discussions ◽

10.5194/hessd-8-391-2011 ◽

2011 ◽

Vol 8 (1) ◽

pp. 391-427 ◽

Cited By ~ 2

Author(s):

M. Di Prinzio ◽

A. Castellarin ◽

E. Toth

Keyword(s):

Cross Validation ◽

Principal Component ◽

Annual Runoff ◽

Data Driven ◽

Spatiotemporal Variability ◽

Ungauged Basins ◽

Streamflow Prediction ◽

Streamflow Regime ◽

Predictions In Ungauged Basins ◽

Unsupervised Neural Networks

Abstract. Objective criteria for catchment classification are identified by the scientific community among the key research topics for improving the interpretation and representation of the spatiotemporal variability of streamflow. A promising approach to catchment classification makes use of unsupervised neural networks (Self Organising Maps, SOM's), which organise input data through non-linear techniques depending on the intrinsic similarity of the data themselves. Our study considers ~300 Italian catchments scattered nationwide, for which several descriptors of the streamflow regime and geomorphoclimatic characteristics are available. We qualitatively and quantitatively compare in the context of PUB (Prediction in Ungauged Basins) a reference classification, RC, with four alternative classifications, AC's. RC was identified by using indices of the streamflow regime as input to SOM, whereas AC's were identified on the basis of catchment descriptors that can be derived for ungauged basins. One AC directly adopts the available catchment descriptors as input to SOM. The remaining AC's are identified by applying SOM to two sets of derived variables obtained by applying Principal Component Analysis (PCA, second AC) and Canonical Correlation Analysis (CCA, third and fourth ACs) to the available catchment descriptors. First, we measure the similarity between each AC and RC. Second, we use AC's and RC to regionalize several streamflow indices and we compare AC's with RC in terms of accuracy of streamflow prediction. In particular, we perform an extensive cross-validation to quantify nationwide the accuracy of predictions in ungauged basins of mean annual runoff, mean annual flood, and flood quantiles associated with given exceedance probabilities. Results of the study show that CCA can significantly improve the effectiveness of SOM classifications for the PUB problem.

Download Full-text