Time to Update the Split‐Sample Approach in Hydrological Model Calibration

Shen, Helen C.; Tolson, Bryan A.; Mai, Juliane

doi:10.1029/2021wr031523

Cited by 88 publications

(42 citation statements)

References 101 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A validation period is potentially valuable to test model performance, but the downside is that there is less data available for calibration. Shen et al (2022) even propose skipping model validation entirely, based on a study of river discharge data in the United States. In the current study, the validation period (2015-2021) contains the driest years on record while at the same time the pumping stations of Hemmen and Zetten show a distinct increase in pumping rates (see Figure 4).…”

Section: Discussionmentioning

confidence: 99%

Application of Time Series Analysis to Estimate Drawdown From Multiple Well Fields

Brakenhoff¹,

Vonk

Collenteur

et al. 2022

Front. Earth Sci.

View full text Add to dashboard Cite

In 2018–2020, meteorological droughts over Northwestern Europe caused severe declines in groundwater heads with significant damage to groundwater-dependent ecosystems and agriculture. The response of the groundwater system to different hydrological stresses is valuable information for decision-makers. In this paper, a reproducible, data-driven approach using open-source software is proposed to quantify the effects of different hydrological stresses on heads. A scripted workflow was developed using the open-source Pastas software for time series modeling of heads. For each head time series, the best model structure and relevant hydrological stresses (rainfall, evaporation, river stages, and pumping at one or more well fields) were selected iteratively. A new method was applied to model multiple well fields with a single response function, where the response was scaled by the distances between the pumping and observation wells. Selection of the best model structure was performed through reliability checking based on four criteria. The time series model of each observation well represents an independent estimate of the contribution of different hydrological stresses to the head and is based exclusively on observed data. The approach was applied to estimate the drawdown caused by nearby well fields to 250 observed head time series measured at 122 locations in the eastern part of the Netherlands, a country where summer droughts can cause problems, even though the country is better known for problems with too much water. Reliable models were obtained for 126 head time series of which 78 contain one or more well fields as a contributing stress. The spatial variation of the modeled responses to pumping at the well fields show the expected decline with distance from the well field, even though all responses were modeled independently. An example application at one well field showed how the head response to pumping varies per aquifer. Time series analysis was used to determine the feasibility of reducing pumping rates to mitigate large drawdowns during droughts, which depends on the magnitude and response time of the groundwater system to changes in pumping. This is salient information for decision-makers. This article is part of the special issue “Rapid, Reproducible, and Robust Environmental Modeling for Decision Support: Worked Examples and Open-Source Software Tools”.

show abstract

Section: Discussionmentioning

confidence: 99%

Application of Time Series Analysis to Estimate Drawdown From Multiple Well Fields

Brakenhoff¹,

Vonk

Collenteur

et al. 2022

Front. Earth Sci.

View full text Add to dashboard Cite

show abstract

“…As should be expected, the validation results, while not indicating a perfect match to the observations, do indicate the efficacy of the bias correction procedure that has been proposed. We do, however, note that it is advisable for the entire data record to be used to formulate the bias correction model, as a split‐sample approach undertaken with limited data, is sub‐optimal to when the entire data is used (Shen et al., 2022).…”

Section: Data and Applicationsmentioning

confidence: 99%

Correcting Systematic Bias in Climate Model Simulations in the Time‐Frequency Domain

Kusumastuti

Jiang

Mehrotra

et al. 2022

Geophysical Research Letters

View full text Add to dashboard Cite

Systematic biases in General Circulation Model (GCM) simulations require some adjustment before their use in change assessment and adaptation management studies. GCM simulations of the Coupled Model Intercomparison Project 6, although outperform the previous generations of GCMs, exhibit persistent biases in magnitude, variability, and frequency across a range of variables of interest. Here, we propose a novel continuous wavelet‐based bias correction (CWBC) approach to address such biases in the time‐frequency domain. The correction focuses on the magnitude and frequency of the modeled time series, as interpreted via the time‐varying spectrum ascertained using the continuous wavelet transform. The approach is applied to correct systematic biases in the time series of Niño 3.4 sea surface temperature and Arctic sea‐ice extent. The application of CWBC successfully reproduces observed attributes in the bias‐corrected time series of both climate variables for the current climate simulation along with providing a sensible projection for the future.

show abstract

“…NSE was selected despite the Kling-Gupta Efficiency (KGE; Gupta et al, 2009) metric being better suited, solely to ease comparisons between the previous regionalization studies that were strongly reliant on NSE and this current study. All hydrological models were calibrated on the entire period of 1979-2018 as suggested by Arsenault et al (2018); and Shen et al (2022) , while keeping the first available year (1979) of each catchment as the warmup period.…”

Section: Hydrological Models and Calibrationmentioning

confidence: 99%

Continuous streamflow prediction in ungauged basins: Long Short-Term Memory Neural Networks clearly outperform hydrological models

Arsenault¹,

Martel²,

Brunet³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Abstract. This study investigates the ability of Long Short-Term Memory (LSTM) neural networks to perform streamflow prediction at ungauged basins. A series of state-of-the-art, hydrological model-dependent regionalization methods is applied to 148 catchments in Northeast North America and compared to a LSTM model that uses the exact same available data as the hydrological models. While conceptual model-based methods attempt to derive parameterizations at ungauged sites from other similar or nearby catchments, the LSTM model uses all available data in the region to maximize the information content and increase its robustness. Furthermore, by design, the LSTM does not require explicit definition of hydrological processes and derives its own structure from the provided data. The LSTM networks were able to clearly outperform the hydrological models in a leave-one-out cross-validation regionalization setting on most catchments in the study area, with the LSTM model outperforming the hydrological models in 93 to 97 % of catchments depending on the hydrological model. Furthermore, for up to 78 % of the catchments, the LSTM model was able to predict streamflow more accurately on pseudo-ungauged catchments than hydrological models calibrated on the target data, showing that the LSTM model’s structure was better suited to convert the meteorological data and geophysical descriptors into streamflow than the hydrological models even calibrated to those sites in these cases. Furthermore, the LSTM model robustness was tested by varying its hyperparameters, and still outperformed hydrological models in regionalization in almost all cases. Overall, LSTM networks have the potential to change the regionalization research landscape by providing clear improvement pathways over traditional methods in the field of streamflow prediction in ungauged catchments.

show abstract

Time to Update the Split‐Sample Approach in Hydrological Model Calibration

Cited by 88 publications

References 101 publications

Application of Time Series Analysis to Estimate Drawdown From Multiple Well Fields

Application of Time Series Analysis to Estimate Drawdown From Multiple Well Fields

Correcting Systematic Bias in Climate Model Simulations in the Time‐Frequency Domain

Continuous streamflow prediction in ungauged basins: Long Short-Term Memory Neural Networks clearly outperform hydrological models

Contact Info

Product

Resources

About