@article{Shen-2022-Time,
title = "Time to Update the Split‐Sample Approach in Hydrological Model Calibration",
author = "Shen, Hongren and
Tolson, Bryan A. and
Mai, Juliane",
journal = "Water Resources Research, Volume 58, Issue 3",
volume = "58",
number = "3",
year = "2022",
publisher = "American Geophysical Union (AGU)",
url = "https://gwf-uwaterloo.github.io/gwf-publications/G22-45003",
doi = "10.1029/2021wr031523",
abstract = "Model calibration and validation are critical in hydrological model robustness assessment. Unfortunately, the commonly used split‐sample test (SST) framework for data splitting requires modelers to make subjective decisions without clear guidelines. This large‐sample SST assessment study empirically assesses how different data splitting methods influence post‐validation model testing period performance, thereby identifying optimal data splitting methods under different conditions. This study investigates the performance of two lumped conceptual hydrological models calibrated and tested in 463 catchments across the United States using 50 different data splitting schemes. These schemes are established regarding the data availability, length and data recentness of continuous calibration sub‐periods (CSPs). A full‐period CSP is also included in the experiment, which skips model validation. The assessment approach is novel in multiple ways including how model building decisions are framed as a decision tree problem and viewing the model building process as a formal testing period classification problem, aiming to accurately predict model success/failure in the testing period. Results span different climate and catchment conditions across a 35‐year period with available data, making conclusions quite generalizable. Calibrating to older data and then validating models on newer data produces inferior model testing period performance in every single analysis conducted and should be avoided. Calibrating to the full available data and skipping model validation entirely is the most robust split‐sample decision. Experimental findings remain consistent no matter how model building factors (i.e., catchments, model types, data availability, and testing periods) are varied. Results strongly support revising the traditional split‐sample approach in hydrological modeling.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="Shen-2022-Time">
<titleInfo>
<title>Time to Update the Split‐Sample Approach in Hydrological Model Calibration</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hongren</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bryan</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Tolson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juliane</namePart>
<namePart type="family">Mai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<genre authority="bibutilsgt">journal article</genre>
<relatedItem type="host">
<titleInfo>
<title>Water Resources Research, Volume 58, Issue 3</title>
</titleInfo>
<originInfo>
<issuance>continuing</issuance>
<publisher>American Geophysical Union (AGU)</publisher>
</originInfo>
<genre authority="marcgt">periodical</genre>
<genre authority="bibutilsgt">academic journal</genre>
</relatedItem>
<abstract>Model calibration and validation are critical in hydrological model robustness assessment. Unfortunately, the commonly used split‐sample test (SST) framework for data splitting requires modelers to make subjective decisions without clear guidelines. This large‐sample SST assessment study empirically assesses how different data splitting methods influence post‐validation model testing period performance, thereby identifying optimal data splitting methods under different conditions. This study investigates the performance of two lumped conceptual hydrological models calibrated and tested in 463 catchments across the United States using 50 different data splitting schemes. These schemes are established regarding the data availability, length and data recentness of continuous calibration sub‐periods (CSPs). A full‐period CSP is also included in the experiment, which skips model validation. The assessment approach is novel in multiple ways including how model building decisions are framed as a decision tree problem and viewing the model building process as a formal testing period classification problem, aiming to accurately predict model success/failure in the testing period. Results span different climate and catchment conditions across a 35‐year period with available data, making conclusions quite generalizable. Calibrating to older data and then validating models on newer data produces inferior model testing period performance in every single analysis conducted and should be avoided. Calibrating to the full available data and skipping model validation entirely is the most robust split‐sample decision. Experimental findings remain consistent no matter how model building factors (i.e., catchments, model types, data availability, and testing periods) are varied. Results strongly support revising the traditional split‐sample approach in hydrological modeling.</abstract>
<identifier type="citekey">Shen-2022-Time</identifier>
<identifier type="doi">10.1029/2021wr031523</identifier>
<location>
<url>https://gwf-uwaterloo.github.io/gwf-publications/G22-45003</url>
</location>
<part>
<date>2022</date>
<detail type="volume"><number>58</number></detail>
<detail type="issue"><number>3</number></detail>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T Time to Update the Split‐Sample Approach in Hydrological Model Calibration
%A Shen, Hongren
%A Tolson, Bryan A.
%A Mai, Juliane
%J Water Resources Research, Volume 58, Issue 3
%D 2022
%V 58
%N 3
%I American Geophysical Union (AGU)
%F Shen-2022-Time
%X Model calibration and validation are critical in hydrological model robustness assessment. Unfortunately, the commonly used split‐sample test (SST) framework for data splitting requires modelers to make subjective decisions without clear guidelines. This large‐sample SST assessment study empirically assesses how different data splitting methods influence post‐validation model testing period performance, thereby identifying optimal data splitting methods under different conditions. This study investigates the performance of two lumped conceptual hydrological models calibrated and tested in 463 catchments across the United States using 50 different data splitting schemes. These schemes are established regarding the data availability, length and data recentness of continuous calibration sub‐periods (CSPs). A full‐period CSP is also included in the experiment, which skips model validation. The assessment approach is novel in multiple ways including how model building decisions are framed as a decision tree problem and viewing the model building process as a formal testing period classification problem, aiming to accurately predict model success/failure in the testing period. Results span different climate and catchment conditions across a 35‐year period with available data, making conclusions quite generalizable. Calibrating to older data and then validating models on newer data produces inferior model testing period performance in every single analysis conducted and should be avoided. Calibrating to the full available data and skipping model validation entirely is the most robust split‐sample decision. Experimental findings remain consistent no matter how model building factors (i.e., catchments, model types, data availability, and testing periods) are varied. Results strongly support revising the traditional split‐sample approach in hydrological modeling.
%R 10.1029/2021wr031523
%U https://gwf-uwaterloo.github.io/gwf-publications/G22-45003
%U https://doi.org/10.1029/2021wr031523
Markdown (Informal)
[Time to Update the Split‐Sample Approach in Hydrological Model Calibration](https://gwf-uwaterloo.github.io/gwf-publications/G22-45003) (Shen et al., GWF 2022)
ACL
- Hongren Shen, Bryan A. Tolson, and Juliane Mai. 2022. Time to Update the Split‐Sample Approach in Hydrological Model Calibration. Water Resources Research, Volume 58, Issue 3, 58(3).
