Articles | Volume 25, issue 9
https://doi.org/10.5194/hess-25-4947-2021
© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/hess-25-4947-2021
© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
09 Sep 2021
Research article |
| 09 Sep 2021
| 09 Sep 2021
Development of a Wilks feature importance method with improved variable rankings for supporting hydrological inference and modelling
Kailong Li
Faculty of Engineering, University of Regina, Regina, Saskatchewan,
Canada S4S 0A2
Guohe Huang
CORRESPONDING AUTHOR
Faculty of Engineering, University of Regina, Regina, Saskatchewan,
Canada S4S 0A2
Brian Baetz
Department of Civil Engineering, McMaster University, Hamilton,
Ontario, Canada L8S 4L8
Viewed
Total article views: 4,425 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 01 Mar 2021)
| HTML | XML | Total | Supplement | BibTeX | EndNote | |
|---|---|---|---|---|---|---|
| 2,754 | 1,491 | 180 | 4,425 | 394 | 178 | 204 |
- HTML: 2,754
- PDF: 1,491
- XML: 180
- Total: 4,425
- Supplement: 394
- BibTeX: 178
- EndNote: 204
Total article views: 3,414 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 09 Sep 2021)
| HTML | XML | Total | Supplement | BibTeX | EndNote | |
|---|---|---|---|---|---|---|
| 2,173 | 1,078 | 163 | 3,414 | 197 | 171 | 193 |
- HTML: 2,173
- PDF: 1,078
- XML: 163
- Total: 3,414
- Supplement: 197
- BibTeX: 171
- EndNote: 193
Total article views: 1,011 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 01 Mar 2021)
| HTML | XML | Total | Supplement | BibTeX | EndNote | |
|---|---|---|---|---|---|---|
| 581 | 413 | 17 | 1,011 | 197 | 7 | 11 |
- HTML: 581
- PDF: 413
- XML: 17
- Total: 1,011
- Supplement: 197
- BibTeX: 7
- EndNote: 11
Viewed (geographical distribution)
Total article views: 4,425 (including HTML, PDF, and XML)
Thereof 4,160 with geography defined
and 265 with unknown origin.
Total article views: 3,414 (including HTML, PDF, and XML)
Thereof 3,198 with geography defined
and 216 with unknown origin.
Total article views: 1,011 (including HTML, PDF, and XML)
Thereof 962 with geography defined
and 49 with unknown origin.
| Country | # | Views | % |
|---|
| Country | # | Views | % |
|---|
| Country | # | Views | % |
|---|
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
1
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
1
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
1
Cited
25 citations as recorded by crossref.
- Earthquake fatality prediction based on hybrid feature importance assessment: a case study in Yunnan Province, China M. Luo et al. https://doi.org/10.1007/s11069-023-05812-6
- What controls hydrology? An assessment across the contiguous United States through an interpretable machine learning approach K. Li & S. Razavi https://doi.org/10.1016/j.jhydrol.2024.131835
- Stepwise Clustered Ensemble (SCE): An R package for interpretable and robust regression in environmental modeling K. Li et al. https://doi.org/10.1016/j.envsoft.2026.107152
- Dimensionality Reduction in River Water Quality Classification Using Genetic Algorithm and Correlation-Based Feature Selection Y. Riwanto & F. Ningrum https://doi.org/10.29303/jppipa.v11i9.11863
- A physics-driven hybrid transformer model for hydrologic simulation under nonstationary environmental conditions H. Zhang et al. https://doi.org/10.1016/j.jhydrol.2026.135133
- Development of a macroscale distributed hydro-modeling method: Bayesian principal-monotonicity inference G. Cheng et al. https://doi.org/10.1016/j.jhydrol.2022.128803
- Feature extraction of fluorescence excitation-emission matrices using PCA fused with Wilks Λ-statistic and FDA for origin identification and active components content prediction of sweet basil W. Du et al. https://doi.org/10.1007/s11694-024-02935-7
- Temporal-Spatial changes of monthly vegetation growth and their driving forces in the ancient Yellow river irrigation system, China K. Li et al. https://doi.org/10.1016/j.jconhyd.2021.103911
- Can unmanned aerial vehicle laser scanning serve as an effective alternative to traditional field methods for predicting tree growth in even-aged Chinese fir (Cunninghamia lanceolata) plantations? R. Li et al. https://doi.org/10.1007/s10342-026-01945-y
- Development of a physics-informed data-driven model for gaining insights into hydrological processes in irrigated watersheds K. Li et al. https://doi.org/10.1016/j.jhydrol.2022.128323
- Development of a Stepwise‐Clustered Multi‐Catchment Hydrological Model for Quantifying Interactions in Regional Climate‐Runoff Relationships F. Wang et al. https://doi.org/10.1029/2021WR030035
- Transformer-enhanced extraction of operating rules for multi-objective reservoir groups: a min river basin case study M. Yan et al. https://doi.org/10.1016/j.jhydrol.2026.135578
- Determination of soil source using laser induced breakdown spectroscopy combined with feature selection Y. Ding et al. https://doi.org/10.1039/D3JA00133D
- Identifying trustworthiness challenges in deep learning models for continental-scale water quality prediction X. Xia et al. https://doi.org/10.1016/j.ynexs.2025.100104
- Deriving hydrological inferences from a machine learning model to understand the physical drivers of flow duration curves S. Jain et al. https://doi.org/10.1016/j.jhydrol.2025.134687
- Explainable Machine Learning for Streamflow Forecasting: Application to the Bosna River Basin S. Gnjato et al. https://doi.org/10.3390/w18101226
- Benchmark-guided insights into hybrid process-based-deep learning models for continental-scale streamflow prediction across the United States D. Sourya et al. https://doi.org/10.1016/j.ejrh.2026.103636
- A comparative assessment of cluster-based regionalization approaches using conceptual rainfall–runoff models J. Ougahi & J. Rowan https://doi.org/10.1038/s41598-026-49424-z
- Precipitation recycling impacts on runoff in arid regions of China and Mongolia: a machine learning approach R. Li et al. https://doi.org/10.1080/02626667.2025.2456211
- Integrated machine learning and geochemical modeling reveal hydrogeochemical controls on fluoride and arsenic co-contamination in groundwater Z. Ullah et al. https://doi.org/10.1007/s10653-026-03161-4
- An integrated interpretable framework for multiscale drivers and nonlinear responses of ecosystem services in karst regions J. Chen et al. https://doi.org/10.1016/j.ecolind.2026.115199
- African Q99 prediction model: Hydrological clustering and regression machine learning for extreme flow prediction in African catchments M. El baida et al. https://doi.org/10.1016/j.jafrearsci.2026.106225
- Feature importance measures for flood forecasting system design F. Cappelli et al. https://doi.org/10.1080/02626667.2024.2321332
- Intensifying propagation from El Niño to regional drought in China H. Dong et al. https://doi.org/10.1016/j.jhydrol.2025.133999
- Predicting water quality variables using gradient boosting machine: global versus local explainability using SHapley Additive Explanations (SHAP) K. Merabet et al. https://doi.org/10.1007/s12145-025-01796-y
25 citations as recorded by crossref.
- Earthquake fatality prediction based on hybrid feature importance assessment: a case study in Yunnan Province, China M. Luo et al. https://doi.org/10.1007/s11069-023-05812-6
- What controls hydrology? An assessment across the contiguous United States through an interpretable machine learning approach K. Li & S. Razavi https://doi.org/10.1016/j.jhydrol.2024.131835
- Stepwise Clustered Ensemble (SCE): An R package for interpretable and robust regression in environmental modeling K. Li et al. https://doi.org/10.1016/j.envsoft.2026.107152
- Dimensionality Reduction in River Water Quality Classification Using Genetic Algorithm and Correlation-Based Feature Selection Y. Riwanto & F. Ningrum https://doi.org/10.29303/jppipa.v11i9.11863
- A physics-driven hybrid transformer model for hydrologic simulation under nonstationary environmental conditions H. Zhang et al. https://doi.org/10.1016/j.jhydrol.2026.135133
- Development of a macroscale distributed hydro-modeling method: Bayesian principal-monotonicity inference G. Cheng et al. https://doi.org/10.1016/j.jhydrol.2022.128803
- Feature extraction of fluorescence excitation-emission matrices using PCA fused with Wilks Λ-statistic and FDA for origin identification and active components content prediction of sweet basil W. Du et al. https://doi.org/10.1007/s11694-024-02935-7
- Temporal-Spatial changes of monthly vegetation growth and their driving forces in the ancient Yellow river irrigation system, China K. Li et al. https://doi.org/10.1016/j.jconhyd.2021.103911
- Can unmanned aerial vehicle laser scanning serve as an effective alternative to traditional field methods for predicting tree growth in even-aged Chinese fir (Cunninghamia lanceolata) plantations? R. Li et al. https://doi.org/10.1007/s10342-026-01945-y
- Development of a physics-informed data-driven model for gaining insights into hydrological processes in irrigated watersheds K. Li et al. https://doi.org/10.1016/j.jhydrol.2022.128323
- Development of a Stepwise‐Clustered Multi‐Catchment Hydrological Model for Quantifying Interactions in Regional Climate‐Runoff Relationships F. Wang et al. https://doi.org/10.1029/2021WR030035
- Transformer-enhanced extraction of operating rules for multi-objective reservoir groups: a min river basin case study M. Yan et al. https://doi.org/10.1016/j.jhydrol.2026.135578
- Determination of soil source using laser induced breakdown spectroscopy combined with feature selection Y. Ding et al. https://doi.org/10.1039/D3JA00133D
- Identifying trustworthiness challenges in deep learning models for continental-scale water quality prediction X. Xia et al. https://doi.org/10.1016/j.ynexs.2025.100104
- Deriving hydrological inferences from a machine learning model to understand the physical drivers of flow duration curves S. Jain et al. https://doi.org/10.1016/j.jhydrol.2025.134687
- Explainable Machine Learning for Streamflow Forecasting: Application to the Bosna River Basin S. Gnjato et al. https://doi.org/10.3390/w18101226
- Benchmark-guided insights into hybrid process-based-deep learning models for continental-scale streamflow prediction across the United States D. Sourya et al. https://doi.org/10.1016/j.ejrh.2026.103636
- A comparative assessment of cluster-based regionalization approaches using conceptual rainfall–runoff models J. Ougahi & J. Rowan https://doi.org/10.1038/s41598-026-49424-z
- Precipitation recycling impacts on runoff in arid regions of China and Mongolia: a machine learning approach R. Li et al. https://doi.org/10.1080/02626667.2025.2456211
- Integrated machine learning and geochemical modeling reveal hydrogeochemical controls on fluoride and arsenic co-contamination in groundwater Z. Ullah et al. https://doi.org/10.1007/s10653-026-03161-4
- An integrated interpretable framework for multiscale drivers and nonlinear responses of ecosystem services in karst regions J. Chen et al. https://doi.org/10.1016/j.ecolind.2026.115199
- African Q99 prediction model: Hydrological clustering and regression machine learning for extreme flow prediction in African catchments M. El baida et al. https://doi.org/10.1016/j.jafrearsci.2026.106225
- Feature importance measures for flood forecasting system design F. Cappelli et al. https://doi.org/10.1080/02626667.2024.2321332
- Intensifying propagation from El Niño to regional drought in China H. Dong et al. https://doi.org/10.1016/j.jhydrol.2025.133999
- Predicting water quality variables using gradient boosting machine: global versus local explainability using SHapley Additive Explanations (SHAP) K. Merabet et al. https://doi.org/10.1007/s12145-025-01796-y
Saved (final revised paper)
Latest update: 12 Nov 2026
Short summary
We proposed a test statistic feature importance method to quantify the importance of predictor variables for random-forest-like models. The proposed method does not rely on any performance measures to evaluate variable rankings, which can thus result in unbiased variable rankings. The resulting variable rankings based on the proposed method could help random forest achieve its optimum predictive accuracy.
We proposed a test statistic feature importance method to quantify the importance of predictor...
Altmetrics
Final-revised paper
Preprint