Hybridization of stochastic hydrological models and machine learning methods for improving rainfall-runoff modeling
Accurately simulating river discharge remains a challenge. Hybrid models combining hydrological models with machine learning improve discharge simulation and offer better interpretability than standalone machine learning models. However, the commonly used models are deterministic. This study introdu...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-03-01
|
| Series: | Results in Engineering |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590123025001677 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832590921290481664 |
|---|---|
| author | Sianou Ezéckiel Houénafa Olatunji Johnson Erick K. Ronoh Stephen E. Moore |
| author_facet | Sianou Ezéckiel Houénafa Olatunji Johnson Erick K. Ronoh Stephen E. Moore |
| author_sort | Sianou Ezéckiel Houénafa |
| collection | DOAJ |
| description | Accurately simulating river discharge remains a challenge. Hybrid models combining hydrological models with machine learning improve discharge simulation and offer better interpretability than standalone machine learning models. However, the commonly used models are deterministic. This study introduces an innovative extension to stochastic hydrological models, offering a novel combination that has not been previously explored. The proposed approach predicts discharge by integrating the simulated statistical properties of daily discharge probability distributions, derived from a stochastic rainfall-runoff model, into machine learning frameworks. This integration allows the machine learning models to incorporate insights from the uncertainties in discharge, thereby enhancing predictive accuracy of discharge simulations. The hybridization presented combines the physically-based stochastic HyMoLAP (Sto. HyMoLAP) model with machine learning techniques, including Wavelet-based eXtreme Gradient Boosting (WXGBoost) and Wavelet-based Gated Recurrent Unit (WGRU). Evaluated on the Ouémé at Bonou river basin, Benin, the Sto. HyMoLAP-WGRU model shows the best predictive performance, especially for low and high discharges. It achieves an overall Nash-Sutcliffe Efficiency (NSE) of 0.896, which is 7.30% higher than the NSE of HyMoLAP, and 29.67% and 259.71% higher than those of the standalone machine learning models. The Combined Accuracy (CA) is 38.11, reflecting reductions of 19.81%, 42.30%, and 62.41% compared to the standalone models. The analyses show that the performance of hybrid models depends on the simulated discharge distribution properties used as input. They suggest that the hybridization approach could be particularly beneficial for runoff simulations in catchments subject to significant random fluctuations where point discharge simulation is challenging. |
| format | Article |
| id | doaj-art-e1be73c115be48548e5c47be73833d82 |
| institution | Kabale University |
| issn | 2590-1230 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Results in Engineering |
| spelling | doaj-art-e1be73c115be48548e5c47be73833d822025-01-23T05:27:41ZengElsevierResults in Engineering2590-12302025-03-0125104079Hybridization of stochastic hydrological models and machine learning methods for improving rainfall-runoff modelingSianou Ezéckiel Houénafa0Olatunji Johnson1Erick K. Ronoh2Stephen E. Moore3Department of Mathematics, Pan African University Institute for Basic Sciences, Technology and Innovation, Nairobi, Kenya; Corresponding author.Department of Mathematics, University of Manchester, Manchester, United KingdomDepartment of Agricultural and Biosystems Engineering, Jomo Kenyatta University of Agriculture and Technology, Nairobi, KenyaDepartment of Mathematics, University of Cape Coast, Cape Coast, Ghana; Center for Artificial Intelligence, GhanaAccurately simulating river discharge remains a challenge. Hybrid models combining hydrological models with machine learning improve discharge simulation and offer better interpretability than standalone machine learning models. However, the commonly used models are deterministic. This study introduces an innovative extension to stochastic hydrological models, offering a novel combination that has not been previously explored. The proposed approach predicts discharge by integrating the simulated statistical properties of daily discharge probability distributions, derived from a stochastic rainfall-runoff model, into machine learning frameworks. This integration allows the machine learning models to incorporate insights from the uncertainties in discharge, thereby enhancing predictive accuracy of discharge simulations. The hybridization presented combines the physically-based stochastic HyMoLAP (Sto. HyMoLAP) model with machine learning techniques, including Wavelet-based eXtreme Gradient Boosting (WXGBoost) and Wavelet-based Gated Recurrent Unit (WGRU). Evaluated on the Ouémé at Bonou river basin, Benin, the Sto. HyMoLAP-WGRU model shows the best predictive performance, especially for low and high discharges. It achieves an overall Nash-Sutcliffe Efficiency (NSE) of 0.896, which is 7.30% higher than the NSE of HyMoLAP, and 29.67% and 259.71% higher than those of the standalone machine learning models. The Combined Accuracy (CA) is 38.11, reflecting reductions of 19.81%, 42.30%, and 62.41% compared to the standalone models. The analyses show that the performance of hybrid models depends on the simulated discharge distribution properties used as input. They suggest that the hybridization approach could be particularly beneficial for runoff simulations in catchments subject to significant random fluctuations where point discharge simulation is challenging.http://www.sciencedirect.com/science/article/pii/S2590123025001677Stochastic hydrological modelHyMoLAPMachine learningHybrid modelsUncertainties |
| spellingShingle | Sianou Ezéckiel Houénafa Olatunji Johnson Erick K. Ronoh Stephen E. Moore Hybridization of stochastic hydrological models and machine learning methods for improving rainfall-runoff modeling Results in Engineering Stochastic hydrological model HyMoLAP Machine learning Hybrid models Uncertainties |
| title | Hybridization of stochastic hydrological models and machine learning methods for improving rainfall-runoff modeling |
| title_full | Hybridization of stochastic hydrological models and machine learning methods for improving rainfall-runoff modeling |
| title_fullStr | Hybridization of stochastic hydrological models and machine learning methods for improving rainfall-runoff modeling |
| title_full_unstemmed | Hybridization of stochastic hydrological models and machine learning methods for improving rainfall-runoff modeling |
| title_short | Hybridization of stochastic hydrological models and machine learning methods for improving rainfall-runoff modeling |
| title_sort | hybridization of stochastic hydrological models and machine learning methods for improving rainfall runoff modeling |
| topic | Stochastic hydrological model HyMoLAP Machine learning Hybrid models Uncertainties |
| url | http://www.sciencedirect.com/science/article/pii/S2590123025001677 |
| work_keys_str_mv | AT sianouezeckielhouenafa hybridizationofstochastichydrologicalmodelsandmachinelearningmethodsforimprovingrainfallrunoffmodeling AT olatunjijohnson hybridizationofstochastichydrologicalmodelsandmachinelearningmethodsforimprovingrainfallrunoffmodeling AT erickkronoh hybridizationofstochastichydrologicalmodelsandmachinelearningmethodsforimprovingrainfallrunoffmodeling AT stephenemoore hybridizationofstochastichydrologicalmodelsandmachinelearningmethodsforimprovingrainfallrunoffmodeling |