Integrating machine learning with process-based glacio-hydrological model for improving the performance of runoff simulation in cold regions
(2025) In Journal of Hydrology 656.- Abstract
- Hydrological modelling is essential for effective water resources management, as it represents complex physical processes through mathematical equations to improve our understanding of the water cycle. FLEXG is a glacio-hydrological model that has been successfully applied and found to perform well in glacierized regions. This study seeks to improve the capability of classical FLEXG model for glacio-hydrological simulations in northern Sweden using three different hybrid approaches. The first approach integrates the Random Forest (RF) algorithm with the FLEXG model to simulate catchment runoff dynamics using the physical principles of catchments. This process-guided approach incorporates the concepts of glacier and non-glacier runoffs into... (More)
- Hydrological modelling is essential for effective water resources management, as it represents complex physical processes through mathematical equations to improve our understanding of the water cycle. FLEXG is a glacio-hydrological model that has been successfully applied and found to perform well in glacierized regions. This study seeks to improve the capability of classical FLEXG model for glacio-hydrological simulations in northern Sweden using three different hybrid approaches. The first approach integrates the Random Forest (RF) algorithm with the FLEXG model to simulate catchment runoff dynamics using the physical principles of catchments. This process-guided approach incorporates the concepts of glacier and non-glacier runoffs into RF training. The second hybrid approach refines runoff predictions by integrating residuals with meteorological and glacio-hydrological variables, demonstrating improved accuracy in simulated daily runoff. The third hybrid approach couples meteorological and glacio-hydrological variables via a sequential approach into RF model. The FLEXG simulated daily runoff with Kling-Gupta Efficiency (KGE) of 0.68 and Nash-Sutcliffe Efficiency (NSE) of 0.58 during the validation period, while the best hybrid model (the second hybrid approach) achieved KGE of 0.90 and NSE of 0.86 in the same period. In addition, the best hybrid approach improved capability of the process-based hydrological model for detection of the top 10 % peak flow events, achieving False Alarm Ratio (FAR) of 0.11 and Probability of Detection (POD) of 0.90. The results showed that the proposed hybrid approaches are capable of improving the performance of the FLEXG model. However, it is important to recognize that increasing the number of variables also adds complexity to the model’s structure. This research demonstrates the potential of hybrid modelling approaches to enhance glacio-hydrological predictions in cold regions, which can be useful for water resource management in rapidly changing glaciated environments. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/d58da197-4ccb-4539-b8be-0e1a1ae49af3
- author
- Mohammadi, Babak
LU
; Gao, Hongkai ; Pilesjö, Petter LU ; Tuo, Ye ; Guo, Renkui LU
and Duan, Zheng LU
- organization
- publishing date
- 2025-02-24
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Glacio-hydrological modelling, Catchment hydrology, Snow cover area, Runoff, Hybrid model, Explainable artificial intelligence
- in
- Journal of Hydrology
- volume
- 656
- article number
- 132963
- publisher
- Elsevier
- external identifiers
-
- scopus:85219680921
- ISSN
- 0022-1694
- DOI
- 10.1016/j.jhydrol.2025.132963
- project
- Improving hydrological modelling in cold regions using satellite remote sensing and machine learning techniques
- language
- English
- LU publication?
- yes
- id
- d58da197-4ccb-4539-b8be-0e1a1ae49af3
- date added to LUP
- 2025-04-06 13:15:45
- date last changed
- 2025-06-10 10:29:54
@article{d58da197-4ccb-4539-b8be-0e1a1ae49af3, abstract = {{Hydrological modelling is essential for effective water resources management, as it represents complex physical processes through mathematical equations to improve our understanding of the water cycle. FLEXG is a glacio-hydrological model that has been successfully applied and found to perform well in glacierized regions. This study seeks to improve the capability of classical FLEXG model for glacio-hydrological simulations in northern Sweden using three different hybrid approaches. The first approach integrates the Random Forest (RF) algorithm with the FLEXG model to simulate catchment runoff dynamics using the physical principles of catchments. This process-guided approach incorporates the concepts of glacier and non-glacier runoffs into RF training. The second hybrid approach refines runoff predictions by integrating residuals with meteorological and glacio-hydrological variables, demonstrating improved accuracy in simulated daily runoff. The third hybrid approach couples meteorological and glacio-hydrological variables via a sequential approach into RF model. The FLEXG simulated daily runoff with Kling-Gupta Efficiency (KGE) of 0.68 and Nash-Sutcliffe Efficiency (NSE) of 0.58 during the validation period, while the best hybrid model (the second hybrid approach) achieved KGE of 0.90 and NSE of 0.86 in the same period. In addition, the best hybrid approach improved capability of the process-based hydrological model for detection of the top 10 % peak flow events, achieving False Alarm Ratio (FAR) of 0.11 and Probability of Detection (POD) of 0.90. The results showed that the proposed hybrid approaches are capable of improving the performance of the FLEXG model. However, it is important to recognize that increasing the number of variables also adds complexity to the model’s structure. This research demonstrates the potential of hybrid modelling approaches to enhance glacio-hydrological predictions in cold regions, which can be useful for water resource management in rapidly changing glaciated environments.}}, author = {{Mohammadi, Babak and Gao, Hongkai and Pilesjö, Petter and Tuo, Ye and Guo, Renkui and Duan, Zheng}}, issn = {{0022-1694}}, keywords = {{Glacio-hydrological modelling; Catchment hydrology; Snow cover area; Runoff; Hybrid model; Explainable artificial intelligence}}, language = {{eng}}, month = {{02}}, publisher = {{Elsevier}}, series = {{Journal of Hydrology}}, title = {{Integrating machine learning with process-based glacio-hydrological model for improving the performance of runoff simulation in cold regions}}, url = {{http://dx.doi.org/10.1016/j.jhydrol.2025.132963}}, doi = {{10.1016/j.jhydrol.2025.132963}}, volume = {{656}}, year = {{2025}}, }