Assessment of the hydrological and coupled soft computing models, based on different satellite precipitation datasets, to simulate streamflow and sediment load in a mountainous catchment
This study evaluated the performance and hydrologic utility of four different satellite precipitation datasets (SPDs), including GPM (IMERG_F), PERSIANN_CDR, CHIRPS, and CMORPH, to predict daily streamflow and SL using the SWAT hydrological model as well as SWAT coupled soft computing models (SCMs)...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IWA Publishing
2023-02-01
|
| Series: | Journal of Water and Climate Change |
| Subjects: | |
| Online Access: | http://jwcc.iwaponline.com/content/14/2/610 |
| _version_ | 1797202794102390784 |
|---|---|
| author | Muhammad Adnan Khan Jürgen Stamm |
| author_facet | Muhammad Adnan Khan Jürgen Stamm |
| author_sort | Muhammad Adnan Khan |
| collection | DOAJ |
| description | This study evaluated the performance and hydrologic utility of four different satellite precipitation datasets (SPDs), including GPM (IMERG_F), PERSIANN_CDR, CHIRPS, and CMORPH, to predict daily streamflow and SL using the SWAT hydrological model as well as SWAT coupled soft computing models (SCMs) such as artificial neural networks (SWAT-ANNs), random forests (SWAT-RFs), and support vector regression (SWAT-SVR), in the mountainous Upper Jhelum River Basin (UJRB), Pakistan. SCMs were developed using the outputs of un-calibrated SWAT models to improve the predictions. Overall, the GPM shows the highest performance for the entire simulation with R2 and PBIAS varying from 0.71 to 0.96 and −13.1 to 0.01%, respectively. For the best GPM-based models, SWAT-RF showed a superior ability to simulate the entire streamflow with R2 of 0.96, compared with the SWAT-ANN (R2 = 0.90), SWAT-SVR (R2 = 0.87), and SWAT-CUP (R2 = 0.71). Similarly, SWAT-ANN presented the best performance capability to simulate the SL with an R2 of 0.71, compared with the SWAT-RF (R2 = 0.66), SWAT-SVR (R2 = 0.52), and SWAT-CUP (R2 = 0.42). Hence, hydrological coupled SCMs based on SPDs could be an effective technique for simulating hydrological parameters, particularly in complex terrain where gauge network density is low or uneven.
HIGHLIGHTS
Soft computing models development using the outputs of un-calibrated SWAT models to improve the prediction of daily streamflow and sediment load in Rivers.;
Effectiveness of the hydrological coupled soft computing models based on satellite precipitation datasets for simulating hydrological parameters.;
Auto-optimization of different sensitive parameters of the soft computing models to improve predictions.; |
| first_indexed | 2024-04-09T19:04:29Z |
| format | Article |
| id | doaj.art-2bcee5371b8b442cbb1f685074370d8e |
| institution | Directory Open Access Journal |
| issn | 2040-2244 2408-9354 |
| language | English |
| last_indexed | 2024-04-24T08:09:06Z |
| publishDate | 2023-02-01 |
| publisher | IWA Publishing |
| record_format | Article |
| series | Journal of Water and Climate Change |
| spelling | doaj.art-2bcee5371b8b442cbb1f685074370d8e2024-04-17T08:17:18ZengIWA PublishingJournal of Water and Climate Change2040-22442408-93542023-02-0114261063210.2166/wcc.2023.470470Assessment of the hydrological and coupled soft computing models, based on different satellite precipitation datasets, to simulate streamflow and sediment load in a mountainous catchmentMuhammad Adnan Khan0Jürgen Stamm1 Institute of Hydraulic Engineering and Technical Hydromechanics, Technische Universität Dresden, Dresden 01062, Germany Institute of Hydraulic Engineering and Technical Hydromechanics, Technische Universität Dresden, Dresden 01062, Germany This study evaluated the performance and hydrologic utility of four different satellite precipitation datasets (SPDs), including GPM (IMERG_F), PERSIANN_CDR, CHIRPS, and CMORPH, to predict daily streamflow and SL using the SWAT hydrological model as well as SWAT coupled soft computing models (SCMs) such as artificial neural networks (SWAT-ANNs), random forests (SWAT-RFs), and support vector regression (SWAT-SVR), in the mountainous Upper Jhelum River Basin (UJRB), Pakistan. SCMs were developed using the outputs of un-calibrated SWAT models to improve the predictions. Overall, the GPM shows the highest performance for the entire simulation with R2 and PBIAS varying from 0.71 to 0.96 and −13.1 to 0.01%, respectively. For the best GPM-based models, SWAT-RF showed a superior ability to simulate the entire streamflow with R2 of 0.96, compared with the SWAT-ANN (R2 = 0.90), SWAT-SVR (R2 = 0.87), and SWAT-CUP (R2 = 0.71). Similarly, SWAT-ANN presented the best performance capability to simulate the SL with an R2 of 0.71, compared with the SWAT-RF (R2 = 0.66), SWAT-SVR (R2 = 0.52), and SWAT-CUP (R2 = 0.42). Hence, hydrological coupled SCMs based on SPDs could be an effective technique for simulating hydrological parameters, particularly in complex terrain where gauge network density is low or uneven. HIGHLIGHTS Soft computing models development using the outputs of un-calibrated SWAT models to improve the prediction of daily streamflow and sediment load in Rivers.; Effectiveness of the hydrological coupled soft computing models based on satellite precipitation datasets for simulating hydrological parameters.; Auto-optimization of different sensitive parameters of the soft computing models to improve predictions.;http://jwcc.iwaponline.com/content/14/2/610artificial neural networksrandom forestsatellite precipitation productssupport vector regressionswat |
| spellingShingle | Muhammad Adnan Khan Jürgen Stamm Assessment of the hydrological and coupled soft computing models, based on different satellite precipitation datasets, to simulate streamflow and sediment load in a mountainous catchment Journal of Water and Climate Change artificial neural networks random forest satellite precipitation products support vector regression swat |
| title | Assessment of the hydrological and coupled soft computing models, based on different satellite precipitation datasets, to simulate streamflow and sediment load in a mountainous catchment |
| title_full | Assessment of the hydrological and coupled soft computing models, based on different satellite precipitation datasets, to simulate streamflow and sediment load in a mountainous catchment |
| title_fullStr | Assessment of the hydrological and coupled soft computing models, based on different satellite precipitation datasets, to simulate streamflow and sediment load in a mountainous catchment |
| title_full_unstemmed | Assessment of the hydrological and coupled soft computing models, based on different satellite precipitation datasets, to simulate streamflow and sediment load in a mountainous catchment |
| title_short | Assessment of the hydrological and coupled soft computing models, based on different satellite precipitation datasets, to simulate streamflow and sediment load in a mountainous catchment |
| title_sort | assessment of the hydrological and coupled soft computing models based on different satellite precipitation datasets to simulate streamflow and sediment load in a mountainous catchment |
| topic | artificial neural networks random forest satellite precipitation products support vector regression swat |
| url | http://jwcc.iwaponline.com/content/14/2/610 |
| work_keys_str_mv | AT muhammadadnankhan assessmentofthehydrologicalandcoupledsoftcomputingmodelsbasedondifferentsatelliteprecipitationdatasetstosimulatestreamflowandsedimentloadinamountainouscatchment AT jurgenstamm assessmentofthehydrologicalandcoupledsoftcomputingmodelsbasedondifferentsatelliteprecipitationdatasetstosimulatestreamflowandsedimentloadinamountainouscatchment |