Comparison of machine learning and process-based SWAT model in simulating streamflow in the Upper Indus Basin
Abstract This study appraised and compared the performance of process-based hydrological SWAT (soil and water assessment tool) with a machine learning-based multi-layer perceptron (MLP) models for simulating streamflow in the Upper Indus Basin. The study period ranges from 1998 to 2013, where SWAT a...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2022-06-01
|
| Series: | Applied Water Science |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s13201-022-01692-6 |
| _version_ | 1811241286578995200 |
|---|---|
| author | Khalil Ur Rahman Quoc Bao Pham Khan Zaib Jadoon Muhammad Shahid Daniel Prakash Kushwaha Zheng Duan Babak Mohammadi Khaled Mohamed Khedher Duong Tran Anh |
| author_facet | Khalil Ur Rahman Quoc Bao Pham Khan Zaib Jadoon Muhammad Shahid Daniel Prakash Kushwaha Zheng Duan Babak Mohammadi Khaled Mohamed Khedher Duong Tran Anh |
| author_sort | Khalil Ur Rahman |
| collection | DOAJ |
| description | Abstract This study appraised and compared the performance of process-based hydrological SWAT (soil and water assessment tool) with a machine learning-based multi-layer perceptron (MLP) models for simulating streamflow in the Upper Indus Basin. The study period ranges from 1998 to 2013, where SWAT and MLP models were calibrated/trained and validated/tested for multiple sites during 1998–2005 and 2006–2013, respectively. The performance of both models was evaluated using nash–sutcliffe efficiency (NSE), coefficient of determination (R 2), Percent BIAS (PBIAS), and mean absolute percentage error (MAPE). Results illustrated the relatively poor performance of the SWAT model as compared with the MLP model. NSE, PBIAS, R 2, and MAPE for SWAT (MLP) models during calibration ranged from the minimum of 0.81 (0.90), 3.49 (0.02), 0.80 (0.25) and 7.61 (0.01) to the maximum of 0.86 (0.99), 9.84 (0.12), 0.87 (0.99), and 15.71 (0.267), respectively. The poor performance of SWAT compared with MLP might be influenced by several factors, including the selection of sensitive parameters, selection of snow specific sensitive parameters that might not represent actual snow conditions, potential limitations of the SCS-CN method used to simulate streamflow, and lack of SWAT ability to capture the hydropeaking in Indus River sub-basins (at Shatial bridge and Bisham Qila). Based on the robust performance of the MLP model, the current study recommends to develop and assess machine learning models and merging the SWAT model with machine learning models. |
| first_indexed | 2024-04-12T13:33:15Z |
| format | Article |
| id | doaj.art-d901f5209a2b4ac19dbb7f922d3f9fb6 |
| institution | Directory Open Access Journal |
| issn | 2190-5487 2190-5495 |
| language | English |
| last_indexed | 2024-04-12T13:33:15Z |
| publishDate | 2022-06-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Applied Water Science |
| spelling | doaj.art-d901f5209a2b4ac19dbb7f922d3f9fb62022-12-22T03:31:06ZengSpringerOpenApplied Water Science2190-54872190-54952022-06-0112811910.1007/s13201-022-01692-6Comparison of machine learning and process-based SWAT model in simulating streamflow in the Upper Indus BasinKhalil Ur Rahman0Quoc Bao Pham1Khan Zaib Jadoon2Muhammad Shahid3Daniel Prakash Kushwaha4Zheng Duan5Babak Mohammadi6Khaled Mohamed Khedher7Duong Tran Anh8State Key Laboratory of Hydroscience and Engineering, Department of Hydraulic Engineering, Tsinghua UniversityInstitute of Applied Technology, Thu Dau Mot UniversityDepartment of Civil Engineering, Islamic International UniversityNICE, SCEE, National University of Sciences & Technology (NUST)Department of Soil and Water Conservation Engineering, College of Technology, G.B. Pant University of Agriculture & TechnologyDepartment of Physical Geography and Ecosystem Science, Lund UniversityDepartment of Physical Geography and Ecosystem Science, Lund UniversityDepartment of Civil Engineering, College of Engineering, King Khalid UniversityHUTECH UniversityAbstract This study appraised and compared the performance of process-based hydrological SWAT (soil and water assessment tool) with a machine learning-based multi-layer perceptron (MLP) models for simulating streamflow in the Upper Indus Basin. The study period ranges from 1998 to 2013, where SWAT and MLP models were calibrated/trained and validated/tested for multiple sites during 1998–2005 and 2006–2013, respectively. The performance of both models was evaluated using nash–sutcliffe efficiency (NSE), coefficient of determination (R 2), Percent BIAS (PBIAS), and mean absolute percentage error (MAPE). Results illustrated the relatively poor performance of the SWAT model as compared with the MLP model. NSE, PBIAS, R 2, and MAPE for SWAT (MLP) models during calibration ranged from the minimum of 0.81 (0.90), 3.49 (0.02), 0.80 (0.25) and 7.61 (0.01) to the maximum of 0.86 (0.99), 9.84 (0.12), 0.87 (0.99), and 15.71 (0.267), respectively. The poor performance of SWAT compared with MLP might be influenced by several factors, including the selection of sensitive parameters, selection of snow specific sensitive parameters that might not represent actual snow conditions, potential limitations of the SCS-CN method used to simulate streamflow, and lack of SWAT ability to capture the hydropeaking in Indus River sub-basins (at Shatial bridge and Bisham Qila). Based on the robust performance of the MLP model, the current study recommends to develop and assess machine learning models and merging the SWAT model with machine learning models.https://doi.org/10.1007/s13201-022-01692-6Hydrological modelingGlacierSWATMLPUpper Indus Basin |
| spellingShingle | Khalil Ur Rahman Quoc Bao Pham Khan Zaib Jadoon Muhammad Shahid Daniel Prakash Kushwaha Zheng Duan Babak Mohammadi Khaled Mohamed Khedher Duong Tran Anh Comparison of machine learning and process-based SWAT model in simulating streamflow in the Upper Indus Basin Applied Water Science Hydrological modeling Glacier SWAT MLP Upper Indus Basin |
| title | Comparison of machine learning and process-based SWAT model in simulating streamflow in the Upper Indus Basin |
| title_full | Comparison of machine learning and process-based SWAT model in simulating streamflow in the Upper Indus Basin |
| title_fullStr | Comparison of machine learning and process-based SWAT model in simulating streamflow in the Upper Indus Basin |
| title_full_unstemmed | Comparison of machine learning and process-based SWAT model in simulating streamflow in the Upper Indus Basin |
| title_short | Comparison of machine learning and process-based SWAT model in simulating streamflow in the Upper Indus Basin |
| title_sort | comparison of machine learning and process based swat model in simulating streamflow in the upper indus basin |
| topic | Hydrological modeling Glacier SWAT MLP Upper Indus Basin |
| url | https://doi.org/10.1007/s13201-022-01692-6 |
| work_keys_str_mv | AT khalilurrahman comparisonofmachinelearningandprocessbasedswatmodelinsimulatingstreamflowintheupperindusbasin AT quocbaopham comparisonofmachinelearningandprocessbasedswatmodelinsimulatingstreamflowintheupperindusbasin AT khanzaibjadoon comparisonofmachinelearningandprocessbasedswatmodelinsimulatingstreamflowintheupperindusbasin AT muhammadshahid comparisonofmachinelearningandprocessbasedswatmodelinsimulatingstreamflowintheupperindusbasin AT danielprakashkushwaha comparisonofmachinelearningandprocessbasedswatmodelinsimulatingstreamflowintheupperindusbasin AT zhengduan comparisonofmachinelearningandprocessbasedswatmodelinsimulatingstreamflowintheupperindusbasin AT babakmohammadi comparisonofmachinelearningandprocessbasedswatmodelinsimulatingstreamflowintheupperindusbasin AT khaledmohamedkhedher comparisonofmachinelearningandprocessbasedswatmodelinsimulatingstreamflowintheupperindusbasin AT duongtrananh comparisonofmachinelearningandprocessbasedswatmodelinsimulatingstreamflowintheupperindusbasin |