Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Comparison of machine learning and process-based SWAT model in simulating streamflow in the Upper Indus Basin

Rahman, Khalil Ur ; Pham, Quoc Bao ; Jadoon, Khan Zaib ; Shahid, Muhammad ; Kushwaha, Daniel Prakash ; Duan, Zheng LU ; Mohammadi, Babak LU orcid ; Khedher, Khaled Mohamed and Anh, Duong Tran (2022) In Applied water science 12(8).
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 (R2), 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, R2, and... (More)

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 (R2), 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, R2, 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.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; ; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Glacier, Hydrological modeling, machine learning, SWAT, streamflow
in
Applied water science
volume
12
issue
8
article number
178
publisher
Springer
external identifiers
  • scopus:85131807019
ISSN
2190-5487
DOI
10.1007/s13201-022-01692-6
language
English
LU publication?
yes
additional info
Funding Information: The authors extend their gratitude to the Water and Power Development Authority (WAPDA) for providing streamflow and climate data. The authors are also thankful to Pakistan Meteorology Department (PMD) for providing in-situ precipitation data. Funding Information: This research work was supported by the Shuimu Scholar Program of Tsinghua University (Grant number 2020SM072). Publisher Copyright: © 2022, The Author(s).
id
32a303b0-cb31-4549-9d3c-f68402d2a395
date added to LUP
2022-07-12 07:39:41
date last changed
2023-05-16 13:07:22
@article{32a303b0-cb31-4549-9d3c-f68402d2a395,
  abstract     = {{<p>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<sup>2</sup>), 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<sup>2</sup>, 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.</p>}},
  author       = {{Rahman, Khalil Ur and Pham, Quoc Bao and Jadoon, Khan Zaib and Shahid, Muhammad and Kushwaha, Daniel Prakash and Duan, Zheng and Mohammadi, Babak and Khedher, Khaled Mohamed and Anh, Duong Tran}},
  issn         = {{2190-5487}},
  keywords     = {{Glacier; Hydrological modeling; machine learning; SWAT; streamflow}},
  language     = {{eng}},
  number       = {{8}},
  publisher    = {{Springer}},
  series       = {{Applied water science}},
  title        = {{Comparison of machine learning and process-based SWAT model in simulating streamflow in the Upper Indus Basin}},
  url          = {{http://dx.doi.org/10.1007/s13201-022-01692-6}},
  doi          = {{10.1007/s13201-022-01692-6}},
  volume       = {{12}},
  year         = {{2022}},
}