Exploring alternate coupling inputs of a data-driven model for optimum daily streamflow prediction in calibrated SWAT-BiLSTM rainfall-runoff modeling

Accurate streamflow prediction in mountainous regions is vital for sustaining water resources in downstream areas, ensuring reliable availability for agriculture, energy, and consumption. However, physically based prediction models are prone to substantial uncertainties due to complex processes and...

Full description

Saved in:
Bibliographic Details
Main Authors: Khalil Ahmad, Mudassar Iqbal, Muhammad Atiq Ur Rehman Tariq, Afed Ullah Khan, Abdullah Nadeem, Jinlei Chen, Kseniia Usanova, Hamad Almujibah, Hashem Alyami, Muhammad Abid
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-04-01
Series:Frontiers in Water
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/frwa.2025.1558218/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850261765462425600
author Khalil Ahmad
Khalil Ahmad
Mudassar Iqbal
Muhammad Atiq Ur Rehman Tariq
Afed Ullah Khan
Abdullah Nadeem
Jinlei Chen
Kseniia Usanova
Kseniia Usanova
Hamad Almujibah
Hashem Alyami
Muhammad Abid
author_facet Khalil Ahmad
Khalil Ahmad
Mudassar Iqbal
Muhammad Atiq Ur Rehman Tariq
Afed Ullah Khan
Abdullah Nadeem
Jinlei Chen
Kseniia Usanova
Kseniia Usanova
Hamad Almujibah
Hashem Alyami
Muhammad Abid
author_sort Khalil Ahmad
collection DOAJ
description Accurate streamflow prediction in mountainous regions is vital for sustaining water resources in downstream areas, ensuring reliable availability for agriculture, energy, and consumption. However, physically based prediction models are prone to substantial uncertainties due to complex processes and the inherent variability in model parameters and parameterization. This study addresses these challenges by exploring alternative coupling inputs for data-driven (DD) models to optimize daily streamflow prediction in a calibrated SWAT-BiLSTM rainfall-runoff model within the Astore sub-basin of the Upper Indus Basin (UIB), Pakistan. The research explores two standalone models (SWAT and BiLSTM) and three alternative coupling inputs: conventional climatic variables (precipitation and temperature), cross-correlation based selected inputs, and exclusion of direct climatic inputs, in calibrated SWAT-BiLSTM model. The study spans calibration, validation, and prediction periods from 2007 to 2011, 2012 to 2015, and 2017 to 2019, respectively. Based on compromise programing (CP) ranking, SWAT-C-BiLSTM (QP) and SWAT-C-BiLSTM (T1 QP) showed competent performances followed by BiLSTM, SWAT-C-BiLSTM (PTQP), and SWAT. These findings highlight that excluding climatic parameters alternative SWAT-C-BiLSTM (QP) enhances the couple model’s accuracy sufficiently and underscores the potential for this approach to contribute to sustainable water resource management.
format Article
id doaj-art-6592ff06c48c4c0896da2c0445b3be53
institution OA Journals
issn 2624-9375
language English
publishDate 2025-04-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Water
spelling doaj-art-6592ff06c48c4c0896da2c0445b3be532025-08-20T01:55:19ZengFrontiers Media S.A.Frontiers in Water2624-93752025-04-01710.3389/frwa.2025.15582181558218Exploring alternate coupling inputs of a data-driven model for optimum daily streamflow prediction in calibrated SWAT-BiLSTM rainfall-runoff modelingKhalil Ahmad0Khalil Ahmad1Mudassar Iqbal2Muhammad Atiq Ur Rehman Tariq3Afed Ullah Khan4Abdullah Nadeem5Jinlei Chen6Kseniia Usanova7Kseniia Usanova8Hamad Almujibah9Hashem Alyami10Muhammad Abid11Centre of Excellence in Water Resources Engineering, University of Engineering and Technology, Lahore, PakistanDepartment of Civil Engineering, University of Engineering and Technology Peshawar, Bannu Campus, Bannu, PakistanCentre of Excellence in Water Resources Engineering, University of Engineering and Technology, Lahore, PakistanCentre of Excellence in Water Resources Engineering, University of Engineering and Technology, Lahore, PakistanDepartment of Civil Engineering, University of Engineering and Technology Peshawar, Bannu Campus, Bannu, PakistanCentre of Excellence in Water Resources Engineering, University of Engineering and Technology, Lahore, PakistanState Key Laboratory of Cryospheric Science and Frozen Soil Engineering, Northwest Institute of Eco-Environment and Resources, Chinese Academy of Sciences, Lanzhou, ChinaScientific and Technological Complex for Digital Engineering in Construction, Peter the Great St. Petersburg Polytechnic University, Saint Petersburg, RussiaAcademy of Engineering, RUDN University, Moscow, RussiaDepartment of Civil Engineering, College of Engineering, Taif University, Taif, Saudi ArabiaDepartment of Computer Science, College of Computers and Information Technology, Taif University, Taif, Saudi ArabiaCollege of Aerospace and Civil Engineering, Harbin Engineering University, Harbin, ChinaAccurate streamflow prediction in mountainous regions is vital for sustaining water resources in downstream areas, ensuring reliable availability for agriculture, energy, and consumption. However, physically based prediction models are prone to substantial uncertainties due to complex processes and the inherent variability in model parameters and parameterization. This study addresses these challenges by exploring alternative coupling inputs for data-driven (DD) models to optimize daily streamflow prediction in a calibrated SWAT-BiLSTM rainfall-runoff model within the Astore sub-basin of the Upper Indus Basin (UIB), Pakistan. The research explores two standalone models (SWAT and BiLSTM) and three alternative coupling inputs: conventional climatic variables (precipitation and temperature), cross-correlation based selected inputs, and exclusion of direct climatic inputs, in calibrated SWAT-BiLSTM model. The study spans calibration, validation, and prediction periods from 2007 to 2011, 2012 to 2015, and 2017 to 2019, respectively. Based on compromise programing (CP) ranking, SWAT-C-BiLSTM (QP) and SWAT-C-BiLSTM (T1 QP) showed competent performances followed by BiLSTM, SWAT-C-BiLSTM (PTQP), and SWAT. These findings highlight that excluding climatic parameters alternative SWAT-C-BiLSTM (QP) enhances the couple model’s accuracy sufficiently and underscores the potential for this approach to contribute to sustainable water resource management.https://www.frontiersin.org/articles/10.3389/frwa.2025.1558218/fulladvancement in rainfall-runoffBiLSTMinputs selectionstreamflow predictionSWAT-BiLSTM modelingsupervised machine learning
spellingShingle Khalil Ahmad
Khalil Ahmad
Mudassar Iqbal
Muhammad Atiq Ur Rehman Tariq
Afed Ullah Khan
Abdullah Nadeem
Jinlei Chen
Kseniia Usanova
Kseniia Usanova
Hamad Almujibah
Hashem Alyami
Muhammad Abid
Exploring alternate coupling inputs of a data-driven model for optimum daily streamflow prediction in calibrated SWAT-BiLSTM rainfall-runoff modeling
Frontiers in Water
advancement in rainfall-runoff
BiLSTM
inputs selection
streamflow prediction
SWAT-BiLSTM modeling
supervised machine learning
title Exploring alternate coupling inputs of a data-driven model for optimum daily streamflow prediction in calibrated SWAT-BiLSTM rainfall-runoff modeling
title_full Exploring alternate coupling inputs of a data-driven model for optimum daily streamflow prediction in calibrated SWAT-BiLSTM rainfall-runoff modeling
title_fullStr Exploring alternate coupling inputs of a data-driven model for optimum daily streamflow prediction in calibrated SWAT-BiLSTM rainfall-runoff modeling
title_full_unstemmed Exploring alternate coupling inputs of a data-driven model for optimum daily streamflow prediction in calibrated SWAT-BiLSTM rainfall-runoff modeling
title_short Exploring alternate coupling inputs of a data-driven model for optimum daily streamflow prediction in calibrated SWAT-BiLSTM rainfall-runoff modeling
title_sort exploring alternate coupling inputs of a data driven model for optimum daily streamflow prediction in calibrated swat bilstm rainfall runoff modeling
topic advancement in rainfall-runoff
BiLSTM
inputs selection
streamflow prediction
SWAT-BiLSTM modeling
supervised machine learning
url https://www.frontiersin.org/articles/10.3389/frwa.2025.1558218/full
work_keys_str_mv AT khalilahmad exploringalternatecouplinginputsofadatadrivenmodelforoptimumdailystreamflowpredictionincalibratedswatbilstmrainfallrunoffmodeling
AT khalilahmad exploringalternatecouplinginputsofadatadrivenmodelforoptimumdailystreamflowpredictionincalibratedswatbilstmrainfallrunoffmodeling
AT mudassariqbal exploringalternatecouplinginputsofadatadrivenmodelforoptimumdailystreamflowpredictionincalibratedswatbilstmrainfallrunoffmodeling
AT muhammadatiqurrehmantariq exploringalternatecouplinginputsofadatadrivenmodelforoptimumdailystreamflowpredictionincalibratedswatbilstmrainfallrunoffmodeling
AT afedullahkhan exploringalternatecouplinginputsofadatadrivenmodelforoptimumdailystreamflowpredictionincalibratedswatbilstmrainfallrunoffmodeling
AT abdullahnadeem exploringalternatecouplinginputsofadatadrivenmodelforoptimumdailystreamflowpredictionincalibratedswatbilstmrainfallrunoffmodeling
AT jinleichen exploringalternatecouplinginputsofadatadrivenmodelforoptimumdailystreamflowpredictionincalibratedswatbilstmrainfallrunoffmodeling
AT kseniiausanova exploringalternatecouplinginputsofadatadrivenmodelforoptimumdailystreamflowpredictionincalibratedswatbilstmrainfallrunoffmodeling
AT kseniiausanova exploringalternatecouplinginputsofadatadrivenmodelforoptimumdailystreamflowpredictionincalibratedswatbilstmrainfallrunoffmodeling
AT hamadalmujibah exploringalternatecouplinginputsofadatadrivenmodelforoptimumdailystreamflowpredictionincalibratedswatbilstmrainfallrunoffmodeling
AT hashemalyami exploringalternatecouplinginputsofadatadrivenmodelforoptimumdailystreamflowpredictionincalibratedswatbilstmrainfallrunoffmodeling
AT muhammadabid exploringalternatecouplinginputsofadatadrivenmodelforoptimumdailystreamflowpredictionincalibratedswatbilstmrainfallrunoffmodeling