Novel hybrid and weighted ensemble models to predict river discharge series with outliers

In this study, a novel hybrid framework named HVK/HVA-HEM was designed to predict river discharge with outliers. Firstly, the Hampel filter (HF) identifies and corrects outliers in the discharge series. Next, this series was denoised and decomposed using ensemble empirical mode decomposition (EEMD)...

Full description

Saved in:
Bibliographic Details
Main Authors: Maha Shabbir, Sohail Chand, Farhat Iqbal
Format: Article
Language:English
Published: Elsevier 2024-04-01
Series:Kuwait Journal of Science
Subjects:
Online Access:https://www.sciencedirect.com/science/article/pii/S2307410824000130
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849725773532889088
author Maha Shabbir
Sohail Chand
Farhat Iqbal
author_facet Maha Shabbir
Sohail Chand
Farhat Iqbal
author_sort Maha Shabbir
collection DOAJ
description In this study, a novel hybrid framework named HVK/HVA-HEM was designed to predict river discharge with outliers. Firstly, the Hampel filter (HF) identifies and corrects outliers in the discharge series. Next, this series was denoised and decomposed using ensemble empirical mode decomposition (EEMD) and variational mode decomposition (VMD) respectively. The HF-VMD components were employed to K-nearest neighbor (KNN) and autoregressive integrated moving average (ARIMA) models, while the HF-EEMD series was applied to the multilayer perceptron (MLP) model to obtain the predictions of the proposed HVK(HF-VMD-KNN), HVA(HF-VMD-ARIMA), and HEM(HF-EEMD-MLP) hybrid models. Lastly, using the mean absolute error (MAE) weights of HVK, HVA and HEM predictions, the HVK-HEM and HVA-HEM models were formulated. The application of the new hybrid framework was displayed using the discharge of four rivers in Pakistan. In terms of the RMSE of Kabul River, the HEM hybrid model had better performance than MLP (175.2053 m3/s), HF-MLP (156.1853 m3/s), EEMD-MLP (133.4049 m3/s) and VMD-MLP (170.1337 m3/s). Similarly, the proposed HVK and HEM hybrid models are more efficient than their respective single, HF, EEMD, and VMD-based models. Overall, the proposed HVA-HEM hybrid model outperformed all competing and proposed models.
format Article
id doaj-art-769a751024d449748ffe243bc3e32109
institution DOAJ
issn 2307-4116
language English
publishDate 2024-04-01
publisher Elsevier
record_format Article
series Kuwait Journal of Science
spelling doaj-art-769a751024d449748ffe243bc3e321092025-08-20T03:10:23ZengElsevierKuwait Journal of Science2307-41162024-04-01512100188https://doi.org/10.1016/j.kjs.2024.100188Novel hybrid and weighted ensemble models to predict river discharge series with outliersMaha Shabbir0https://orcid.org/0000-0002-1525-2505Sohail Chand1https://orcid.org/0000-0002-4564-143XFarhat Iqbal2https://orcid.org/0000-0002-8579-0966College of Statistical Sciences, University of the Punjab, Lahore, PakistanCollege of Statistical Sciences, University of the Punjab, Lahore, PakistanDepartment of Mathematics, Imam Abdulrahman Bin Faisal University, Saudi ArabiaIn this study, a novel hybrid framework named HVK/HVA-HEM was designed to predict river discharge with outliers. Firstly, the Hampel filter (HF) identifies and corrects outliers in the discharge series. Next, this series was denoised and decomposed using ensemble empirical mode decomposition (EEMD) and variational mode decomposition (VMD) respectively. The HF-VMD components were employed to K-nearest neighbor (KNN) and autoregressive integrated moving average (ARIMA) models, while the HF-EEMD series was applied to the multilayer perceptron (MLP) model to obtain the predictions of the proposed HVK(HF-VMD-KNN), HVA(HF-VMD-ARIMA), and HEM(HF-EEMD-MLP) hybrid models. Lastly, using the mean absolute error (MAE) weights of HVK, HVA and HEM predictions, the HVK-HEM and HVA-HEM models were formulated. The application of the new hybrid framework was displayed using the discharge of four rivers in Pakistan. In terms of the RMSE of Kabul River, the HEM hybrid model had better performance than MLP (175.2053 m3/s), HF-MLP (156.1853 m3/s), EEMD-MLP (133.4049 m3/s) and VMD-MLP (170.1337 m3/s). Similarly, the proposed HVK and HEM hybrid models are more efficient than their respective single, HF, EEMD, and VMD-based models. Overall, the proposed HVA-HEM hybrid model outperformed all competing and proposed models.https://www.sciencedirect.com/science/article/pii/S2307410824000130river dischargeoutliersdecompositiondenoisinghybrid models
spellingShingle Maha Shabbir
Sohail Chand
Farhat Iqbal
Novel hybrid and weighted ensemble models to predict river discharge series with outliers
Kuwait Journal of Science
river discharge
outliers
decomposition
denoising
hybrid models
title Novel hybrid and weighted ensemble models to predict river discharge series with outliers
title_full Novel hybrid and weighted ensemble models to predict river discharge series with outliers
title_fullStr Novel hybrid and weighted ensemble models to predict river discharge series with outliers
title_full_unstemmed Novel hybrid and weighted ensemble models to predict river discharge series with outliers
title_short Novel hybrid and weighted ensemble models to predict river discharge series with outliers
title_sort novel hybrid and weighted ensemble models to predict river discharge series with outliers
topic river discharge
outliers
decomposition
denoising
hybrid models
url https://www.sciencedirect.com/science/article/pii/S2307410824000130
work_keys_str_mv AT mahashabbir novelhybridandweightedensemblemodelstopredictriverdischargeserieswithoutliers
AT sohailchand novelhybridandweightedensemblemodelstopredictriverdischargeserieswithoutliers
AT farhatiqbal novelhybridandweightedensemblemodelstopredictriverdischargeserieswithoutliers