An extreme forecast index-driven runoff prediction approach using stacking ensemble learning

Runoff prediction plays a crucial role in hydropower generation and flood prevention, enhancing prediction accuracy in hydrology. This study proposes an extreme forecast index (EFI)-driven runoff prediction approach using stacking ensemble learning to improve prediction performance. EFI is introduce...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhiyuan Leng, Lu Chen, Binlin Yang, Siming Li, Bin Yi
Format: Article
Language:English
Published: Taylor & Francis Group 2024-12-01
Series:Geomatics, Natural Hazards & Risk
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/19475705.2024.2353144
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850246975465717760
author Zhiyuan Leng
Lu Chen
Binlin Yang
Siming Li
Bin Yi
author_facet Zhiyuan Leng
Lu Chen
Binlin Yang
Siming Li
Bin Yi
author_sort Zhiyuan Leng
collection DOAJ
description Runoff prediction plays a crucial role in hydropower generation and flood prevention, enhancing prediction accuracy in hydrology. This study proposes an extreme forecast index (EFI)-driven runoff prediction approach using stacking ensemble learning to improve prediction performance. EFI is introduced as an input into four machine learning models (Support Vector Regression, Multi-layer Perceptron, Gradient Boosting Decision Tree, and Ridge Regression) for runoff prediction with lead times of 24 h, 48 h, and 72 h. The stacking ensemble learning framework comprises four base-models and a meta-model, and model hyperparameters are re-optimized using the particle swarm optimization algorithm. The approach focuses on predicting the inflow processes of the Geheyan Reservoir in the Qing River using EFI and runoff time series. Results demonstrate that the EFI-runoff simulation can improve runoff prediction capability due to EFI’s higher sensitivity to observed runoff, and the proposed stacking ensemble learning model outperforms the individual model in predicting runoff with all lead times. The relative flood peak error, mean relative error, root mean square error, and Nash-Sutcliffe efficiency coefficient of the model’s one-day-ahead prediction are 7.987%, 22.421%, 632.871 m3/s, and 0.771, respectively. Therefore, this approach can be effectively utilized to improve accuracy in short-term runoff prediction applications.
format Article
id doaj-art-2c00889b58a344e09ccbfc657e259471
institution OA Journals
issn 1947-5705
1947-5713
language English
publishDate 2024-12-01
publisher Taylor & Francis Group
record_format Article
series Geomatics, Natural Hazards & Risk
spelling doaj-art-2c00889b58a344e09ccbfc657e2594712025-08-20T01:59:04ZengTaylor & Francis GroupGeomatics, Natural Hazards & Risk1947-57051947-57132024-12-0115110.1080/19475705.2024.2353144An extreme forecast index-driven runoff prediction approach using stacking ensemble learningZhiyuan Leng0Lu Chen1Binlin Yang2Siming Li3Bin Yi4School of Civil and Hydraulic Engineering, Huazhong University of Science and Technology, Wuhan, ChinaSchool of Civil and Hydraulic Engineering, Huazhong University of Science and Technology, Wuhan, ChinaSchool of Civil and Hydraulic Engineering, Huazhong University of Science and Technology, Wuhan, ChinaSchool of Civil and Hydraulic Engineering, Huazhong University of Science and Technology, Wuhan, ChinaSchool of Civil and Hydraulic Engineering, Huazhong University of Science and Technology, Wuhan, ChinaRunoff prediction plays a crucial role in hydropower generation and flood prevention, enhancing prediction accuracy in hydrology. This study proposes an extreme forecast index (EFI)-driven runoff prediction approach using stacking ensemble learning to improve prediction performance. EFI is introduced as an input into four machine learning models (Support Vector Regression, Multi-layer Perceptron, Gradient Boosting Decision Tree, and Ridge Regression) for runoff prediction with lead times of 24 h, 48 h, and 72 h. The stacking ensemble learning framework comprises four base-models and a meta-model, and model hyperparameters are re-optimized using the particle swarm optimization algorithm. The approach focuses on predicting the inflow processes of the Geheyan Reservoir in the Qing River using EFI and runoff time series. Results demonstrate that the EFI-runoff simulation can improve runoff prediction capability due to EFI’s higher sensitivity to observed runoff, and the proposed stacking ensemble learning model outperforms the individual model in predicting runoff with all lead times. The relative flood peak error, mean relative error, root mean square error, and Nash-Sutcliffe efficiency coefficient of the model’s one-day-ahead prediction are 7.987%, 22.421%, 632.871 m3/s, and 0.771, respectively. Therefore, this approach can be effectively utilized to improve accuracy in short-term runoff prediction applications.https://www.tandfonline.com/doi/10.1080/19475705.2024.2353144Runoff predictionextreme forecast indexmachine learningstacking ensemble learningparticle swarm optimization
spellingShingle Zhiyuan Leng
Lu Chen
Binlin Yang
Siming Li
Bin Yi
An extreme forecast index-driven runoff prediction approach using stacking ensemble learning
Geomatics, Natural Hazards & Risk
Runoff prediction
extreme forecast index
machine learning
stacking ensemble learning
particle swarm optimization
title An extreme forecast index-driven runoff prediction approach using stacking ensemble learning
title_full An extreme forecast index-driven runoff prediction approach using stacking ensemble learning
title_fullStr An extreme forecast index-driven runoff prediction approach using stacking ensemble learning
title_full_unstemmed An extreme forecast index-driven runoff prediction approach using stacking ensemble learning
title_short An extreme forecast index-driven runoff prediction approach using stacking ensemble learning
title_sort extreme forecast index driven runoff prediction approach using stacking ensemble learning
topic Runoff prediction
extreme forecast index
machine learning
stacking ensemble learning
particle swarm optimization
url https://www.tandfonline.com/doi/10.1080/19475705.2024.2353144
work_keys_str_mv AT zhiyuanleng anextremeforecastindexdrivenrunoffpredictionapproachusingstackingensemblelearning
AT luchen anextremeforecastindexdrivenrunoffpredictionapproachusingstackingensemblelearning
AT binlinyang anextremeforecastindexdrivenrunoffpredictionapproachusingstackingensemblelearning
AT simingli anextremeforecastindexdrivenrunoffpredictionapproachusingstackingensemblelearning
AT binyi anextremeforecastindexdrivenrunoffpredictionapproachusingstackingensemblelearning
AT zhiyuanleng extremeforecastindexdrivenrunoffpredictionapproachusingstackingensemblelearning
AT luchen extremeforecastindexdrivenrunoffpredictionapproachusingstackingensemblelearning
AT binlinyang extremeforecastindexdrivenrunoffpredictionapproachusingstackingensemblelearning
AT simingli extremeforecastindexdrivenrunoffpredictionapproachusingstackingensemblelearning
AT binyi extremeforecastindexdrivenrunoffpredictionapproachusingstackingensemblelearning