A CNN deep learning approach to scour depth estimation around complex bridge piers in steady flow environments

Abstract Scour around complex bridge piers (CBP) caused by sediment erosion due to steady flow is a critical challenge in hydraulic engineering, often leading to structural instabilities and failures. The accurate estimation of maximum scour depth is crucial for ensuring bridge safety and optimizing...

Full description

Saved in:
Bibliographic Details
Main Authors: Ngoc Thi Huynh, Anh Thu Thi Phan, Tan Tai Trieu, Ho-Hong-Duy Nguyen, Thanh Nhan Nguyen
Format: Article
Language:English
Published: SpringerOpen 2025-06-01
Series:Advances in Bridge Engineering
Subjects:
Online Access:https://doi.org/10.1186/s43251-025-00170-8
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849238323658227712
author Ngoc Thi Huynh
Anh Thu Thi Phan
Tan Tai Trieu
Ho-Hong-Duy Nguyen
Thanh Nhan Nguyen
author_facet Ngoc Thi Huynh
Anh Thu Thi Phan
Tan Tai Trieu
Ho-Hong-Duy Nguyen
Thanh Nhan Nguyen
author_sort Ngoc Thi Huynh
collection DOAJ
description Abstract Scour around complex bridge piers (CBP) caused by sediment erosion due to steady flow is a critical challenge in hydraulic engineering, often leading to structural instabilities and failures. The accurate estimation of maximum scour depth is crucial for ensuring bridge safety and optimizing design. Traditional empirical methods and physics-based models, while widely utilized, often struggle to capture the complex interactions between hydrodynamic forces, sediment transport, and varying pier geometries, leading to conservative or inaccurate predictions. This study presents a one-dimensional convolutional neural network (1D CNN) and long short-term memory (LSTM) deep learning models for predicting the maximum scour depth around CBP under steady current conditions in a clear-water environment. The proposed model leverages the ability of 1D CNNs to process high-dimensional input dataset, capturing intricate non-linear relationships between influential parameters, such as flow velocity, pier configurations, sediment properties, and water depth. The dataset was transformed into non-dimensional forms using the Buckingham Pi theorem to enhance model generalization. The 1D CNN model was trained and validated using an extensive dataset, and its performance was benchmarked against established empirical models, including FDOT, HEC-18, and Coleman’s equation. Results show that the proposed 1D CNN model significantly outperforms traditional approaches, achieving higher coefficient of determination (R 2  = 0.85) values and lower root mean squared error (RMSE = 0.1125), mean absolute error (MAE = 0.1078), and scatter index (SI = 0.1149). Moreover, the model's bias (B = -0.0194) and standard error (SE = 0.1147) remain minimal across unseen datasets, demonstrating robust predictive capability. This research highlights the potential of deep learning as a reliable and precise tool for scour depth prediction, contributing to improved risk assessment and sustainable bridge design under steady flow environments.
format Article
id doaj-art-ab85f0d60b4a4207918a2d935dd6267a
institution Kabale University
issn 2662-5407
language English
publishDate 2025-06-01
publisher SpringerOpen
record_format Article
series Advances in Bridge Engineering
spelling doaj-art-ab85f0d60b4a4207918a2d935dd6267a2025-08-20T04:01:40ZengSpringerOpenAdvances in Bridge Engineering2662-54072025-06-016112910.1186/s43251-025-00170-8A CNN deep learning approach to scour depth estimation around complex bridge piers in steady flow environmentsNgoc Thi Huynh0Anh Thu Thi Phan1Tan Tai Trieu2Ho-Hong-Duy Nguyen3Thanh Nhan Nguyen4Faculty of Civil Engineering, Ho Chi Minh City University of Technology (HCMUT)Faculty of Civil Engineering, Ho Chi Minh City University of Technology (HCMUT)Faculty of Civil Engineering, Ho Chi Minh City University of Technology (HCMUT)Ocean Engineering Department, Pukyong National UniversityOcean Engineering Department, Pukyong National UniversityAbstract Scour around complex bridge piers (CBP) caused by sediment erosion due to steady flow is a critical challenge in hydraulic engineering, often leading to structural instabilities and failures. The accurate estimation of maximum scour depth is crucial for ensuring bridge safety and optimizing design. Traditional empirical methods and physics-based models, while widely utilized, often struggle to capture the complex interactions between hydrodynamic forces, sediment transport, and varying pier geometries, leading to conservative or inaccurate predictions. This study presents a one-dimensional convolutional neural network (1D CNN) and long short-term memory (LSTM) deep learning models for predicting the maximum scour depth around CBP under steady current conditions in a clear-water environment. The proposed model leverages the ability of 1D CNNs to process high-dimensional input dataset, capturing intricate non-linear relationships between influential parameters, such as flow velocity, pier configurations, sediment properties, and water depth. The dataset was transformed into non-dimensional forms using the Buckingham Pi theorem to enhance model generalization. The 1D CNN model was trained and validated using an extensive dataset, and its performance was benchmarked against established empirical models, including FDOT, HEC-18, and Coleman’s equation. Results show that the proposed 1D CNN model significantly outperforms traditional approaches, achieving higher coefficient of determination (R 2  = 0.85) values and lower root mean squared error (RMSE = 0.1125), mean absolute error (MAE = 0.1078), and scatter index (SI = 0.1149). Moreover, the model's bias (B = -0.0194) and standard error (SE = 0.1147) remain minimal across unseen datasets, demonstrating robust predictive capability. This research highlights the potential of deep learning as a reliable and precise tool for scour depth prediction, contributing to improved risk assessment and sustainable bridge design under steady flow environments.https://doi.org/10.1186/s43251-025-00170-8Complex bridge pier1D CNNLSTMMaximum scour depth
spellingShingle Ngoc Thi Huynh
Anh Thu Thi Phan
Tan Tai Trieu
Ho-Hong-Duy Nguyen
Thanh Nhan Nguyen
A CNN deep learning approach to scour depth estimation around complex bridge piers in steady flow environments
Advances in Bridge Engineering
Complex bridge pier
1D CNN
LSTM
Maximum scour depth
title A CNN deep learning approach to scour depth estimation around complex bridge piers in steady flow environments
title_full A CNN deep learning approach to scour depth estimation around complex bridge piers in steady flow environments
title_fullStr A CNN deep learning approach to scour depth estimation around complex bridge piers in steady flow environments
title_full_unstemmed A CNN deep learning approach to scour depth estimation around complex bridge piers in steady flow environments
title_short A CNN deep learning approach to scour depth estimation around complex bridge piers in steady flow environments
title_sort cnn deep learning approach to scour depth estimation around complex bridge piers in steady flow environments
topic Complex bridge pier
1D CNN
LSTM
Maximum scour depth
url https://doi.org/10.1186/s43251-025-00170-8
work_keys_str_mv AT ngocthihuynh acnndeeplearningapproachtoscourdepthestimationaroundcomplexbridgepiersinsteadyflowenvironments
AT anhthuthiphan acnndeeplearningapproachtoscourdepthestimationaroundcomplexbridgepiersinsteadyflowenvironments
AT tantaitrieu acnndeeplearningapproachtoscourdepthestimationaroundcomplexbridgepiersinsteadyflowenvironments
AT hohongduynguyen acnndeeplearningapproachtoscourdepthestimationaroundcomplexbridgepiersinsteadyflowenvironments
AT thanhnhannguyen acnndeeplearningapproachtoscourdepthestimationaroundcomplexbridgepiersinsteadyflowenvironments
AT ngocthihuynh cnndeeplearningapproachtoscourdepthestimationaroundcomplexbridgepiersinsteadyflowenvironments
AT anhthuthiphan cnndeeplearningapproachtoscourdepthestimationaroundcomplexbridgepiersinsteadyflowenvironments
AT tantaitrieu cnndeeplearningapproachtoscourdepthestimationaroundcomplexbridgepiersinsteadyflowenvironments
AT hohongduynguyen cnndeeplearningapproachtoscourdepthestimationaroundcomplexbridgepiersinsteadyflowenvironments
AT thanhnhannguyen cnndeeplearningapproachtoscourdepthestimationaroundcomplexbridgepiersinsteadyflowenvironments