Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Estimating seepage in heterogeneous earthfill dams on permeable foundations using explainable machine learning.

Scientific reports·2026

Same author

Assessing the impact of groundwater abstraction and concrete dam fractures on saltwater intrusion using numerical modeling and interpretable machine learning.

Scientific reports·2026

Same author

Explainable ML modeling of saltwater intrusion control with underground barriers in coastal sloping aquifers.

Scientific reports·2025

Same author

Hydraulic Performance Modeling of Inclined Double Cutoff Walls Beneath Hydraulic Structures Using Optimized Ensemble Machine Learning.

Scientific reports·2025

Same author

Hybrid metaheuristic optimized Catboost models for construction cost estimation of concrete solid slabs.

Scientific reports·2025

Same author

Author Correction: Advanced predictive machine and deep learning models for round-ended CFST column.

Scientific reports·2025

Search research articles

Related Experiment Video

Updated: May 27, 2025

Curtain Flow Column: Optimization of Efficiency and Sensitivity

Curtain Flow Column: Optimization of Efficiency and Sensitivity

Published on: June 12, 2016

Advanced predictive machine and deep learning models for round-ended CFST column.

Feng Shen^1,2, Ishan Jha³, Haytham F Isleem^4,5

¹College of Civil Engineering, Huaqiao University, Xiamen, 361021, China.

Scientific Reports

|February 20, 2025

Summary

This summary is machine-generated.

Machine learning models accurately predict concrete-filled steel tubular (CFST) column capacity. CatBoost achieved the highest accuracy, outperforming traditional methods and deep learning models for structural analysis.

Keywords:

Axial load prediction Concrete-filled steel tubular columns Deep learning architectures Machine learning models SHAP Analysis Structural engineering applications

More Related Videos

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

Related Experiment Videos

Last Updated: May 27, 2025

Curtain Flow Column: Optimization of Efficiency and Sensitivity

Curtain Flow Column: Optimization of Efficiency and Sensitivity

Published on: June 12, 2016

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

Area of Science:

Structural Engineering
Materials Science
Computational Mechanics

Background:

Confined columns, specifically concrete-filled steel tubular (CFST) columns, are vital in modern infrastructure for their strength and efficiency.
Accurate prediction of axial load-carrying capacity (Pcc) is crucial for ensuring structural integrity and optimizing designs.
Existing analytical solutions often struggle to capture the complex, nonlinear behavior of CFST columns.

Purpose of the Study:

To develop and evaluate data-driven approaches, specifically machine learning (ML) and deep learning (DL) models, for predicting the axial load-carrying capacity of CFST columns.
To benchmark the performance of these ML/DL models against established analytical solutions.
To identify key input features influencing the load-carrying capacity of CFST columns.

Main Methods:

Utilized an extensive dataset comprising 200 experimental tests on CFST stub columns.
Evaluated six models: LightGBM, XGBoost, CatBoost (ML), and Deep Neural Network (DNN), Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM) (DL).
Employed SHapley Additive exPlanations (SHAP) for feature importance analysis.

Main Results:

The CatBoost model demonstrated superior predictive accuracy with an RMSE of 396.50 kN and R² of 0.932.
ML models generally outperformed DL models, with DNN achieving an RMSE of 496.19 kN and R² of 0.958, while LSTM underperformed (RMSE: 2010.46 kN).
Cross-sectional width was identified as the most significant positive predictor, while column length was a key negative influencer.

Conclusions:

Data-driven models, particularly CatBoost, offer robust and accurate predictions for CFST column capacity, surpassing traditional analytical methods.
The developed models provide interpretable insights into feature importance, aiding engineering judgment.
A user-friendly Python interface enables practical, real-time application of these advanced predictive tools in structural design.