Machine-learning interpretability techniques for seismic performance assessment of infrastructure systems

Mangalathu, Sujith; Karthikeyan, Karthika; Feng, De‐Cheng; Jeon, Jong‐Su

doi:10.1016/j.engstruct.2021.112883

Cited by 79 publications

(12 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, with the development of artificial intelligence, some algorithms with data at the core have emerged [19]. Among these algorithms, machine learning has received remarkable attention of researchers, and there have been many successful examples [20][21][22][23][24]. In structure engineering, Hoang et al [25] constructed machine learning based alternatives for estimating the punching shear capacity of steel fiber reinforced concrete (SFRC) flat slabs.…”

Section: Introductionmentioning

confidence: 99%

Interpretable Machine Learning Models for Punching Shear Strength Estimation of FRP Reinforced Concrete Slabs

2022

View full text Add to dashboard Cite

Fiber reinforced polymer (FRP) serves as a prospective alternative to reinforcement in concrete slabs. However, similarly to traditional reinforced concrete slabs, FRP reinforced concrete slabs are susceptible to punching shear failure. Accounts of the insufficient consideration of impact factors, existing empirical models and design provisions for punching strength of FRP reinforced concrete slabs have some problems such as high bias and variance. This study established machine learning-based models to accurately predict the punching shear strength of FRP reinforced concrete slabs. A database of 121 groups of experimental results of FRP reinforced concrete slabs are collected from a literature review. Several machine learning algorithms, such as artificial neural network, support vector machine, decision tree, and adaptive boosting, are selected to build models and compare the performance between them. To demonstrate the predicted accuracy of machine learning, this paper also introduces 6 empirical models and design codes for comparative analysis. The comparative results demonstrate that adaptive boosting has the highest predicted precision, in which the root mean squared error, mean absolute error and coefficient of determination of which are 29.83, 23.00 and 0.99, respectively. GB 50010-2010 (2015) has the best predicted performance among these empirical models and design codes, and ACI 318-19 has the similar result. In addition, among these empirical models, the model proposed by El-Ghandour et al. (1999) has the highest predicted accuracy. According to the results obtained above, SHapley Additive exPlanation (SHAP) is adopted to illustrate the predicted process of AdaBoost. SHAP not only provides global and individual interpretations, but also carries out feature dependency analysis for each input variable. The interpretation results of the model reflect the importance and contribution of the factors that influence the punching shear strength in the machine learning model.

show abstract

Section: Introductionmentioning

confidence: 99%

Interpretable Machine Learning Models for Punching Shear Strength Estimation of FRP Reinforced Concrete Slabs

2022

View full text Add to dashboard Cite

show abstract

“…The formula is as follows:

where

is the number of input features, and

. The

variables typically represent a feature being observed

or unknown

, and the

are the feature attribution values [ 43 , 44 , 45 ].…”

Section: Methodsmentioning

confidence: 99%

Phase Transformation Temperature Prediction in Steels via Machine Learning

Zhang,

Cheng,

Pan

et al. 2024

Materials

View full text Add to dashboard Cite

The phase transformation temperature plays an important role in the design, production and heat treatment process of steels. In the present work, an improved version of the gradient-boosting method LightGBM has been utilized to study the influencing factors of the four phase transformation temperatures, namely Ac1, Ac3, the martensite transformation start (MS) temperature and the bainitic transformation start (BS) temperature. The effects of the alloying element were discussed in detail by comparing their influencing mechanisms on different phase transformation temperatures. The training accuracy was significantly improved by further introducing appropriate features related to atomic parameters. The melting temperature and coefficient of linear thermal expansion of the pure metals corresponding to the alloying elements, atomic Waber–Cromer pseudopotential radii and valence electron number were the top four among the eighteen atomic parameters used to improve the trained model performance. The training and prediction processes were analyzed using a partial dependence plot (PDP) and Shapley additive explanation (SHAP) methods to reveal the relationships between the features and phase transformation temperature.

show abstract

“…In other words, the physical relationship between the input features and the output response is not clear (Mangalathu et al., 2022). XAI tries to enhance the transparency of the DLMs by explaining the relationship between the input features (predictors or input variables) and the response variable (Mangalathu et al., 2022). This explainability approach is highly appreciated in the earthquake engineering field where designers, stakeholders, and decision‐makers are highly interested in having insights into the input–output variables relationship and the interpretability of the predicted response from the DLM.…”

Section: The Proposed Proceduresmentioning

confidence: 99%

“…Explainability of the DLM using XAI DLMs; (Zou et al, 2022) are considered "black boxes" that cannot provide an understandable justification regarding the predictions obtained. In other words, the physical relationship between the input features and the output response is not clear (Mangalathu et al, 2022). XAI tries to enhance the transparency of the DLMs by explaining the relationship between the input features (predictors or input variables) and the response variable (Mangalathu et al, 2022).…”

Section: 5mentioning

confidence: 99%

Explainable probabilistic deep learning framework for seismic assessment of structures using distribution‐free prediction intervals

Noureldin

Abuhmed

Saygi

et al. 2023

Computer aided Civil Eng

View full text Add to dashboard Cite

A new probabilistic framework is proposed for providing a distribution-free prediction interval (PI) of seismic responses required for various earthquake engineering applications. The framework overcomes the limitation of point prediction models and avoids the complexity of traditional probabilistic methods. The framework utilizes a few assumptions of probability distributions and requires no prior assumed statistical distribution for the PI. Ensemble probabilistic deep learning models (DLMs) are used to provide quality-driven PIs of seismic responses for low-to mid-rise buildings with limited irregularity. Considering these systems and ground motions with the aid of Monte Carlo simulation and nonlinear time-history analysis (NLTHA), huge datasets are generated for training. To have an insight into the probabilistic DLM, explainable artificial intelligence techniques are used. The superiority of the proposed framework in quantifying uncertainties is validated by comparison with the conventional Bayesian method. In addition, its applicability is investigated by providing bounds of seismic fragility curves, life cycle cost, and resilience index obtained by NLTHA for a benchmark case study model. The results showed that the proposed framework is robust and outperforms the conventional Bayesian method in uncertainty quantification for the considered dataset.

show abstract

Machine-learning interpretability techniques for seismic performance assessment of infrastructure systems

Cited by 79 publications

References 34 publications

Interpretable Machine Learning Models for Punching Shear Strength Estimation of FRP Reinforced Concrete Slabs

Interpretable Machine Learning Models for Punching Shear Strength Estimation of FRP Reinforced Concrete Slabs

Phase Transformation Temperature Prediction in Steels via Machine Learning

Explainable probabilistic deep learning framework for seismic assessment of structures using distribution‐free prediction intervals

Contact Info

Product

Resources

About