Studying petrophysical properties of micritic limestones using machine learning methods

Nguyen‐Sy, Tuan; Vu, Minh‐Ngoc; Tran-Le, Anh-Dung; Tran, Bao-Viet; Nguyen, Thi-Thu-Nga; Nguyen, Thoi‐Trung

doi:10.1016/j.jappgeo.2020.104226

Cited by 9 publications

(6 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The XGB model, an advanced tree boosting system presented by Chen and Guestrin, 35 was confirmed to be a perfect machine-learning model for learning tabular datasets. 31,[36][37][38] It uses many additive functions f k to represent the relationship between the vector of input features X i and the output target y i of ith measurement as…”

Section: The Chosen Xgboost Modelmentioning

confidence: 99%

“…35 XGBoost model is considered for the present study because it was confirmed to outperform other advanced machine-learning models for different types of tabular datasets. 31,[36][37][38] Also, the main objective of this study is not to repeat a comparison between different machine-learning tools but it focuses more on the data treatment strategy. More precisely, we aim to demonstrate that adding more low-cost and measurable features to the initial dataset would significantly improve the accuracy of the machine-learning model.…”

Section: The Chosen Xgboost Modelmentioning

confidence: 99%

“…An extensive list of machine‐learning frameworks has been developed in literature including neural network models, 32 support vector models, 33 or tree‐based models, 34 among others. The XGB model, an advanced tree boosting system presented by Chen and Guestrin, 35 was confirmed to be a perfect machine‐learning model for learning tabular datasets 31,36–38 . It uses many additive functions

f_{k}

to represent the relationship between the vector of input features

X_{i}

and the output target

{\bar{y}}_{i}

of i th measurement as

{\bar{y}}_{i} goodbreak= y_{i}^{0} goodbreak+ η \sum_{k = 1}^{M} f_{k} ((), {boldX}_{i}),

where

y_{i}^{0}

is the initial guess of

{\bar{y}}_{i}

, it is simply an average overall measurement in the training subset;

η

is the learning rate and

M

the number of boosting trees.…”

Section: Optimized Machine‐learning Model For Predicting the Creep Of...mentioning

confidence: 99%

“…XGBoost model is considered for the present study because it was confirmed to outperform other advanced machine‐learning models for different types of tabular datasets 31,36–38 . Also, the main objective of this study is not to repeat a comparison between different machine‐learning tools but it focuses more on the data treatment strategy.…”

Section: Optimized Machine‐learning Model For Predicting the Creep Of...mentioning

confidence: 99%

See 3 more Smart Citations

Optimized machine‐learning methods for predicting the long‐term viscoelastic behavior of heterogeneous concrete mixtures

Nguyen‐Sy

Thai

2023

Structural Concrete

View full text Add to dashboard Cite

Long‐term creep compliance is one of the most important mechanical properties for evaluating the long‐term behavior of concrete structures. This paper aims to optimize machine‐learning models to predict this viscoelastic property. The most relevant dataset available in the literature is considered, cleaned, and preprocessed to optimize the outcome. The advanced XGBoost model, which is to be the most effective shallow machine‐learning model for modeling tabular datasets, is employed in this study to maximize model accuracy. Short‐term creep compliances of a given sample at typical ages are used as input features to model the long‐term creep compliance of concrete. This approach outperforms standard machine‐learning approaches that do not include short‐term creep as an input feature. Indeed, the short‐term behavior of concrete strongly influents its long‐term one. The optimized machine model presented herein is accurate and useful for practical applications. It uses input features that are easy to obtain to predict long‐term creep compliance up to several decades, which is difficult and expensive to measure.

show abstract

Section: The Chosen Xgboost Modelmentioning

confidence: 99%

Section: The Chosen Xgboost Modelmentioning

confidence: 99%

f_{k}

to represent the relationship between the vector of input features

X_{i}

and the output target

{\bar{y}}_{i}

of i th measurement as

{\bar{y}}_{i} goodbreak= y_{i}^{0} goodbreak+ η \sum_{k = 1}^{M} f_{k} ((), {boldX}_{i}),

where

y_{i}^{0}

is the initial guess of

{\bar{y}}_{i}

, it is simply an average overall measurement in the training subset;

η

is the learning rate and

M

the number of boosting trees.…”

Section: Optimized Machine‐learning Model For Predicting the Creep Of...mentioning

confidence: 99%

Section: Optimized Machine‐learning Model For Predicting the Creep Of...mentioning

confidence: 99%

See 2 more Smart Citations

Optimized machine‐learning methods for predicting the long‐term viscoelastic behavior of heterogeneous concrete mixtures

Nguyen‐Sy

Thai

2023

Structural Concrete

View full text Add to dashboard Cite

show abstract

“…Yan et al applied XGBoost to well logging interpretation of tight sandstone and found that it performed better for fluid identification than the SVM and RF models [27]. Nguyen et al used XGBoost for predicting compressional and shear waves in micritic limestones and achieved higher accuracy than an artificial neural network (ANN) and SVM [42]. Gu et al used a particle swarm optimization (PSO) algorithm to determine the hyperparameters of the XGBoost algorithm and applied XGBoost to predict the permeability of tight sandstone [43].…”

Section: Introductionmentioning

confidence: 99%

Total Organic Carbon Content Prediction in Lacustrine Shale Using Extreme Gradient Boosting Machine Learning Based on Bayesian Optimization

Liu¹,

Tian²,

Chen³

2021

Geofluids

View full text Add to dashboard Cite

The total organic carbon (TOC) content is a critical parameter for estimating shale oil resources. However, common TOC prediction methods rely on empirical formulas, and their applicability varies widely from region to region. In this study, a novel data-driven Bayesian optimization extreme gradient boosting (XGBoost) model was proposed to predict the TOC content using wireline log data. The lacustrine shale in the Damintun Sag, Bohai Bay Basin, China, was used as a case study. Firstly, correlation analysis was used to analyze the relationship between the well logs and the core-measured TOC data. Based on the degree of correlation, six logging curves reflecting TOC content were selected to construct training dataset for machine learning. Then, the performance of the XGBoost model was tested using K -fold cross-validation, and the hyperparameters of the model were determined using a Bayesian optimization method to improve the search efficiency and reduce the uncertainty caused by the rule of thumb. Next, through the analysis of prediction errors, the coefficient of determination ( R 2 ) of the TOC content predicted by the XGBoost model and the core-measured TOC content reached 0.9135. The root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) were 0.63, 0.77, and 12.55%, respectively. In addition, five commonly used methods, namely, Δ log R method, random forest, support vector machine, K -nearest neighbors, and multiple linear regression, were used to predict the TOC content to confirm that the XGBoost model has higher prediction accuracy and better robustness. Finally, the proposed approach was applied to predict the TOC curves of 20 exploration wells in the Damintun Sag. We obtained quantitative contour maps of the TOC content of this block for the first time. The results of this study facilitate the rapid detection of the sweet spots of the lacustrine shale oil.

show abstract

Prediction of Mohr-Coulomb Constants of Selected Korean Rocks Based on Extreme Gradient Boosting Method and Its Evaluation

2022

View full text Add to dashboard Cite

Studying petrophysical properties of micritic limestones using machine learning methods

Cited by 9 publications

References 22 publications

Optimized machine‐learning methods for predicting the long‐term viscoelastic behavior of heterogeneous concrete mixtures

Optimized machine‐learning methods for predicting the long‐term viscoelastic behavior of heterogeneous concrete mixtures

Total Organic Carbon Content Prediction in Lacustrine Shale Using Extreme Gradient Boosting Machine Learning Based on Bayesian Optimization

Prediction of Mohr-Coulomb Constants of Selected Korean Rocks Based on Extreme Gradient Boosting Method and Its Evaluation

Contact Info

Product

Resources

About