Data-driven estimation for permeability of simplex pore-throat reservoirs via an improved light gradient boosting machine: A demonstration of sand-mud profile, Ordos Basin, northern China

Gu, Yufeng; Yang, Yang; Gao, Yinshan; Yan, Shi; Zhang, Daoyong; Zhang, Chen

doi:10.1016/j.petrol.2022.110909

Cited by 8 publications

(2 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…LightGBM is a gradient-supervised technique based on decision trees and the idea of boosting algorithms 95 . LightGBM technique, which includes several decision trees, is applicable in various ML tasks like regression, classification, and ranking 96 – 98 . Each LightGBM technique employs a powerful learning framework to produce prediction values 99 .…”

Section: Methodsmentioning

confidence: 99%

Modeling CO2 solubility in water using gradient boosting and light gradient boosting machine

Mahmoudzadeh,

Amiri-Ramsheh,

Atashrouz

et al. 2024

Sci Rep

View full text Add to dashboard Cite

The growing application of carbon dioxide (CO2) in various environmental and energy fields, including carbon capture and storage (CCS) and several CO2-based enhanced oil recovery (EOR) techniques, highlights the importance of studying the phase equilibria of this gas with water. Therefore, accurate prediction of CO2 solubility in water becomes an important thermodynamic property. This study focused on developing two powerful intelligent models, namely gradient boosting (GBoost) and light gradient boosting machine (LightGBM) that predict CO2 solubility in water with high accuracy. The results revealed the outperformance of the GBoost model with root mean square error (RMSE) and determination coefficient (R2) of 0.137 mol/kg and 0.9976, respectively. The trend analysis demonstrated that the developed models were highly capable of detecting the physical trend of CO2 solubility in water across various pressure and temperature ranges. Moreover, the Leverage technique was employed to identify suspected data points as well as the applicability domain of the proposed models. The results showed that less than 5% of the data points were detected as outliers representing the large applicability domain of intelligent models. The outcome of this research provided insight into the potential of intelligent models in predicting solubility of CO2 in pure water.

show abstract

Section: Methodsmentioning

confidence: 99%

Modeling CO2 solubility in water using gradient boosting and light gradient boosting machine

Mahmoudzadeh,

Amiri-Ramsheh,

Atashrouz

et al. 2024

Sci Rep

View full text Add to dashboard Cite

show abstract

“…The EFB algorithm can combine many exclusive characteristics to a much less characteristic density that can dramatically avoid unnecessary calculations for zero feature value [88]. The LightGBM algorithm is a histogram-based algorithm that inserts continuous feature (attribute) into discrete values [89], giving rise to faster training speed with higher efficiency and reduced memory usage [90], [91].…”

Section: Light Gradient Boosting Machine (Lightgbm)mentioning

confidence: 99%

Boosting Algorithm to Handle Unbalanced Classification of PM_2.5 Concentration Levels by Observing Meteorological Parameters in Jakarta-Indonesia Using AdaBoost, XGBoost, CatBoost, and LightGBM

et al. 2023

View full text Add to dashboard Cite

show abstract

Employing ensemble learning techniques for modeling nanofluids' specific heat capacity

Deymi

Hadavimoghaddam

Atashrouz

et al. 2023

International Communications in Heat and Mass Transfer

View full text Add to dashboard Cite

Data-driven estimation for permeability of simplex pore-throat reservoirs via an improved light gradient boosting machine: A demonstration of sand-mud profile, Ordos Basin, northern China

Cited by 8 publications

References 27 publications

Modeling CO2 solubility in water using gradient boosting and light gradient boosting machine

Modeling CO2 solubility in water using gradient boosting and light gradient boosting machine

Boosting Algorithm to Handle Unbalanced Classification of PM_2.5 Concentration Levels by Observing Meteorological Parameters in Jakarta-Indonesia Using AdaBoost, XGBoost, CatBoost, and LightGBM

Employing ensemble learning techniques for modeling nanofluids' specific heat capacity

Contact Info

Product

Resources

About

Data-driven estimation for permeability of simplex pore-throat reservoirs via an improved light gradient boosting machine: A demonstration of sand-mud profile, Ordos Basin, northern China

Cited by 8 publications

References 27 publications

Modeling CO2 solubility in water using gradient boosting and light gradient boosting machine

Modeling CO2 solubility in water using gradient boosting and light gradient boosting machine

Boosting Algorithm to Handle Unbalanced Classification of PM2.5 Concentration Levels by Observing Meteorological Parameters in Jakarta-Indonesia Using AdaBoost, XGBoost, CatBoost, and LightGBM

Employing ensemble learning techniques for modeling nanofluids' specific heat capacity

Contact Info

Product

Resources

About

Boosting Algorithm to Handle Unbalanced Classification of PM_2.5 Concentration Levels by Observing Meteorological Parameters in Jakarta-Indonesia Using AdaBoost, XGBoost, CatBoost, and LightGBM