The controlling factors and prediction model of pore structure in global shale sediments based on random forest machine learning

Jiang, Fujie; Huo, Lina; Chen, Di; Cao, Lei; Zhao, Renjie; Li, Yuan; Guo, Tingwei

doi:10.1016/j.earscirev.2023.104442

Cited by 14 publications

(15 citation statements)

References 191 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It ensures the high accuracy and generalization performance of the random forest method. Therefore, the random forest algorithm was used to obtain variation importance measures (VIM) to rank the contribution of each variable by the Gini index. , …”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Performance Prediction and Heating Parameter Optimization of Organic-Rich Shale In Situ Conversion Based on Numerical Simulation and Artificial Intelligence Algorithms

Liu,

Yao,

Liu

et al. 2024

ACS Omega

View full text Add to dashboard Cite

In situ conversion technology is a green and effective way to realize the development of organic-rich shale. Supercritical CO 2 can be used as a good heating medium for shale in situ conversion. Numerical simulation is an important means to explore the shale in situ conversion process, but it requires a lot of time and computational cost for in situ conversion simulation under different working conditions. Therefore, a computational framework for rapid prediction of shale in situ conversion development performance and heating parameter optimization is proposed by coupling artificial neural network (ANN) and particle swarm optimization (PSO). The results indicated that kerogen pyrolysis and hydrocarbon product release mainly occurred within 2 years of shale in situ conversion. The production curves of pyrolysis hydrocarbon obviously slowed after in situ conversion for 2 years. The database was constructed by a large number of in situ conversion simulations, and Pearson correlation analysis and the random forest method were adopted to obtain seven main controlling factors affecting reservoir temperature and hydrocarbon production. The determination coefficient of the obtained ANN-based prediction models is higher than 97%, and the mean square error (MSE) is lower than 0.3%. The basic reservoir case can choose to inject 350−450 °C supercritical CO 2 (Sc-CO 2 ) fluid with a rate of 600 m 3 /day to obtain a more promising development effect. The heating parameter optimization for three typical reservoir cases using PSO was performed, and reasonable injection temperature and injection rate were obtained. It realized accurate development prediction and rapid heating parameter optimization, which helps the effective application of shale in situ conversion development design.

show abstract

Section: Methodsmentioning

confidence: 99%

“…Therefore, the random forest algorithm was used to obtain variation importance measures (VIM) to rank the contribution of each variable by the Gini index. 56,57 3.3. ANN-Based Prediction Model.…”

Section: Database Optimizationmentioning

confidence: 99%

Performance Prediction and Heating Parameter Optimization of Organic-Rich Shale In Situ Conversion Based on Numerical Simulation and Artificial Intelligence Algorithms

Liu,

Yao,

Liu

et al. 2024

ACS Omega

View full text Add to dashboard Cite

show abstract

“…There is considerable interest in machine learning research concerning ensemble learning methods for generating many classifiers and combining their results. Many ensemble methods are widely used, including boosting bagging and, more recently, random forest (RF) 49 . The RF approach converts input vectors into a planned work of tree predictors using random input samples.…”

Section: Soft Computing Techniquesmentioning

confidence: 99%

Performance analysis and modelling of circular jets aeration in an open channel using soft computing techniques

Puri,

Kumar,

Kumar

et al. 2024

Sci Rep

View full text Add to dashboard Cite

Dissolved oxygen (DO) is an important parameter in assessing water quality. The reduction in DO concentration is the result of eutrophication, which degrades the quality of water. Aeration is the best way to enhance the DO concentration. In the current study, the aeration efficiency (E20) of various numbers of circular jets in an open channel was experimentally investigated for different channel angle of inclination (θ), discharge (Q), number of jets (Jn), Froude number (Fr), and hydraulic radius of each jet (HRJn). The statistical results show that jets from 8 to 64 significantly provide aeration in the open channel. The aeration efficiency and input parameters are modelled into a linear relationship. Additionally, utilizing WEKA software, three soft computing models for predicting aeration efficiency were created with Artificial Neural Network (ANN), M5P, and Random Forest (RF). Performance evaluation results and box plot have shown that ANN is the outperforming model with correlation coefficient (CC) = 0.9823, mean absolute error (MAE) = 0.0098, and root mean square error (RMSE) = 0.0123 during the testing stage. In order to assess the influence of different input factors on the E20 of jets, a sensitivity analysis was conducted using the most effective model, i.e., ANN. The sensitivity analysis results indicate that the angle of inclination is the most influential input variable in predicting E20, followed by discharge and the number of jets.

show abstract

“…In the heterogeneous and anisotropic shale matrix, micro- (<2 nm) and mesopores (2–50 nm) form critical pore throat passageways, ,, enhancing the gas molecule-wall collisions, thereby inducing a slippage effect and enhancing apparent permeability ( k app ). , When the sizes of the pores in the reservoir are comparable to those of gas molecules, and the pore pressure drops due to depletion, slip flow becomes significant, causing deviations from conventional flow models like Darcy’s law . Despite its importance, the extent of slip flow’s influence on matrix transport at low pore pressures is still largely unclear .…”

Section: Introductionmentioning

confidence: 99%

Laboratory Observation of Fluid Flow in Depleted Shale Gas Reservoir: Coupling Effect of Sorbing and Non-sorbing Gas on Stress, Slippage, Flow Regime in Anisotropic and Fractured Shales

Bal,

Misra

2024

Energy Fuels

View full text Add to dashboard Cite

Understanding gas flow in depleted unconventional reservoirs is crucial but limited, particularly in organic-rich shale with ultrafine nanopores and high matrix compressibility. Here, we assess the apparent permeability (k app ) along perpendicular and parallel to bedding, as well as through fractures�using shale samples from three petroliferous basins in India. Our experiments simulate depleted reservoir conditions with varying mean pore pressures (P m ), using both sorbing (N 2 , CO 2 ) and nonsorbing (He, Ar) gases, and the results are compared to nanopore structures determined through low-pressure gas sorption and He-pycnometer. We further explored the gas fluid dynamic behavior, intrinsic permeability (k ∞ ), stress sensitivity, and effective stress coefficients and correlated between experimental variables and shale properties. We found that gas type and shale anisotropy significantly influence k app . He, exhibits the highest k app , followed by Ar, N 2 , and the lowest for CO 2 due to varying adsorption affinities. At lower effective stress (σ eff < 15 MPa), bedding parallel gas flow results in higher k app , while at higher stress, perpendicular flow increases permeability. Bedding perpendicular flow is matrix-dominated, while bedding parallel flow contains stress-sensitive microfractures serving as flow conduits. CO 2 in parallel bedding and fractured samples show a nonlinear relationship between slippage factor (b) and σ eff , indicating higher sensitivity compared to bedding perpendicular samples. Gas type exerts a stronger impact on b than σ eff . Notably, CO 2 with higher adsorption affinity, low k app , and enhanced penetration capacity in complex nanopores, emerges as a practical candidate for carbon storage and enhanced oil/gas recovery.

show abstract

The controlling factors and prediction model of pore structure in global shale sediments based on random forest machine learning

Cited by 14 publications

References 191 publications

Performance Prediction and Heating Parameter Optimization of Organic-Rich Shale In Situ Conversion Based on Numerical Simulation and Artificial Intelligence Algorithms

Performance Prediction and Heating Parameter Optimization of Organic-Rich Shale In Situ Conversion Based on Numerical Simulation and Artificial Intelligence Algorithms

Performance analysis and modelling of circular jets aeration in an open channel using soft computing techniques

Laboratory Observation of Fluid Flow in Depleted Shale Gas Reservoir: Coupling Effect of Sorbing and Non-sorbing Gas on Stress, Slippage, Flow Regime in Anisotropic and Fractured Shales

Contact Info

Product

Resources

About