Intelligent Image Segmentation for Organic-Rich Shales Using Random Forest, Wavelet Transform, and Hessian Matrix

Wu, Yaokun; Misra, Siddharth

doi:10.1109/lgrs.2019.2943849

Cited by 30 publications

(7 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The micro-CT images are segmented into four distinct components, namely, water, oil, rock, and gas (Figures and ). More information about the segmentation procedure suited for porous materials is published by Wu and Misra and Misra et al We apply the newly formulated statistical methods on the segmented images to measure the change in connectivity of the wetting and nonwetting phases in the carbonate sample undergoing WAG injection. In this study, the geological material is a water-wet rock; therefore, the wetting and nonwetting phases are water and oil, respectively.…”

Section: Methodsmentioning

confidence: 99%

Spatiotemporal Variations in the Connectivity of Wetting and Nonwetting Phases during Water Alternating Gas Injection

Ganguly

Misra

2021

Energy Fuels

Self Cite

View full text Add to dashboard Cite

Water alternating gas (WAG) injection is a well-established technique that leverages the benefits of gas injection and waterflooding processes to improve the ultimate oil recovery. The connectivity of the fluid phases in a porous media is a crucial factor governing the mobility, displacement, and recovery of the multiple fluid phases during primary, secondary, or enhanced recovery operation. We develop, apply, and evaluate several statistical and computational functions capable of quantifying connectivity of a fluid phase of interest captured in the segmented microcomputed tomography scans of fluid-filled porous material undergoing WAG injection. These functions capture the evolution of three-dimensional connectivity of the wetting and nonwetting phases along the length of the sample during each injection process. The changes in connectivity of the fluid phases compared with the changes in fluid saturations better describe the effects of WAG injection and the recovery at each stage. This is a first-of-its-kind quantification of connectivity of wetting and nonwetting phases, focused on WAG injection. A robust quantification of the fluid phase connectivity in a porous material undergoing WAG injection facilitates a better understanding of the efficiency of the sequential injection strategies and reveals new approaches for improving oil recovery. The direct computation and comparison of the connectivity help determine the level of contribution of each injection cycle to the final recovery of the oil phase, thereby facilitating optimization of future injection strategies.

show abstract

Section: Methodsmentioning

confidence: 99%

Spatiotemporal Variations in the Connectivity of Wetting and Nonwetting Phases during Water Alternating Gas Injection

Ganguly

Misra

2021

Energy Fuels

Self Cite

View full text Add to dashboard Cite

show abstract

“…Such ensemble learning algorithm in which each tree is trained in parallel forms a Decision Tree ensemble, which is referred to as Random Forests. The greedy strategy in RF determines the importance of each tree at each stage 53 . Moreover, RF can measure the feature’s importance and retain the most informative input features 54 .…”

Section: Models’ Implementationmentioning

confidence: 99%

Modeling solubility of CO2–N2 gas mixtures in aqueous electrolyte systems using artificial intelligence techniques and equations of state

Nakhaei-Kohani

Taslimi-Renani

Hadavimoghaddam

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Determining the solubility of non-hydrocarbon gases such as carbon dioxide (CO2) and nitrogen (N2) in water and brine is one of the most controversial challenges in the oil and chemical industries. Although many researches have been conducted on solubility of gases in brine and water, very few researches investigated the solubility of power plant flue gases (CO2–N2 mixtures) in aqueous solutions. In this study, using six intelligent models, including Random Forest, Decision Tree (DT), Gradient Boosting-Decision Tree (GB-DT), Adaptive Boosting-Decision Tree (AdaBoost-DT), Adaptive Boosting-Support Vector Regression (AdaBoost-SVR), and Gradient Boosting-Support Vector Regression (GB-SVR), the solubility of CO2–N2 mixtures in water and brine solutions was predicted, and the results were compared with four equations of state (EOSs), including Peng–Robinson (PR), Soave–Redlich–Kwong (SRK), Valderrama–Patel–Teja (VPT), and Perturbed-Chain Statistical Associating Fluid Theory (PC-SAFT). The results indicate that the Random Forest model with an average absolute percent relative error (AAPRE) value of 2.8% has the best predictions. The GB-SVR and DT models also have good precision with AAPRE values of 6.43% and 7.41%, respectively. For solubility of CO2 present in gaseous mixtures in aqueous systems, the PC-SAFT model, and for solubility of N2, the VPT EOS had the best results among the EOSs. Also, the sensitivity analysis of input parameters showed that increasing the mole percent of CO2 in gaseous phase, temperature, pressure, and decreasing the ionic strength increase the solubility of CO2–N2 mixture in water and brine solutions. Another significant issue is that increasing the salinity of brine also has a subtractive effect on the solubility of CO2–N2 mixture. Finally, the Leverage method proved that the actual data are of excellent quality and the Random Forest approach is quite reliable for determining the solubility of the CO2–N2 gas mixtures in aqueous systems.

show abstract

“…A random forest is made up of a set of different decision trees that are all being learned at the same time. The system determines the superiority and significance of each decision tree 78 . Furthermore, a constructed attribute of the Classification model that is used to choose different attributes allows the RF to govern various inputs characteristics without the requirement to remove a set of variables for dimension decrement 79 .…”

Section: Model Developmentmentioning

confidence: 99%

Modeling the solubility of light hydrocarbon gases and their mixture in brine with machine learning and equations of state

Mohammadi

Hadavimoghaddam

Atashrouz

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Knowledge of the solubilities of hydrocarbon components of natural gas in pure water and aqueous electrolyte solutions is important in terms of engineering designs and environmental aspects. In the current work, six machine-learning algorithms, namely Random Forest, Extra Tree, adaptive boosting support vector regression (AdaBoost-SVR), Decision Tree, group method of data handling (GMDH), and genetic programming (GP) were proposed for estimating the solubility of pure and mixture of methane, ethane, propane, and n-butane gases in pure water and aqueous electrolyte systems. To this end, a huge database of hydrocarbon gases solubility (1836 experimental data points) was prepared over extensive ranges of operating temperature (273–637 K) and pressure (0.051–113.27 MPa). Two different approaches including eight and five inputs were adopted for modeling. Moreover, three famous equations of state (EOSs), namely Peng-Robinson (PR), Valderrama modification of the Patel–Teja (VPT), and Soave–Redlich–Kwong (SRK) were used in comparison with machine-learning models. The AdaBoost-SVR models developed with eight and five inputs outperform the other models proposed in this study, EOSs, and available intelligence models in predicting the solubility of mixtures or/and pure hydrocarbon gases in pure water and aqueous electrolyte systems up to high-pressure and high-temperature conditions having average absolute relative error values of 10.65% and 12.02%, respectively, along with determination coefficient of 0.9999. Among the EOSs, VPT, SRK, and PR were ranked in terms of good predictions, respectively. Also, the two mathematical correlations developed with GP and GMDH had satisfactory results and can provide accurate and quick estimates. According to sensitivity analysis, the temperature and pressure had the greatest effect on hydrocarbon gases’ solubility. Additionally, increasing the ionic strength of the solution and the pseudo-critical temperature of the gas mixture decreases the solubilities of hydrocarbon gases in aqueous electrolyte systems. Eventually, the Leverage approach has revealed the validity of the hydrocarbon solubility databank and the high credit of the AdaBoost-SVR models in estimating the solubilities of hydrocarbon gases in aqueous solutions.

show abstract

Intelligent Image Segmentation for Organic-Rich Shales Using Random Forest, Wavelet Transform, and Hessian Matrix

Cited by 30 publications

References 8 publications

Spatiotemporal Variations in the Connectivity of Wetting and Nonwetting Phases during Water Alternating Gas Injection

Spatiotemporal Variations in the Connectivity of Wetting and Nonwetting Phases during Water Alternating Gas Injection

Modeling solubility of CO2–N2 gas mixtures in aqueous electrolyte systems using artificial intelligence techniques and equations of state

Modeling the solubility of light hydrocarbon gases and their mixture in brine with machine learning and equations of state

Contact Info

Product

Resources

About