Application of modified GMDH network for CO
            <sub>2</sub>
            -oil minimum miscibility pressure prediction

Huang, Wei; Du, Yong; Ren, Hongmei; Guo, Jia; Wang, Ruisi; Wang, Zhe; Zhao, Liangyan; Hao, Ziyan

doi:10.1080/15567036.2019.1604908

Cited by 6 publications

(3 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The established SVR-ABC model achieved promising statistical metrics, where the overall AARD and R 2 values were 3.24% and 0.9868, respectively. Huang et al illustrated the development of a modified GMDH paradigm for modeling MMP of pure and impure CO 2 – oil systems. The authors employed 52 and 40 data points for developing the explicit correlations for these two systems, respectively.…”

Section: Progress On Modeling the Mmp Of The Co2 – Oil Systems Using ...mentioning

confidence: 99%

Utilizing Artificial Intelligence Techniques for Modeling Minimum Miscibility Pressure in Carbon Capture and Utilization Processes: A Comprehensive Review and Applications

Amar,

Djema,

Ourabah

et al. 2024

Energy Fuels

View full text Add to dashboard Cite

The carbon dioxide (CO 2 ) based enhanced oil recovery methods (EORs) are considered among the promising techniques for increasing the recovery factor from mature oil reservoirs and reducing the amount of CO 2 emission in the atmosphere. Determining the minimum miscibility pressure (MMP) of CO 2 − oil systems is a crucial step for successfully implementing CO 2 − EOR processes. Therefore, various approaches have been proposed for determining this key parameter. However, the laboratory tests are expensive and timeconsuming, while most available correlations present moderate accuracy. To address these shortcomings, various studies have applied artificial intelligence (AI) techniques to model the MMP of the CO 2 − oil systems. In this study, we reviewed the published works for predicting the MMP of the CO 2 − oil systems using AI-based models. Our analyses revealed the robustness of these techniques in modeling MMP. In this context, it was noticed that more than 70 AI-based paradigms have been utilized for estimating the MMP of CO 2 − oil systems. Among the applications, the hybrid schemes combining machine learning and nature-inspired algorithms (ML-NIA) take the top spot, accounting for 27% of applications. Additionally, the investigation demonstrated that the artificial neural network (ANN) is the most utilized ML method in the modeling phase, while the genetic algorithm (GA) is the most widely applied NIA for improving ML performance. In the second part of this study, we suggest an updated correlation based on gene expression programming (GEP) for the accurate prediction of MMP of CO 2 − oil systems. Our proposed explicit correlation yielded excellent predictive performance, achieving overall root-mean-square error and determination coefficient (R 2 ) values of 0.9253 and 09713, respectively. These promising statistical metrics enabled the newly updated GEP-based correlation to outperform the preexisting models. Besides, the physical validity and interpretability of the proposed correlation were proven using the trend analysis and the Shape Dependence Analysis plot, respectively. Lastly, the findings of this study provide a dual benefit, the review and the illustration of the published studies on applying AI techniques for modeling the MMP of the CO 2 − oil systems; and second, the newly implemented GEP-based correlation can significantly enhance the effective prediction of the MMP in CO 2 -oil systems, thus, facilitating the simulation of various CO 2 − based EOR processes.

show abstract

Section: Progress On Modeling the Mmp Of The Co2 – Oil Systems Using ...mentioning

confidence: 99%

Utilizing Artificial Intelligence Techniques for Modeling Minimum Miscibility Pressure in Carbon Capture and Utilization Processes: A Comprehensive Review and Applications

Amar,

Djema,

Ourabah

et al. 2024

Energy Fuels

View full text Add to dashboard Cite

show abstract

“…In the inner levels of the GMDH method 90 , there are multiple independent neurons. All neurons per layer are attached in couples via a quadratic polynomial and form individual neurons in the structure of polynomials in the subsequent layer 91 . Each GMDH neuron's generated value is determined by employing a quadratic polynomial representative that comprises the preceding neuron 92 , 93 .…”

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

“…Group Method of Data Handling (GMDH) [39] is a prominent and widely recognized ML technique [40][41][42][43]. The GMDH offers several advantages compared to the other ML techniques, including automatic feature selection [43], employing a self-organizing algorithm for optimizing the structure and complexity of the model [44], interpretability by providing simple and practical models [45], non-linearity handling [46], and adaptability [47]. These advantages make GMDH a valuable tool in various domains, particularly when dealing with complex datasets.…”

Section: Introductionmentioning

confidence: 99%

Modeling Hydrodynamic Behavior of the Ottawa River: Harnessing the Power of Numerical Simulation and Machine Learning for Enhanced Predictability

Cardi,

Dussel,

Letessier

et al. 2023

Hydrology

View full text Add to dashboard Cite

The Ottawa River Watershed is a vast area that stretches across Ontario and Quebec and holds great importance for Canada’s people, economy, and collective history, both in the present and the future. The river has faced numerous floods in recent years due to climate change. The most significant flood occurred in 2019, surpassing a 100-year flood event, and serves as a stark reminder of how climate change impacts our environment. Considering the limitations of machine learning (ML) models, which heavily rely on historical data used during training, they may struggle to accurately predict such “non-experienced” or “unseen” floods that were not encountered during the training process. To tackle this challenge, our study has utilized a combination of numerical modeling and ML to create an integrated methodology. Indeed, a comprehensive dataset of river flow discharge was generated using a numerical model, encompassing a wide range of potential future floods. This significantly improved the ML training process to generalize the accuracy of results. Utilizing this dataset, a novel ML model called the Expanded Framework of Group Method of Data Handling (EFGMDH) has been developed. Its purpose is to provide decision-makers with explicit equations for estimating three crucial hydrodynamic characteristics of the Ottawa River: floodplain width, flow velocity, and river flow depth. These predictions rely on various inputs, including the location of the desired cross-section, river slope, Manning roughness coefficient at different river sections (right, left, and middle), and river flow discharge. To establish practical models for each of the aforementioned hydrodynamic characteristics of the Ottawa River, different input combinations were tested to identify the most optimal ones. The EFGMDH model demonstrated high accuracy throughout the training and testing stages, achieving an R2 value exceeding 0.99. The proposed model’s exceptional performance demonstrates its reliability and practical applications for the study area.

show abstract

Application of modified GMDH network for CO ₂ -oil minimum miscibility pressure prediction

Cited by 6 publications

References 29 publications

Utilizing Artificial Intelligence Techniques for Modeling Minimum Miscibility Pressure in Carbon Capture and Utilization Processes: A Comprehensive Review and Applications

Utilizing Artificial Intelligence Techniques for Modeling Minimum Miscibility Pressure in Carbon Capture and Utilization Processes: A Comprehensive Review and Applications

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

Modeling Hydrodynamic Behavior of the Ottawa River: Harnessing the Power of Numerical Simulation and Machine Learning for Enhanced Predictability

Contact Info

Product

Resources

About

Application of modified GMDH network for CO 2 -oil minimum miscibility pressure prediction

Cited by 6 publications

References 29 publications

Utilizing Artificial Intelligence Techniques for Modeling Minimum Miscibility Pressure in Carbon Capture and Utilization Processes: A Comprehensive Review and Applications

Utilizing Artificial Intelligence Techniques for Modeling Minimum Miscibility Pressure in Carbon Capture and Utilization Processes: A Comprehensive Review and Applications

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

Modeling Hydrodynamic Behavior of the Ottawa River: Harnessing the Power of Numerical Simulation and Machine Learning for Enhanced Predictability

Contact Info

Product

Resources

About

Application of modified GMDH network for CO ₂ -oil minimum miscibility pressure prediction