Predicting the wettability rocks/minerals-brine-hydrogen system for hydrogen storage: Re-evaluation approach by multi-machine learning scheme

Thanh, Hung Vo; Rahimi, Mohammad; Dai, Zhenxue; Zhang, Hemeng; Zhang, Tao

doi:10.1016/j.fuel.2023.128183

Cited by 21 publications

(4 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Extreme Gradient Boosting (XGBoost), developed by Chen and Guestrin, is an ensemble learning algorithm that combines multiple decision trees or regression trees. This technique has found widespread applications in fields including energy, environment, and engineering design, showing promising results. − During the XGBoost-based regression process, the residuals between the actual and predicted data are calculated by using the existing model. The residuals are then utilized as the target for training a new decision tree model.…”

Section: Methods For Calculating Feature Parameters and Machine Learningmentioning

confidence: 99%

Flow Patterns and Pore Structure Effects on Residual Oil during Water and CO₂ Flooding: In Situ CT Scanning

Zhang,

Lin,

Ren

2023

Energy Fuels

View full text Add to dashboard Cite

Carbon dioxide (CO 2 ) enhanced oil recovery (EOR) is an important technology to achieve carbon neutrality by sequestering CO 2 underground while simultaneously recovering crude oil. Reservoir pore structure is a key factor influencing CO 2 EOR. In this study, we utilized advanced online in situ CT scanning and digital rock techniques to obtain, for the first time, evolution profiles of the finger area during water flooding and CO 2 flooding processes, quantitatively assessing the differences in fluid patterns. Additionally, we first introduced an innovative approach using advanced machine learning techniques, especially XGBoost and SHAP, to construct a predictive model of the relative change of oil phase occupancy (RCPOC) based on pore structure parameters and evaluated the importance of each pore structure parameter. Importantly, our results revealed that CO 2 can significantly increase the sweep efficiency area while substantially reducing residual oil saturation, in stark contrast to the relatively uniform water front observed during water flooding. Furthermore, we elucidated the critical role of capillary forces, demonstrating that water flooding primarily extracts trapped oil from small pores, while CO 2 flooding effectively extracts oil from larger pores. During CO 2 flooding, there is a positive correlation between coordination number, mean throat radius (MeanTR), and mean throat length (MeanTL) and the change in oil occupancy, whereas their influence during water flooding is limited. In summary, this study contributes to the understanding of flow patterns and pore structure effects on residual oil during water flooding and the CO 2 flooding processes. It also provides a novel approach based on pore structure parameters to predict RCPOC and assess the importance of influencing factors, thereby expanding our research perspective on this issue.

show abstract

Section: Methods For Calculating Feature Parameters and Machine Learningmentioning

confidence: 99%

Flow Patterns and Pore Structure Effects on Residual Oil during Water and CO₂ Flooding: In Situ CT Scanning

Zhang,

Lin,

Ren

2023

Energy Fuels

View full text Add to dashboard Cite

show abstract

“…Several reservoir parameters were selected as the input variables to determine whether there exist potential microbial reactions. Thanh et al 35 applied different machine learning algorithms to predict the H 2 wettability in underground H 2 storage sites. The XGBoost and random forest algorithms showed high prediction performance with R 2 > 0.95.…”

Section: Introductionmentioning

confidence: 99%

“…The XGBoost and random forest algorithms showed high prediction performance with R 2 > 0.95. However, the studies of Katterbauer et al and Thanh et al did not focus on H 2 storage capacity and efficiency. In contrast, extensive analyses − have investigated the uncertainty quantification and performance optimization of CO 2 sequestration using ROMs.…”

Section: Introductionmentioning

confidence: 99%

Integrating Capacity and Efficiency for Optimal Hydrogen Storage Site Selection in Saline Aquifers

Chen,

Mao

et al. 2024

Energy Fuels

View full text Add to dashboard Cite

Hydrogen (H 2 ) energy is a promising transition pathway from conventional fossil fuels to sustainable clean energy. However, H 2 requires a large storage capacity because of its low volumetric energy−density nature. Underground H 2 storage sites provide ample space for H 2 storage. In this work, we proposed a general workflow to select saline aquifers' optimal H 2 storage sites, considering the capacity and operational efficiency. We developed a comprehensive data set of high-fidelity numerical simulations to quantify the effects of geologic and operating parameters on H 2 storage performance. The simulation results are used to train a robust reduced-order model (ROM) to estimate H 2 storage performance. Due to its high accuracy and flexibility, we selected the multilayer perceptron to develop our ROM. The mean squared errors of all ROMs are less than 0.0001, and the coefficients of determination (R 2 ) were higher than 0.99. Integrating the performance estimations from the ROMs with volumetric calculations of H 2 storage capacity, we quantitatively evaluated the H 2 storage in saline aquifers using a designed objective function. We applied our workflow in the Intermountain-West (I-WEST) region, which is the central mountain area in the United States, including Arizona, Colorado, New Mexico, Montana, Utah, and Wyoming. We identified the top three promising saline aquifers for H 2 storage from 12 potential storage sites. Our workflow and ROMs are agnostic to the region and could be applied to other areas. Generally, this work supports safe and efficient H 2 storage operations in saline aquifers in the I-WEST region.

show abstract

“…The wettability of quartz surfaces is impacted by numerous factors, e.g., mineral surface properties and in situ conditions. , Additionally, the quartz surface may go through various chemical reactions in the subsurface, e.g., hydroxylation and dehydroxylation, altering the wetting behaviors. It is commonly accepted that the hydrophilicity of the quartz surface is enhanced by the increased area density of hydroxyl groups on the surface. , Apart from the nature of the quartz surface, the in situ conditions, e.g., pressure, salinity, and mixture with cushion gases, also significantly impact the wetting properties.…”

Section: Introductionmentioning

confidence: 99%

Molecular Insights into the Impact of Surface Chemistry and Pressure on Quartz Wettability: Resolving Discrepancies for Hydrogen Geo-storage

Zheng,

Germann,

Gross

et al. 2024

ACS Sustainable Chem. Eng.

View full text Add to dashboard Cite

Subsurface formations are promising for large-scale H 2 storage, balancing the energy demand and supply. Wettability is vital in ensuring storage safety, efficiency, and capacity, whereas noticeable discrepancies exist in the literature. This work reconciles these discrepancies by revealing the mechanisms of quartz wettability alteration with surface chemistry and pressure using classical molecular dynamics simulation. We find that the fully rigid quartz substrate results in much lower hydrophilicity than the fully flexible and the hydroxyl group flexible quartz substrates due to the lower probability of hydrogen bond formation between water and hydroxyl groups. Also, quartz wettability relies on not only the area density but also the arrangement of the surface hydroxyl groups. Monolayer water adsorption on both hydrophilic and hydrophobic quartz surfaces is observed, whereas the structure of the adsorbed water film is different. Dissolved H 2 prefers to move to the quartz surface rather than staying in bulk water. The water contact angle on the fully hydroxylated quartz fluctuates between 30.7 and 37.1°with pressure ranging from 1− 30 MPa, without a monotonic trend. We reveal that the dominant mechanism of wettability alteration within this pressure range is due to the pinning effect induced by the microstructures on the quartz surface.

show abstract

Predicting the wettability rocks/minerals-brine-hydrogen system for hydrogen storage: Re-evaluation approach by multi-machine learning scheme

Cited by 21 publications

References 45 publications

Flow Patterns and Pore Structure Effects on Residual Oil during Water and CO₂ Flooding: In Situ CT Scanning

Flow Patterns and Pore Structure Effects on Residual Oil during Water and CO₂ Flooding: In Situ CT Scanning

Integrating Capacity and Efficiency for Optimal Hydrogen Storage Site Selection in Saline Aquifers

Molecular Insights into the Impact of Surface Chemistry and Pressure on Quartz Wettability: Resolving Discrepancies for Hydrogen Geo-storage

Contact Info

Product

Resources

About

Predicting the wettability rocks/minerals-brine-hydrogen system for hydrogen storage: Re-evaluation approach by multi-machine learning scheme

Cited by 21 publications

References 45 publications

Flow Patterns and Pore Structure Effects on Residual Oil during Water and CO2 Flooding: In Situ CT Scanning

Flow Patterns and Pore Structure Effects on Residual Oil during Water and CO2 Flooding: In Situ CT Scanning

Integrating Capacity and Efficiency for Optimal Hydrogen Storage Site Selection in Saline Aquifers

Molecular Insights into the Impact of Surface Chemistry and Pressure on Quartz Wettability: Resolving Discrepancies for Hydrogen Geo-storage

Contact Info

Product

Resources

About

Flow Patterns and Pore Structure Effects on Residual Oil during Water and CO₂ Flooding: In Situ CT Scanning

Flow Patterns and Pore Structure Effects on Residual Oil during Water and CO₂ Flooding: In Situ CT Scanning