Layer | Fill | Outline |
---|
Map layers
Theme | Visible | Selectable | Appearance | Zoom Range (now: 0) |
---|
Fill | Stroke |
---|---|
Collaborating Authors
Predicting Trapping Indices in CO2 Sequestration: A Data-Driven Machine Learning Approach for Coupled Chemo-Hydro-Mechanical Models in Deep Saline Aquifers
Tariq, Zeeshan (King Abdullah University of Science and Technology) | Yan, Bicheng (King Abdullah University of Science and Technology) | Sun, Shuyu (King Abdullah University of Science and Technology)
ABSTRACT Storing carbon dioxide (CO2) in deep geological formations, such as saline aquifers and depleted oil and gas reservoirs, through Geological Carbon Sequestration (GCS) offers tremendous potential for large-scale CO2 storage. To gain a better understanding of how CO2 is trapped in saline aquifers, it is important to create robust and speedy tools for assessing CO2 trapping efficiency. Therefore, this study focuses on using machine learning techniques to predict the efficiency of CO2 trapping in deep saline formations as part of GCS. The methodology involves simulating the CO2 trapping mechanisms using a physics-based numerical reservoir simulator and creating a dataset based on uncertainty variables. The study used a numerical reservoir simulator to simulate CO2 trapping mechanisms over 170 years, with uncertainty variables like petrophysical properties, reservoir physical parameters, and operational decision parameters being utilized to create a large dataset for training, testing, and validation. 722 reservoir simulations were performed and the results of residual trapping, mineral trapping, solubility trapping, and cumulative CO2 injection were analyzed. A deep neural network was applied to predict the CO2 trapping efficiency. The results showed that the deep neural network model can predict the trapping indices with a coefficient of determination above 0.95 and average absolute percentage error below 5%. INTRODUCTION Carbon capture and storage (CCS) is a technology that captures carbon dioxide (CO2) emissions from power plants and industrial sources, transports it to a storage site, and injects it deep underground into geologic formations, such as saline aquifers. The aim of CCS is to reduce greenhouse gas emissions and mitigate climate change (A. Z. Al-Yaseri et al., 2016; Arif et al., 2016; Gholami & Raza, 2022; Harp et al., 2021; Johnson et al., 2004; Rutqvist, 2012; Tariq et al., 2022; Wen et al., 2021, 2022; Yan, Harp, Chen, & Pawar, 2022; Yan, Harp, Chen, Hoteit, et al., 2022). The need for underground storage of carbon dioxide is crucial in our current era as it helps reduce the emission of greenhouse gases into the atmosphere. The focus on reducing the effects of these emissions and transitioning to net zero carbon energy sources has been a global concern for many years. As the world's population continues to grow, energy demand will increase and the world will not soon reach its peak in energy consumption. This has led to discussions among the energy industry to address the impact of climate action on business sustainability, as greenhouse gases are a major contributor to global warming and climate change.
- North America > United States (0.46)
- Asia (0.29)
- Geology > Geological Subdiscipline > Geomechanics (1.00)
- Geology > Petroleum Play Type (0.69)
- Geology > Rock Type > Sedimentary Rock > Clastic Rock (0.47)
Data-Driven Machine Learning Modeling of Mineral/CO2/Brine Wettability Prediction: Implications for CO2 Geo-Storage
Tariq, Zeeshan (King Abdullah University of Science and Technology) | Ali, Muhammad (King Abdullah University of Science and Technology) | Yan, Bicheng (King Abdullah University of Science and Technology) | Sun, Shuyu (King Abdullah University of Science and Technology) | Khan, Mohammad (Slb) | Yekeen, Nurudeen (Universiti Teknologi PETRONAS) | Hoteit, Hussein (King Abdullah University of Science and Technology)
Abstract CO2 wettability and the reservoir rock-fluid interfacial interactions are crucial parameters for successful CO2 geological sequestration. This study implemented the feed-forward neural network to model the wettability behavior in a ternary system of rock minerals (quartz and mica), CO2, and brine under different operating conditions. To gain higher accuracy of the machine learning models, a sufficient dataset was utilized that was recorded by conducting a large number of laboratory experiments under a realistic pressure range, 0 โ 25 MPa and the temperatures range, 298 โ 343 K. The mica substrates were used as a proxy for the caprock, and quartz substrates were used a proxy for the reservoir rock. Different graphical exploratory data analysis techniques, such as heatmaps, violin plots, and pairplots were used to analyze the experimental dataset. To improve the generalization capabilities of the machine learning models k-fold cross-validation method, and grid search optimization approaches were implemented. The machine learning models were trained to predict the receding and advancing contact angles of mineral/CO2/brine systems. Both statistical evaluation and graphical analyses were performed to show the reliability and performance of the developed models. The results showed that the implemented ML model accurately predicted the wettability behavior under various operating conditions. The training and testing average absolute percent relative errors (AAPE) and R of the FFNN model for mica and quartz were 0.981 and 0.972, respectively. The results confirm the accuracy performance of the ML algorithms. Finally, the investigation of feature importance indicated that pressure had the utmost influence on the contact angles of the minerals/CO2/brine system. The geological conditions profoundly affect rock minerals wetting characteristics, thus CO2 geo-storage capacities. The literature severely lacks advanced information and new methods for characterizing the wettability of mineral/CO2/brine systems at geo-storage conditions. Thus, the ML model's outcomes can be beneficial for precisely predicting the CO2 geo-storage capacities and containment security for the feasibility of large-scale geo-sequestration projects.
- North America > United States (0.68)
- Asia > Middle East (0.46)
- Europe > Denmark > North Sea (0.28)
- Geology > Geological Subdiscipline > Geomechanics (0.69)
- Geology > Mineral > Silicate > Tectosilicate > Quartz (0.66)
- Geology > Rock Type > Sedimentary Rock > Clastic Rock (0.46)
- North America > Canada > Nova Scotia > North Atlantic Ocean > Scotian Basin > Sable Basin > Sable Project > Venture Field (0.99)
- Europe > Denmark > North Sea > Danish Sector > Central Graben > Block 5604/29 > South Arne Field (0.99)
Optimization of Carbon-Geo Storage into Saline Aquifers: A Coupled Hydro-Mechanics-Chemo Process
Tariq, Zeeshan (King Abdullah University of Science and Technology) | Gudala, Manojkumar (King Abdullah University of Science and Technology) | Yan, Bicheng (King Abdullah University of Science and Technology) | Sun, Shuyu (King Abdullah University of Science and Technology) | Rui, Zhenghua (China University of Petroleum, Beijing)
Abstract The potential for large-scale storage of carbon dioxide (CO2) through Geological Carbon Sequestration (GCS) in deep geological formations such as saline aquifers and depleted oil and gas reservoirs is significant. Effectively implementing GCS requires evaluating the risk of plume confinement and storage capacity at each site through a thorough assessment. To assess the stability of the caprock after CO2 injection, efficient tools are needed to evaluate the safe duration of CO2 injection. This study used Particle Swarm Optimization (PSO) evolutionary algorithm to optimize the maximum CO2 storage capacity in saline aquifers without risking the integrity of the caprock. A deep learning (DL) model, fully connected neural networks, was trained to predict the safe injection duration. The movement of CO2 was simulated for 170 years following a 30-year injection period into a deep saline aquifer using a physics-based numerical reservoir simulator. The simulation took into consideration uncertainty variables such as petrophysical properties and reservoir physical parameters, as well as operational decisions like injection rate and perforation depth. Sampling the reservoir model with the Latin-Hypercube approach accounted for a range of parameters. Over 720 reservoir simulations were performed to generate training, testing, and validation datasets, and the best DNN model was selected after multiple executions. The three-layer FCNN model with 30 neurons in each layer showed excellent prediction efficiency with a coefficient of determination factor over 0.98 and an average absolute Percentage Error (AAPE) less than 1%. The trained models showed a good match between simulated and predicted results and were 300 times more computationally efficient. PSO was utilized to optimize the operational parameters in the DL models to achieve maximum CO2 storage with minimum damage to the caprock. The results suggest that the DNN-based model can serve as a reliable alternative to numerical simulation for estimating CO2 performance in the subsurface and monitoring storage potential in GCS projects.
- North America > United States (0.68)
- Europe (0.68)
- Asia (0.46)
- Geology > Geological Subdiscipline > Geomechanics (1.00)
- Geology > Petroleum Play Type (0.78)
- Geology > Rock Type (0.68)
Machine Learning Modeling of Saudi Arabian basalt/CO2/brine Wettability Prediction: Implications for CO2 Geo-Storage
Tariq, Zeeshan (King Abdullah University of Science and Technology) | Ali, Muhammad (King Abdullah University of Science and Technology) | Yan, Bicheng (King Abdullah University of Science and Technology) | Sun, Shuyu (King Abdullah University of Science and Technology) | Hoteit, Hussein (King Abdullah University of Science and Technology)
ABSTRACT CO2 wettability and the reservoir rock-fluid interfacial interactions are crucial parameters that regulates the successful CO2 geological sequestration. This study implemented the feed-forward neural network to model the wettability behavior of Saudi Arabian (SA) basaltic rocks in a ternary system of basaltic rocks, CO2, and brine under different operating conditions. To gain higher accuracy of the machine learning models, a sufficient dataset was utilized that was recorded by conducting a large number of laboratory experiments under a realistic pressure range, 0 โ 25 MPa and the temperatures range, 298 โ 343 K. Different graphical exploratory data analysis techniques, such as heatmaps, violin plots, and pair plots were used to analyze the experimental dataset. The machine learning models were trained to predict the receding and advancing contact angles of SA basalt/CO2/brine systems. Both statistical evaluation and graphical analyses were performed to show the reliability and performance of the developed models. The results showed that the implemented ML model accurately predicted the wettability behavior under various operating conditions. INTRODUCTION Geological formations offer a promising solution to reduce global warming and achieve a low-CO2 economy by injecting carbon dioxide (CO2) into them (Alam et al., 2014; Bethke, 2007; Egermann et al., 2005, 2005; Iglauer et al., 2015; Wang et al., 1998). Saudi Arabia, a significant hydrocarbon-producing country, possesses numerous existing infrastructures and transportation pipelines suitable for natural gas storage, which could be utilized for large-scale CO2 storage in depleted hydrocarbon reservoirs, saline aquifers, and salt caverns. Moreover, sedimentary formations like shales, tight sandstone or carbonates, and igneous rocks such as basalts have recently emerged as potential formations to investigate for CO2 storage (Yan et al., 2022c). Dark-colored, fine-grained igneous rocks called basalts consist mainly of pyroxene, plagioclase, and olivine. They are more abundant and accessible than shales, and the Cenozoic volcanic rocks in Saudi Arabia are one of the largest areas of alkali olivine basalt worldwide, covering nearly 90,000 km. Carbon mineralization is the primary method of CO2 storage in reactive rocks like basalt, and research has shown that basalt can be suitable for CO2 storage through this method, or residual trapping if the basalt formation is capped. Basalt is distributed worldwide with a favorable mineral composition, significant thickness, and good vesicular texture. In contrast to silica minerals in sedimentary formations, CO2 injection into volcanic rocks like basalt can swiftly initiate carbon mineralization and mineral trapping, as evidenced by successful pilot project trials conducted in Washington State (USA) and Iceland, which showed that most of the injected CO2 was mineralized in less than two years.
- North America > United States (1.00)
- Europe (1.00)
- Asia > Middle East > Saudi Arabia (0.55)
- Geology > Rock Type > Igneous Rock > Basalt (1.00)
- Geology > Rock Type > Sedimentary Rock > Clastic Rock > Mudrock > Shale (0.54)
- Geology > Mineral > Silicate > Nesosilicate > Olivine (0.44)
- North America > Canada > Nova Scotia > North Atlantic Ocean > Scotian Basin > Sable Basin > Sable Project > Venture Field (0.99)
- Europe > Denmark > North Sea > Danish Sector > Central Graben > Block 5604/29 > South Arne Field (0.99)
An Intelligent Safe Well Bottom-Hole Pressure Monitoring of CO2 Injection Well into Deep Saline: A coupled Hydro-Mechanical Approach
Tariq, Zeeshan (King Abdullah University of Science and Technology) | Yan, Bicheng (King Abdullah University of Science and Technology) | Sun, Shuyu (King Abdullah University of Science and Technology)
Abstract Geological Carbon Sequestration (GCS) in deep geological formations, like saline aquifers and depleted oil and gas reservoirs, brings enormous potential for large-scale storage of carbon dioxide (CO2). The successful implementation of GCS requires a comprehensive risk assessment of the confinement of plumes and storage potential at each storage site. To better understand the integrity of the caprock after injecting CO2, it is necessary to develop robust and fast tools to evaluate the safe CO2 injection duration. This study applied deep learning (DL) techniques, such as fully connected neural networks, to predict the safe injection duration. A physics-based numerical reservoir simulator was used to simulate the movement of CO2 for 170 years following a 30-year CO2 injection period into a deep saline aquifer. The uncertainty variables were utilized, including petrophysical properties such as porosity and permeability, reservoir physical parameters such as temperature, salinity, thickness, and operational decision parameters such as injection rate and perforation depth. As mentioned earlier, the reservoir model was sampled using the Latin-Hypercube sampling approach to account for a wide range of parameters. Seven hundred twenty-two reservoir simulations were performed to create training, testing, and validation datasets. The DNN model was trained, and several executions were performed to arrive at the best model. After multiple realizations and function evaluations, the predicted results revealed that the three-layer FCNN model with thirty neurons in each layer could predict the safe injection duration of CO2 into deep saline formations. The DNN model showed an excellent prediction efficiency with the highest coefficient of determination factor of above 0.98 and AAPE of less than 1%. Also, the trained predictive models showed excellent agreement between the simulated ground truth and predicted trapping index, yet 300 times more computationally efficient than the latter. These findings indicate that the DNN-based model can support the numerical simulation as an alternative to a robust predictive tool for estimating the performance of CO2 in the subsurface and help monitor the storage potential at each part of the GCS project.
- Asia > Middle East (0.94)
- North America > United States (0.68)
- Europe > Denmark > North Sea (0.28)
- Geology > Geological Subdiscipline > Geomechanics (1.00)
- Geology > Petroleum Play Type (0.88)
- Geology > Rock Type (0.68)
- Geology > Geological Subdiscipline > Economic Geology > Petroleum Geology (0.46)
- Europe > Denmark > North Sea > Danish Sector > Central Graben > Block 5604/29 > South Arne Field (0.99)
- Asia > India > Andhra Pradesh > Bay of Bengal > Krishna-Godavari Basin > Ravva Block > Ravva Field (0.99)