Unsupervised learning monitors the carbon-dioxide plume in the subsurface carbon storage reservoir

Gonzalez, Keyla; Misra, Siddharth

doi:10.1016/j.eswa.2022.117216

Cited by 13 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Notably, the performance of the cDC-GAN model remained relatively robust even when confronted with increased reservoir heterogeneity using the same number of training samples. Furthermore, Gonzalez and Misra proposed a novel and reliable unsupervised learning approach based on multilevel clustering to visualize underground CO 2 plumes. Their method demonstrated excellent scalability, because unsupervised learning obviates the need for labeled data and can effectively handle large-scale data sets.…”

Section: Application Of Machine Learning In Geological Storagementioning

confidence: 99%

Recent Advances in Geological Storage: Trapping Mechanisms, Storage Sites, Projects, and Application of Machine Learning

Feng

et al. 2023

Energy Fuels

View full text Add to dashboard Cite

A significant amount of carbon dioxide (CO2) is being released into the atmosphere as a result of the acceleration of industrialization and increased energy consumption, which are causing a rise in world temperatures. Despite the fact that nations all over the world have actively participated in CO2 storage projects, there is still not enough to moderate global temperatures. Therefore, there is an urgent need for the development of CO2 sequestration technologies. The main geological storage trapping mechanisms are discussed in this work along with an analysis of the major influencing variables. Additionally, the benefits and drawbacks of significant storage locations and current research hotspots are explored. Storage project development across the globe is outlined. The use of machine learning for CO2 sequestration is reviewed toward the end. This extensive review reveals that the main variables affecting CO2 capture capacity are hydrodynamic and geochemical. The sequestration capability of various storage sites is significantly influenced by the reservoir characteristics and implementation methodologies. The successful implementation of the storage project is determined by local policies and public support. The development of machine learning technologies makes storage projects safer and more dependable.

show abstract

Section: Application Of Machine Learning In Geological Storagementioning

confidence: 99%

Recent Advances in Geological Storage: Trapping Mechanisms, Storage Sites, Projects, and Application of Machine Learning

Feng

et al. 2023

Energy Fuels

View full text Add to dashboard Cite

show abstract

“…Another group of researchers from Texas A&M University developed an unsupervised-learning-based method to analyze sensor-based data from geological storage sites and to rapidly predict the move-ment of CO 2 plumes. This model does not rely on a geological model and may be applied to crosswell seismic tomography data [342].…”

Section: Emerging Co 2 Monitoring Technologiesmentioning

confidence: 99%

A Review of CCUS in the Context of Foams, Regulatory Frameworks and Monitoring

2023

View full text Add to dashboard Cite

Greenhouse gas emission into the atmosphere is considered the main reason for the rise in Earth’s mean surface temperature. According to the Paris Agreement, to prevent the rise of the global average surface temperature beyond two degrees Celsius, global CO2 emissions must be cut substantially. While a transition to a net-zero emission scenario is envisioned by mid-century, carbon capture, utilization, and storage (CCUS) will play a crucial role in mitigating ongoing greenhouse gas emissions. Injection of CO2 into geological formations is a major pathway to enable large-scale storage. Despite significant recent technological advancements, mass deployment of these technologies still faces several technical and non-technical difficulties. This paper provides an overview of technical milestones reached thus far in CO2 capture, utilization, geological storage, monitoring technologies, and non-technical aspects such as regulatory frameworks and related policies in the US and the rest of the world. This paper describes different injection methods to store CO2 in various subsurface formations, the use of foams and the resulting potential gains in CO2 storage capacity, the role of nanoparticles for foam stabilization, and ensuring long-term storage safety. This work also addresses several safety-related aspects of geological storage and subsurface monitoring technologies that may mitigate risks associated with long-term storage.

show abstract

“…Using two clusters yielded an average value of 0.5156, three clusters yielded an average value of 0.5004, and four clusters yielded an average value of 0.5500. Based on the computation of the silhouette index, if the average value is close to the value of one, the data grouping is considered better [10].…”

Section: E Cluster Testmentioning

confidence: 99%

Using the Agglomerative Hierarchical Clustering Method to Examine Human Factors in Indonesian Aviation Accidents

Passarella¹,

Oktariani²,

Kurniawan³

et al. 2022

IJACSA

View full text Add to dashboard Cite

This study aims to provide a comprehensive source of knowledge regarding aviation accidents in Indonesia caused by human factors, which are the most significant among other causative elements, requiring a detailed assessment of the accident as a result of pilot and co-pilot faults while operating the aircraft. The KNKT website database is still in the form of accident reports. To this end, the retrieved information based on historical data for 23 years of accidents caused by humans by analyzing the data using the clustering approach to gain data insight in the relationship between total flying hours and pilot licenses. The data analysis revealed that, in general, the aircraft operator complied with the CASR standards.

show abstract

Unsupervised learning monitors the carbon-dioxide plume in the subsurface carbon storage reservoir

Cited by 13 publications

References 14 publications

Recent Advances in Geological Storage: Trapping Mechanisms, Storage Sites, Projects, and Application of Machine Learning

Recent Advances in Geological Storage: Trapping Mechanisms, Storage Sites, Projects, and Application of Machine Learning

A Review of CCUS in the Context of Foams, Regulatory Frameworks and Monitoring

Using the Agglomerative Hierarchical Clustering Method to Examine Human Factors in Indonesian Aviation Accidents

Contact Info

Product

Resources

About