Intelligent Monitoring

Intelligent monitoring systems (IMS) provide an integrated and project-specific approach to acquisition, analysis, and interpretation of a wide array of monitoring tools and data.


  Network integration plan for the continuous active seismic source monitoring and the intelligent monitoring systems control and data acquisition equipment being deployed by Archer Daniels Midland at the Illinois Industrial Carbon Capture and Storage project site (click to enlarge)

A number of cross-cutting technologies are being developed to better integrate and analyze the wide variety of operational and monitoring data that can be acquired at geologic storage sites. These data integration and analysis technologies include computer-based intelligent monitoring networks and advanced data integration and analysis software tools.

IMS networks are automated, computer-based systems that gather field information from injection and monitoring equipment, evaluate geologic conditions, and recommend appropriate actions. Systematic data collection, analysis, and modeling are key components of these systems. IMS networks are designed to show that site performance meets pre-defined objectives and to ensure that release of CO2 is promptly identified and mitigated.

An IMS network may combine data from CO2 monitoring wells, surface monitoring sensors, subsurface monitoring tools, and injection equipment. The data are compiled in real time in a database that is updated continuously. The intelligent monitoring network may also compare field data to available models, as well as historical field data. Measurements that lie outside normal operational limits or historical trends can be flagged as potential risks.

In addition to IMS networks, researchers are developing advanced software tools to perform specific monitoring, verification, and accounting (MVA) data integration and analysis tasks. These tools include data processing software as well as data integration, visualization software, and user interfaces.

Research Agenda and Challenges

Development and establishment of IMS that combine real-time data collection, site-specific and project-specific data analysis and interpretation, and injection control is a key research area. Such systems need to integrate diverse data from atmospheric, near-surface, and subsurface monitoring networks and convert these data into meaningful and actionable information.

Data processing, analysis, and interpretation workflows must be developed that address the particular needs and objectives of an individual storage project. Information delivery and advanced visualization are important components of this key technology.

NETL’s research pathways for intelligent monitoring include:

  • By 2020: Create advanced, integrated measurement and control systems to track CO2 before, during, and after injection and improve injection efficiency.

  • By 2030: Develop high-resolution, robust, permanently installed monitoring networks. Such networks may use autonomous measurement and control systems that integrate atmospheric, near-surface, and subsurface data into reservoir simulations in real time. Such systems may include advanced sensors, high-capacity data transmission, and advanced visualization.

The figure below shows an approximate timeline for intelligent monitoring technology development.

Storage MVA Research Timeline for Intelligent Monitoring

NETL-Supported Intelligent Monitoring Research

  Visual representation of project workflow by the University of North Dakota. The approach shows the integration of monitoring data into an intelligent monitoring interface, which allows project operators access to periodic and real-time information to facilitate better decision making. (click to enlarge)

NETL supports projects that are addressing research challenges associated with Intelligent Monitoring Systems. Examples of projects supporting this key technology area include: (1) development of new, real-time, data-capable workflows, algorithms, and user interfaces that will automate the integration of monitoring data and simulations as part of an IMS at CO2 storage sites, which will allow more efficient operations in the context of a site’s evolving risk profile, optimize storage efficiency and capacity, and guide cost-effective MVA efforts; (2) development of DIAL-GCS, a data integration, assimilation, and learning framework for geologic carbon storage projects that can serve as an IMS for automating storage closed-loop operations by leveraging recent developments in semantic sensor web, complex event processing, reduced order modeling, and machine learning technologies; and (3) development of an integrated IMS architecture that utilizes a permanent, continuously active surface seismic monitoring network for process surveillance and real-time management and optimization of a geologic storage project.

The MVA webpage offers links to detailed information on projects performing research in this area.