Carbon Transport & Storage

AI/ML Approaches for Research and Development Application

Approaches
Use machine learning approaches based on known labels/expectations, usually for
  • Classification (e.g., Logistic, Support Vector Machine)
  • Regression (e.g., Linear, Kernel Ridge)
  • Predict subsurface CO₂ pressure, saturation, and other behaviors to ensure secured carbon storage
  • Optimize operations and performances of critical infrastructure and its components
  • Detect leakage Geochemically informed leak detection
  • Forecast potential infrastructure failure and detects (e.g., pipelines)
  • Structured numeric data, text, image, maps, sequences, time-series data
  • Predictive and prescriptive CO₂ operation and management
  • Predictive regulation and decision support
  • Real-time prediction and monitoring
  • Site management and planning
Approaches
Use machine learning approaches without known labels/expectations, usually for
  • Clustering
  • Dimension reduction
  • Group existing oil fields (onshore and offshore) with similar characteristics as potential repurposed storage fields
  • Cluster subsurface
  • Reduce the dimensions and complexities of the data
  • Structured or unstructured data
  • Anomaly detection for disaster prevention
  • Data reduction
Approaches
Use complex neural network architecture for
  • Image and spatial classification
  • Time series regression
  • Natural language processing
  • Predict subsurface CO₂ pressure, saturation, and other behaviors to ensure secured carbon storage
  • Accelerate data processing of large sensor dataset
  • Predict complex and multi-scale reservoir characteristics
  • Enable a highly reliable transport network that efficiently connects carbon sources to sinks
  • Structured numeric data, text, image, maps, sequences, time-series data
  • Complex CO₂ storage optimization
  • Pipeline failure prediction and prevention
  • Supply chain optimization
  • Multi-scale and resolution prediction
Approaches
Combine more than one machine learning models to handle the tasks
  • Random Forest
  • XGBoost
  • Committee Machine
  • Assess the capacity and long-term integrity of subsurface environments, surface and subsurface mineralization processes, and other potential carbon containment resources
  • Predict subsurface CO₂ pressure and saturation
  • Structured numeric data, text, image, maps, sequences, time-series data
  • Predictive and prescriptive operation optimization
  • Predictive decision support
Approaches

Integrate scientific equations and knowledge into machine learning algorithms (usually using Deep Learning), such as Physics-Informed Machine Learning

  • Predict subsurface CO₂ pressure, saturation, and other behaviors to ensure secured carbon storage
  • Forecast infrastructure life and risks
  • Solve partial differential equations as generalized solver
  • Structured numeric data, text, image, maps, sequences, time-series data
  • Scientific equations, field equations, partial differential equations
  • Predictive and prescriptive operation optimization
  • Multi-scale and resolution prediction
  • Predictive decision support
Large Language Models for UNSTRUCTURED DATA MINING Large Language Models for GENERATIVE DISCOVERY Transfer Learning Science-based Learning Edge Computing Advance Sensor Reinforcement Learning Operator Learning
Characterize Materials
Develop Structural/Functional Materials
Enable Smart Components w/embedded sensors
Optimize regional Planning and Operations
Modeling/Simulation Bridging Scales
Accelerate Flow Sheet Initialization
Optimize Turbine Operations
Assess/Control H2 Combustion Characteristics