Reservoir characterization

Fig. 1—Proposed methodology with multiple stages of carbon-storage investigation for magnesium-, calcium-, and iron-rich minerals.

Oilfield chemistry

Study Explores Accelerated Carbon Capture and Storage Through Mineral Carbonation

This paper presents a novel methodology for assessing the rapid mineral carbonation of carbon dioxide through geochemical interactions with carbon-, magnesium-, and iron-rich minerals abundant in geological formations.

Flowchart illustrating the predictive workflow that starts with data collection and eds withmodel deployment. The flowchart emphasizes key stages of model development and deployment,including data preprocessing, feature creation, model training, model evaluation, and model deployment.

Reservoir characterization

Machine Learning Unlocks Potential of Mud Logs, LWD in the Gulf of Thailand

This study aims to use machine-learning techniques to predict well logs by analyzing mud-log and logging-while-drilling data.

Fig. 1—Workflow for the developed PIML permeability-prediction methodology.

Reservoir characterization

Physics-Informed Machine Learning Enhances Permeability Prediction in Carbonate Reservoirs

This study integrates physics-based constraints into machine-learning models, thereby improving their predictive accuracy and robustness.