Digital Rock Physics and Machine Learning

scroll to explore
Cover image for research topic "Digital Rock Physics and Machine Learning"
ChatGPT summary

Advances in machine learning for digital rock physics applications

This research topic investigates the pore structures of shales and other sedimentary rocks, and the effects of depositional environment, lithofacies, physical compaction, and paleo-salinity on their physical and elastic properties. It also examines the application of digital rock physics (DRP) to analyze the characteristics of pore structures and minerals, and the relationships between microscopic structures and the physical properties of reservoirs.

  • Focused ion beam scanning electron microscopy (FIB-SEM) and large volume FIB-SEM (LV-FIB-SEM) 3D models are used to reconstruct pore networks in shales.
  • Synchronous prestack inversion technology is used to predict fluid and lithological properties of ultra-deep carbonate reservoirs.
  • Core and well logging data from the South China Sea are used to analyze the rock physical characteristics.
  • Continental tight oil sandstone reservoirs are studied in terms of their microstructures, physical properties, and division scheme of reservoir types.
  • Experiments are conducted on core samples from Wells ST1 and ST3 to understand the pore structure characteristics and factors influencing the marl reservoir.
  • FIB-SEM technology is used to quantify the pore structures of shale in the Shahejie formation of Dongying depression.
  • Analysis of the pore structure heterogeneity of the low-thermal-maturity shale is conducted to study the effect of saline on shale pore throat.
  • Rock physical modeling is used to establish the internal relationship between the elastic properties and physical parameters of tight sandstones.
The ChatGPT summary is generated out of the summaries of the individual article abstracts.