Machine learning enhanced data assimilation framework for multiscale carbonate rock characterization
arXiv:2602.06989v2 Announce Type: replace-cross Abstract: Carbonate reservoirs offer significant capacity for subsurface carbon storage, oil production, and underground hydrogen storage. X-ray computed tomography (X-ray CT) coupled with numerical simulations is commonly used to investigate the multiphase flow behaviors in carbonate rocks. Carbonates exhibit pore size distribution across scales, hindering the comprehensive investigation with conventional X-ray CT images. Imaging samples at both macro and micro-scales (multi-scale imaging) proved to be a viable option in this context. However, m
The continuous advancements in AI and imaging techniques are enabling more sophisticated analysis of complex natural structures, making this research timely for addressing resource challenges.
Improved characterization of carbonate rocks through AI can enhance the efficiency of crucial subsurface activities like carbon storage, oil production, and hydrogen storage, impacting energy security and environmental goals.
The integration of machine learning with multiscale imaging provides a more comprehensive and accurate understanding of carbonate reservoir properties than previously possible with conventional methods.
- · Oil & Gas Industry
- · Carbon Capture & Storage Sector
- · Geophysical Exploration Companies
- · AI/ML in Scientific Computing
- · Traditional reservoir characterization methods
- · Companies reliant on less efficient subsurface analysis
More precise and efficient management of subsurface carbon storage, oil extraction, and hydrogen storage projects becomes feasible.
Reduced operational costs and environmental risks associated with these subsurface activities due to better predictive models.
Acceleration of net-zero goals through enhanced carbon storage capacity and optimized energy resource management could positively impact climate change efforts.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG