Unlocking Sub‐Micrometer Features in Carbonate Rocks: A Cascading Super‐Resolution Approach for Multiscale Multi‐Instrument Carbonate Characterization
Bibliographic record
Abstract
Abstract Digital imaging and modeling are essential tools for characterizing rock structures and understanding fluid flow behavior. These efforts often rely on X‐ray micro‐computed tomography (micro‐CT), which faces an inherent trade‐off between resolution and field‐of‐view (FOV). Deep learning super‐resolution (SR) methods have been developed to overcome this limitation, but their application to carbonate rocks is challenged by complex micro‐nanometer features. Due to the resolution limits, micro‐CT fails to capture sub‐micrometer features such as micropores in carbonates, and using such data as high‐resolution (HR) training images limits the SR model's ability to accurately reconstruct the micropore structures. We introduce a cascading SR pipeline designed to address these challenges and reveal sub‐micrometer features in carbonate rocks. The approach integrates multi‐stage 2D SR networks to progressively enhance low‐resolution (LR) images toward the HR domain, followed by a third‐plane SR network for 3D reconstruction. We evaluate this method on a three‐stage SR task: starting from a 3 m resolution micro‐CT image, super‐resolving to an intermediate 1 m resolution, and ultimately reaching 0.1 m resolution based on scanning electron microscopy (SEM), achieving a 30 scale factor. Validation with unseen SEM demonstrates that the reconstructed domains retain essential structural and physical properties. This approach provides a practical solution to current imaging limitations and enables the integration of multi‐resolution modalities for improved rock characterization.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".