A Conditional Diffusion Model for CO₂ Monitoring and Forecasting in Heterogeneous Geological Formations
Bibliographic record
Abstract
Summary Geological storage is an effective way to reduce CO2 concentrations in the atmosphere. However, accurately predicting the subsurface migration of injected CO2 remains challenging mainly due to geological uncertainties, specifically on parameters like porosity and permeability, along with the high computational cost of conventional reservoir modeling and monitoring techniques. Machine learning (ML) methods have shown promise in addressing these challenges, yet many existing approaches struggle with temporal extrapolation tasks. To address this gap, we use a Conditional Denoising Diffusion Probabilistic Model for CO2 monitoring and forecasting in heterogeneous geological formations. Our framework is trained on an open-source sequestration dataset and focuses on predicting CO2 gas saturation and pressure buildup under defined geological constraints. For our initial tests, we use low-resolution data (64x64) and a single conditioning variable (porosity) to predict CO2 gas saturation and pressure buildup for a single year (year 30.0). Preliminary results demonstrate that the model is able to capture the relationship between geological constraints and target outputs, particularly for CO2 gas saturation. This work will be extended to incorporate high-resolution data (96x200), additional geological constraints, and long-term forecasting. Ultimately, the framework aims to predict CO2 plume evolution beyond the temporal training horizon.
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 | 0.003 |
| 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 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
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".