Joint Inversion of Gravity and Magnetic Anomalies to Image Salt–Basement Structures Offshore Abu Dhabi, UAE, Using Deep Neural Networks
Bibliographic record
Abstract
Summary By using a deep neural network (DNN), a novel technique is developed for a 2.5D joint inversion of gravity and magnetic anomalies to model subsurface salts and basement structures. The joint application of gravity and magnetic anomalies addresses the inherent nonuniqueness problem of geophysical inversions. Moreover, DNN is used to conduct the nonlinear inverse mapping of gravity and magnetic anomalies to depth-to-salt and depth-to-basement. To create the training data set, a three-layer forward model of the subsurface is designed indicating sediments, salts, and the basement. The length and height of the model are determined based on the dimensions of the target area to be investigated. Several random parameters are set to create different representations of the forward model by altering the depth and shape of the layers. Given the topography of the salts and basement layers as well as their predefined density and susceptibility values, the gravity and magnetic anomalies of the forward models are calculated. Using multiprocessing algorithms, thousands of training examples are simulated comprising gravity and magnetic anomalies as input features and depth-to-salt and depth-to-basement as labels. The application of the proposed technique is evaluated to interpret the salt–basement structures over hydrocarbon reservoirs in offshore United Arab Emirates (UAE). Correspondingly, a DNN model is trained using the simulated data set of the target region and is assessed by making predictions on the random actual and noise-added synthetic data. Finally, gravity-magnetic anomalies are fed into the DNN inverse model to estimate the salts and basement structures over three profiles. The results proved the capability of our technique in modeling the subsurface structures.
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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".