Well logs reconstruction of petroleum energy exploration based on bidirectional Long Short-term memory networks with a PSO optimization algorithm
Bibliographic record
Abstract
During petroleum energy exploration, estimating missing well logs from existing logging data is very meaningful. Due to a highly nonlinear relationship between various logging data and a challenge to express the complexity of underground geological conditions by deterministic functions, traditional methods are difficult to meet the need of accurate interpretations of log data and fine descriptions of reservoirs. Nevertheless, deep learning method provides an advanced means for reconstructing well logs, and can directly map existing logging data to missing well logs. In this paper, we adopt the PSO-BiLSTM network that combines the BiLSTM (Bidirectional Long Short-term Memory) network with the PSO (Particle Swarm Optimization) algorithm. BiLSTM is an excellent data-driven method that can extract bidirectional temporal well logging data. PSO algorithm enhances the performance of BiLSTM model in predicting missing well logs through hyperparameter optimization, global search capability, and adaptive learning. At the same time, RMSE , MAE , and MAPE are used as indicators to evaluate the performance of PSO-BiLSTM model. The results show that when a PSO-BiLSTM model is applied to well logs reconstruction experiments , the reconstructed value of a log curve is in good agreement with its real value. Compared to LSTM and BiLSTM models, a PSO-BiLSTM model provides the best accuracy and stability in predicting missing well logs. The PSO-BiLSTM model strengthens the extraction of relevant logging information and reduces the error of parameter adjustment. It has an important reference significance for the reconstruction of well logs in complex formations.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| 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) | 0.001 | 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".