Research on Efficiency Driven Classification in Petroleum Engineering Based on Big Data Algorithm
Bibliographic record
Abstract
Existing petroleum engineering big data algorithms have issues like poor efficiency, insufficient classification accuracy, and poor algorithm adaptability in classification tasks by application field. In order to resolve these issues, this paper proposes an RNN (Recurrent Neural Network) algorithm, which improves the performance of the model in multi-category classification by introducing a combination of ReLU activation function and Softmax output layer. By extracting features and optimizing data from different application scenarios in the field of petroleum engineering, the algorithm effectively improves the classification accuracy and application efficiency of the model. Specifically, this paper uses different application fields in petroleum engineering big data as classification labels, uses the architecture of a neural network with multiple layers, and combines it with the Adam optimizer to improve the training speed and stability of the model by adjusting and fine-tuning the model parameters layer by layer. In the training process at each stage, special emphasis is placed on the adjustment of hyperparameters and the alleviation of the gradient vanishing problem, guaranteeing the effectiveness and precision of the classification results in multi-domain data. The findings from the experiments demonstrate that the enhanced algorithm has strong future potential and practical value, and that it can effectively boost the computation efficiency of huge amounts of data in oil and gas engineering as well as the accuracy of classification assignments in real-world applications. In the comparison of different activation functions, the ReLU activation function (improved model) performed best, with a classification accuracy of 0.852, a training time of 125 seconds, an F1-Score of 0.81, and an AUC-ROC of 0.9.
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 | 0.003 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.002 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.005 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| 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".