Imageamento hiperespectral e geração de modelos preditivos da concentração de carbono orgânico total em folhelhos betuminosos
Bibliographic record
Abstract
O uso do imageamento hiperespectral em modelos preditivos para a parametrização de variáveis geoquímicas e geológicas é um conhecimento inovador na geologia de petróleo. Com sucesso, pode reduzir os custos em processos de análise de testemunhos de rocha. O presente estudo aborda um testemunho de rocha de folhelhos betuminosos do Grupo Horn River, Canadá, e objetiva avaliar a possibilidade de predição do Carbono Orgânico Total (COT) por meio de dados de imageamento hiperespectral na região do infravermelho. Desta forma, foi desenvolvido um código baseado no método Máquina de Vetores de Suporte para gerar as predições. Os valores preditos de COT apresentaram um erro de 1,11% dos valores reais de COT. A análise de sensibilidade do modelo indica influência das assinaturas espectrais dos hidrocarbonetos. O modelo foi aplicado a todos os pixels da imagem hiperespectral do testemunho de rocha e mostrou a variabilidade do COT em 2 dimensões. Os resultados indicam grande potencial dos dados de imageamento hiperespectral para predições geoquímicas em folhelhos betuminosos. ABSTRACT: The use of hyperspectral data and predictive models for the parameterization of geochemical variables is a novel knowledge in petroleum geology. Successfully, it can reduce costs in drill core analysis processes. The present study addresses the bituminous shale of the Horn River Formation, Canada, and aims to evaluate the possibility of predicting Total Organic Carbon (TOC) with hiperspectral data in the infrared region, from a drill core. Thus, a code based on the Support Vector Machine method was built to generate the predictions. The predictive model reached an error of 1.11 % of the TOC values. The sensitivity analysis of the model indicates the influence of the hydrocarbon spectral signatures. The model was applied to all pixels of drill core imagery and showed TOC variability in two dimensions. The results indicate the potential of hyperspectral data for geochemical predictions in bituminous shales.
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) | 0.000 | 0.001 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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".