Notice bibliographique
Résumé
As 2022 drew to a close, we saw the emergence of ChatGPT, a development that left me both fascinated and slightly apprehensive. Initial posts on LinkedIn and similar platforms focused on its impressive capabilities, yet it wasn’t long before discussions of its inherent biases began to surface. Artificial intelligence (AI) and machine learning (ML) technologies have rapidly progressed and have significantly affected traditional reservoir engineering, bringing innovative methodologies to reservoir simulations. However, it is essential to understand that these AI and ML technologies are only as effective and trustworthy as the data they are trained on. Limiting the data we feed these systems might inadvertently restrict their predictive power and the scope of their solutions. As we increasingly rely on these data-driven tools for decision-making, we must be cautious of the conclusions they draw and the narratives they generate. These can subtly shape our viewpoints, highlighting the need for a firm understanding of fundamental principles. I am reminded of a term coined by Daniel Yang: the “Nintendo Engineer,” an engineer whose thought process is guided by simulations rather than the other way around. With this in mind, returning to the foundational principles underpinning our field is crucial. This approach could counterbalance our reliance on AI and ML technologies, helping us maintain a well-rounded perspective. The papers I am recommending for your reading embody this mindset. The first paper highlights these technologies’ practical challenges and constraints, offering valuable insights for reservoir engineers. The authors emphasize the need for a balanced approach that combines these advanced techniques with informed decision-making. They also highlight that only some optimization problems can be solved with a plug-and-play approach and that the engineer has to frame the problem in a manageable and meaningful way. The second paper addresses the limitations of the conventional Stone II three-phase permeability model and presents a novel, robust alternative. It takes a fundamentals-based approach to develop an alternative model for the three-phase relative permeability model. Inherent in this recommendation is my bias toward heavy oil because it is the area I currently work in. The third paper showcases the remarkable potential of AI in supplementing traditional reservoir simulation. The paper’s real-world application demonstrates the practicality and adaptability of AI in reservoir engineering and simulation. I hope you enjoy reading this selection of papers and find them enlightening. Recommended additional reading at OnePetro: www.onepetro.org. URTEC 2021-5549 Use of Machine Learning Production Driver Cross Sections for Regional Geologic Insights in the Bakken Three Forks Play by T. Cross, Novi Labs, et al. SPE 214219 Business Intelligence Dashboarding Application in Reservoir Simulation by Ke Wang, ADNOC, et al.
Récupéré en direct depuis OpenAlex et désinversé. Les résumés ne sont pas conservés dans cette base de données : les index inversés représentent 8,6 Go des 9,3 Go de texte de la base, et le serveur dispose de 13 Go libres.
Comment cette classification a été obtenuedéplier
Prédiction machine sur la base complète
Imitation des enseignantsNi prévalence calibrée, ni vérité terrain. Validation humaine à venir. Le volet Gemma est une étiquette directe du modèle pour chaque travail de la base, lue sur la notice réduite au titre. Le volet Codex est un classifieur appris des 10 348 étiquettes directes de Codex et calibré sur les taux pondérés de l'échantillon; les champs sans appui suffisant ne portent aucun appel Codex. Le mode candidate est l'union des deux volets; le consensus est leur intersection. Ces sorties portent le statut machine_predicted_unvalidated et ne sont pas des étiquettes humaines.
Scores du classifieur distillé par catégorie (deux têtes)
| Catégorie | Codex | Gemma |
|---|---|---|
| Métarecherche | 0,003 | 0,006 |
| Méta-épidémiologie (sens strict) | 0,001 | 0,000 |
| Méta-épidémiologie (sens large) | 0,001 | 0,001 |
| Bibliométrie | 0,001 | 0,001 |
| Études des sciences et des technologies | 0,001 | 0,001 |
| Communication savante | 0,006 | 0,005 |
| Science ouverte | 0,001 | 0,002 |
| Intégrité de la recherche | 0,004 | 0,004 |
| Charge utile insuffisante (le modèle a refusé de juger) | 0,218 | 0,120 |
Scores machine (provisoires)
Les deux têtes enseignantes du modèle étudiant, lues sur ce travail. Un score ordonne la base pour la relecture; il n'affirme jamais une catégorie, et le statut de validation accompagne chaque rangée tel quel.
Scores de référence d'un modèle non mature (critères de maturité non atteints, 7 itérations). Un score ordonne; il n'affirme jamais une catégorie.
score_only:v0-immature-baseline · tel quel depuis la passe de notation : score_only signifie que le nombre peut ordonner les travaux, et qu'aucune étiquette de catégorie n'en découleClassification
machine, non validéePrédiction automatique; un appel candidat d’une seule source (Gemma direct ou Codex distillé), pas un consensus.
Le détail, modèle par modèle et score par score, se trouve en fin de page sous « Comment cette classification a été obtenue ».