Gestión eficiente de yacimientos mediante inteligencia artificial

Autores/as

DOI:

https://doi.org/10.5281/23302643

Palabras clave:

Inteligencia artificial, gestión de yacimientos, gemelos digitales, redes neuronales informadas

Resumen

El documento aborda la transición hacia la Ingeniería de Yacimientos 4.0, un paradigma que integra la Inteligencia Artificial (IA) y el procesamiento de Big Data para optimizar la gestión de reservorios de hidrocarburos. Frente a las limitaciones de tiempo y resolución de la simulación numérica tradicional, la IA propone el uso de modelos basados en datos (Data-Driven) y modelos híbridos, como las Redes Neuronales Informadas por la Física (PINNs), garantizando predicciones dinámicas, precisas y técnicamente viables.  A través de cinco capítulos, el texto examina áreas críticas como la interpretación automatizada de sísmica mediante visión artificial, uso de algoritmos de agrupamiento y redes neuronales para predecir propiedades petrofísicas, creación de modelos sustitutos (Proxy Models) y desarrollo de Gemelos Digitales en tiempo real. Este ecosistema inteligente reduce la incertidumbre geológica, optimiza los procesos de recuperación adicional (EOR) y mejora la toma de decisiones bajo criterios de gobernanza del dato e interpretabilidad (XAI).

Descargas

Los datos de descarga aún no están disponibles.

Biografía del autor/a

  • Lenisbeth Paola Fuenmayor Molero, Petróleos & Renovables S. A. Maracaibo, Venezuela

    Ingeniera en Petróleo. Petróleos & Renovables S. A. Maracaibo, Venezuela.

Referencias

Al-Mudhafer, M. (2017). K-Means Clustering for Reservoir Zoning and Flow Units Definition. info@spe.org. Society of Petroleum Engineers. Estados Unidos. "Automated Reservoir Characterization Using Unsupervised Learning". SPE Reservoir Evaluation & Engineering Journal. Journal-editor@spe.org

Al-Mudhafer, W. J. (2017). Integrating well log interpretations and core measurements for flow unit classification using unsupervised machine learning algorithms. Journal of Petroleum Science and Engineering, 151, 201–211. https://doi.org/10.1016/j.petrol.2017.01.008

Aminian, K., & Ameri, S. (2005). Application of artificial neural networks for reservoir characterization. Journal of Natural Gas Science and Engineering, 2(1), 1–11. https://doi.org/10.1016/j.jngse.2005.01.001

Anifowose, F., y Abdulraheem, A. (2011). Advanced Supervised Learning Techniques for Reservoir Property Modeling. fanifowose@kfupm.edu.sa. King Fahd University of Petroleum and Minerals. Arabia Saudita. "Lithofacies Identification and Production Rate Predictions via Random Forest and SVM". Computers & Geosciences. cgeo-journal@elsevier.com

Bora, B., & Gupta, A. (2021). Smart fields and digital transformation in the upstream oil and gas industry: A review of current trends and future directions. Journal of Petroleum Science and Engineering, 203, 108620. https://doi.org/10.1016/j.petrol.2021.108620

Bratvold, R., y Begg, S. (2020). Making Good Decisions in the Oil and Gas Industry. reidun.bratvold@uis.no. Center for Oil Recovery, University of Stavanger. Noruega. "Epistemology and Decision-Making Under Uncertainty in Reservoir Engineering 4.0". SPE Operations & Management. manageditor@spe.org

Caers, J. (2011). Modeling Uncertainty in the Earth Sciences. jcaers@stanford.edu. Wiley-Blackwell. Estados Unidos. "Intelligent Geomodeling and Pattern-Based Spatial Simulation". Mathematical Geosciences. math-geosciences@springer.com

Holdaway, K. (2014). Harnessing Oil and Gas Big Data Analytics. keith.holdaway@sas.com. John Wiley & Sons. Reino Unido. "The 5 Vs of Data Applied to Modern Reservoir Characterization". Oil & Gas Journal. ogj-editor@pennwell.com

Lee, J. y Wattenbarger, R. (2014). Gas Reservoir Engineering. j.lee@tamu.edu. Society of Petroleum Engineers. Estados Unidos. Advanced decline curve analysis and EUR estimation in unconventional reservoirs. SPE Production & Operations. r.wattenbarger@tamu.edu

Mohaghegh, S. (2011). Data-driven reservoir modeling. shahab@data-drivenreservoirmodeling.com. Society of Petroleum Engineers. Estados Unidos. Implementing proxy models for rapid reservoir simulation. Journal of Petroleum Technology. s.mohaghegh@wvu.edu.

Mohaghegh, S. (2017). Data-Driven Reservoir Modeling. shahab@data-driven-reservoir.com. Exploration and Production Data Analytics Tech. Estados Unidos. "Differences Between Physics-Based and Data-Driven Paradigm in Petroleum Engineering". Journal of Petroleum Data Analytics. jpda-editorial@spe.org

Oliver, D. S., & Chen, Y. (2011). Recent progress on reservoir history matching: a review. Computational Geosciences, 15(1), 185–221. https://doi.org/10.1007/s10596-010-9194-2

Raissi, M., Perdikaris, P., y Karniadakis, G. (2019). Physics-Informed Neural Networks: A Deep Learning Framework. maziar.raissi@colorado.edu. Brown University Center for Fluid Mechanics. Estados Unidos. "Integrating Darcy’s Law in the Training of Neural Networks for Porous Media". Journal of Computational Physics. jcp-office@elsevier.com

Satter, A., y Iqbal, G. (2016). Reservoir Engineering 4.0 and Integrated Asset Management. abdus.satter@unisa.edu. Gulf Publishing Company. Estados Unidos. "From Analogue to Digital Assets via Advanced Analytics". World Oil Magazine. editorial@worldoil.com

Siddiqui, S., y Rahman, M. (2013). Stochastic Modeling and Geological Risk Analysis. ssiddiqui@ttu.edu. Texas Tech University Press. Estados Unidos. "Bayesian Networks and Probabilistic Models for Subsurface Risk Management". Journal of Petroleum Exploration and Production Technology. jpept-editor@springer.com

Willhite, G. y Green, D. (2018). Enhanced Oil Recovery. g.willhite@ku.edu. Society of Petroleum Engineers. Estados Unidos. Advanced optimization of injection patterns in mature fields. SPE Reservoir Evaluation & Engineering. d.green@ku.edu.

Wu, X. (2019). Computer Vision in Geosciences. xinwucg@ustc.edu.cn. University of Science and Technology of China. China. "Automated Seismic Interpretation for Fault and Discontinuity Detection Using CNNs". IEEE Transactions on Geoscience and Remote Sensing. tgrs-editor@ieee.org

Descargas

Publicado

2026-10-12

Cómo citar

Gestión eficiente de yacimientos mediante inteligencia artificial. (2026). PetroRenova Indexed, 2(4), 48-74. https://doi.org/10.5281/23302643