Application of multidimensional interpolation and random forest regression to enhanced oil recovery modeling

Краснов, Федор; Glavnov, Nikolay; Sitnikov, A. N.

doi:10.1145/3166094.3166096

Cited by 7 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In machine learning beyond the methods, preparing a result can be more complicated in order to apply it to the oil and gas field. 25 Through the random selection of both the input data and the variables, the RF is able to generate decision trees. During the prediction procedure, those features that do not imply any significance of the final result can be ignored.…”

Section: Methodsmentioning

confidence: 99%

“…As the factor weight or the feature importance is a part of the calculation, it will definitely affect the final result. In machine learning beyond the methods, preparing a result can be more complicated in order to apply it to the oil and gas field . Through the random selection of both the input data and the variables, the RF is able to generate decision trees.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Decision-Making Techniques for Water Shutoff Using Random Forests and Its Application in High Water Cut Reservoirs

et al. 2021

View full text Add to dashboard Cite

The major oil fields are currently in the middle and late stages of waterflooding. The water channels between the wells are serious, and the injected water does little effect. The importance of profile control and water blocking has been identified. In this paper, the decision-making technique for water shutoff is investigated by the fuzzy evaluation method, FEM, which is improved using a random forest, RF, classification model. A machine learning random forest algorithm was developed to identify candidate wells and to predict the well performance for water shutoff operation. A data set consisting of 21 production wells with three-year production history is used, where out of the mentioned well data, 70% of them are implemented for training and the remaining are used for testing the model. After fitting the model, the new weights for the factors are established and decision-making is made. Accordingly, 16 wells out of 21 wells are selected by the FEM where 8 wells out of 21 wells are selected by the new factor weight created by RF for water shutoff. A numerical simulation model is established to plug the selected wells by both methods after which the influence of plugging on water cut, daily oil production, and cumulative oil production is compared. The paper shows that the reservoir had a better performance after eight wells were selected using a new weighting system created by RF instead of the 16 wells that were selected using the FEM model. The paper also states that the new weighting model’s accuracy improved the decision-making abilities of the wells.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Decision-Making Techniques for Water Shutoff Using Random Forests and Its Application in High Water Cut Reservoirs

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The random forest, like any other supervised machine algorithm, has been successfully applied to reservoir characterization (Ao et al, 2018, Krasnov et al, 2017, Baraboshkin et al, 2019. Among the innovations presented in this work, is the application of fractal elements to train and feed a random forest model, focusing on how to supply information in the upstream oil and gas industry.…”

Section: Introductionmentioning

confidence: 99%

Content of Total Organic Carbon Using Random Forest, Borehole Imaging, and Fractal Analysis: A Methodology Applied in the Cretaceous La Luna Formation, South America

2022

Geofis Int

View full text Add to dashboard Cite

Esta investigación presenta un enfoque alternativo para calcular el contenido de carbono orgánico total utilizando registros de cable y técnicas de aprendizaje automático; específicamente, imágenes resistivas de pozo, su resistividad promedio y registro de rayos gamma son empleados para entrenar un modelo regresivo. La metodología se aplicó en la Formación La Luna, la cual ha sido reportada como una de las principales rocas generadoras de Colombia y el oeste de Venezuela. El objetivo de este trabajo es enseñar a una máquina como reconocer patrones entre rasgos fractales en imágenes de pozo y su contenido de carbono orgánico total. El aprendizaje automático implementado se basa en técnicas de aprendizaje por conjuntos, en este caso, un conjunto de árboles de decisión conocido como bosques aleatorios. Los datos empleados tienen un total de 960 mediciones de registros, los cuales fueron divididos aleatoriamente en 80% para entrenamiento y 20% para validación. El resultado es equivalente a la curva obtenida con una regresión semilogarítmica del carbono orgánico medido en el núcleo contra valores de registro de densidad. La precisión de este método es suficientemente alta para ser considerada durante evaluaciones petrofísicas, mostrando un error medio cuadrático de 0.44% y un coeficiente de correlación de Pearson de 0.88. La metodología depende de la calidad de la imagen y cualquier anomalía en estos datos aumentará el error. El modelo generado debe ser recalibrado para otras formaciones, pozos horizontales, desviados y cuando se empleen registro de imágenes durante la perforación.

show abstract

Modeling CO2 Loading Capacity of Diethanolamine (DEA) Aqueous Solutions Using Advanced Deep Learning and Machine Learning Algorithms: Application to Carbon Capture

Mahmoudzadeh,

Hadavimoghaddam,

Atashrouz

et al. 2024

Korean J. Chem. Eng.

View full text Add to dashboard Cite

Application of multidimensional interpolation and random forest regression to enhanced oil recovery modeling

Cited by 7 publications

References 10 publications

Decision-Making Techniques for Water Shutoff Using Random Forests and Its Application in High Water Cut Reservoirs

Decision-Making Techniques for Water Shutoff Using Random Forests and Its Application in High Water Cut Reservoirs

Content of Total Organic Carbon Using Random Forest, Borehole Imaging, and Fractal Analysis: A Methodology Applied in the Cretaceous La Luna Formation, South America

Modeling CO2 Loading Capacity of Diethanolamine (DEA) Aqueous Solutions Using Advanced Deep Learning and Machine Learning Algorithms: Application to Carbon Capture

Contact Info

Product

Resources

About