FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308485586> ?p ?o ?g. }

• W4308485586 endingPage "111169" @default.
• W4308485586 startingPage "111169" @default.
• W4308485586 abstract "Porosity estimation is a fundamental input for reservoir management and petrophysical characterization, and this feature is usually estimated based on laboratory measurements or through the use of well-logs. As an important resource for porosity quantification, nuclear magnetic resonance (NMR) well-logs are extremely useful; they allow geologists and petrophysicists to rapidly quantify different types of porosities (including total, effective, and free fluid porosity), and to perform a full formation evaluation and a reservoir quality analysis. However, the activation of wireline tools, the signal-to-noise ratio, the environmental conditions, and the characteristics of the formation fluid can create expensive and adverse conditions for subsurface acquisition. This research aims to develop machine learning models for the creation of synthetic NMR well-logs, assisted by auxiliary well-logging features. Four supervised models: multilayer perceptron neural network, AdaBoost, XGBoost, and CatBoost, comparing the adjusted R2 and RMSE. Of these, the CatBoost regressor provided the most highly optimized model. It was able to reduce local dissimilarities with the real dataset, and returned a better global metric score, yielding an adjusted R2 of 0.87 and an RMSE of less than 0.01. Moreover, all of the machine learning models provided substantial improvements in total porosity estimation, particularly compared to conventional empirical calculations based on density and sonic well-logs. An improvement of 0.5520 in the adjusted R2 was achieved for the density porosity, and 0.2 for the sonic porosity. The differences between real NMR well-logs and the machine learning outputs were in general less than 5%, for most of the well-logging interval. In addition, a tree boosted porosity model based on well-logs is presented for the first time, and the contributions and impacts of the input features on the model predictions are explored. Finally, the behaviors of the linear and nonlinear features of the model are examined, which allows us to better understand the complex relationships among the features and the dataset used." @default.
• W4308485586 created "2022-11-12" @default.
• W4308485586 creator A5041419220 @default.
• W4308485586 creator A5074863274 @default.
• W4308485586 creator A5086472422 @default.
• W4308485586 date "2023-01-01" @default.
• W4308485586 modified "2023-10-16" @default.
• W4308485586 title "Prediction of nuclear magnetic resonance porosity well-logs in a carbonate reservoir using supervised machine learning models" @default.
• W4308485586 cites W1678356000 @default.
• W4308485586 cites W1971916086 @default.
• W4308485586 cites W2058524839 @default.
• W4308485586 cites W2140404110 @default.
• W4308485586 cites W2775262878 @default.
• W4308485586 cites W2810350385 @default.
• W4308485586 cites W2883318912 @default.
• W4308485586 cites W2913387978 @default.
• W4308485586 cites W2942909925 @default.
• W4308485586 cites W2968220636 @default.
• W4308485586 cites W2971914670 @default.
• W4308485586 cites W2991366864 @default.
• W4308485586 cites W2995779819 @default.
• W4308485586 cites W2996070666 @default.
• W4308485586 cites W2999615587 @default.
• W4308485586 cites W2999707118 @default.
• W4308485586 cites W3007192248 @default.
• W4308485586 cites W3007625702 @default.
• W4308485586 cites W3010527905 @default.
• W4308485586 cites W3044143324 @default.
• W4308485586 cites W3106811549 @default.
• W4308485586 cites W3122925674 @default.
• W4308485586 cites W3137008767 @default.
• W4308485586 cites W3200279263 @default.
• W4308485586 cites W3204572174 @default.
• W4308485586 cites W4200150814 @default.
• W4308485586 doi "https://doi.org/10.1016/j.petrol.2022.111169" @default.
• W4308485586 hasPublicationYear "2023" @default.
• W4308485586 type Work @default.
• W4308485586 citedByCount "1" @default.
• W4308485586 countsByYear W43084855862023 @default.
• W4308485586 crossrefType "journal-article" @default.
• W4308485586 hasAuthorship W4308485586A5041419220 @default.
• W4308485586 hasAuthorship W4308485586A5074863274 @default.
• W4308485586 hasAuthorship W4308485586A5086472422 @default.
• W4308485586 hasConcept C119857082 @default.
• W4308485586 hasConcept C127313418 @default.
• W4308485586 hasConcept C153180895 @default.
• W4308485586 hasConcept C154945302 @default.
• W4308485586 hasConcept C159985019 @default.
• W4308485586 hasConcept C192562407 @default.
• W4308485586 hasConcept C35817400 @default.
• W4308485586 hasConcept C41008148 @default.
• W4308485586 hasConcept C46293882 @default.
• W4308485586 hasConcept C50644808 @default.
• W4308485586 hasConcept C6648577 @default.
• W4308485586 hasConcept C78762247 @default.
• W4308485586 hasConceptScore W4308485586C119857082 @default.
• W4308485586 hasConceptScore W4308485586C127313418 @default.
• W4308485586 hasConceptScore W4308485586C153180895 @default.
• W4308485586 hasConceptScore W4308485586C154945302 @default.
• W4308485586 hasConceptScore W4308485586C159985019 @default.
• W4308485586 hasConceptScore W4308485586C192562407 @default.
• W4308485586 hasConceptScore W4308485586C35817400 @default.
• W4308485586 hasConceptScore W4308485586C41008148 @default.
• W4308485586 hasConceptScore W4308485586C46293882 @default.
• W4308485586 hasConceptScore W4308485586C50644808 @default.
• W4308485586 hasConceptScore W4308485586C6648577 @default.
• W4308485586 hasConceptScore W4308485586C78762247 @default.
• W4308485586 hasLocation W43084855861 @default.
• W4308485586 hasOpenAccess W4308485586 @default.
• W4308485586 hasPrimaryLocation W43084855861 @default.
• W4308485586 hasRelatedWork W1488608874 @default.
• W4308485586 hasRelatedWork W2247603160 @default.
• W4308485586 hasRelatedWork W2410999582 @default.
• W4308485586 hasRelatedWork W2595101125 @default.
• W4308485586 hasRelatedWork W2768877941 @default.
• W4308485586 hasRelatedWork W2967499481 @default.
• W4308485586 hasRelatedWork W3000810068 @default.
• W4308485586 hasRelatedWork W4286220339 @default.
• W4308485586 hasRelatedWork W4380791593 @default.
• W4308485586 hasRelatedWork W1991526616 @default.
• W4308485586 hasVolume "220" @default.
• W4308485586 isParatext "false" @default.
• W4308485586 isRetracted "false" @default.
• W4308485586 workType "article" @default.