FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4295021519> ?p ?o ?g. }

• W4295021519 endingPage "105886" @default.
• W4295021519 startingPage "105886" @default.
• W4295021519 abstract "Lithofacies classification from well logs recorded through heterogeneous carbonate reservoirs helps to improve reservoir discrimination with respect to fluid flow and storage capabilities. A novel technique is developed to classify carbonate lithofacies with the assistance of boosting algorithms for a well drilled into the large Majnoon oil and gas field of southern Iraq. Five boosting machine learning algorithms: Logistic Boosting Regression (LogitBoost), Generalized Boosting Modeling (GBM), Extreme Gradient Boosting (XGBoost), Adaptive Boosting Model (AdaBoost), and K-nearest neighbor (KNN) were comparatively implemented to attain the most realistic lithofacies predictions. Data from available cores provide actual lithofacies determination. Additionally, seven standard well logs recorded provide continuous additional information across the complete reservoir section. Random sub-sampling of the well-log dataset was used to train and test the models. Confusion matrices of the results provided Total Percent Correct (TPC) accuracy measures for LogitBoost, GBM, XGBoost, AdaBoost, and KNN with respect to the entire dataset of 97.65%, 96.99%, 97.74%, 97.74%, and 96.74%, respectively, and with respect to the validation subsets TPC was 94%, 96%, 98%, 91%, and 96%, respectively. The XGBoost provided more accurate lithofacies classification than the other five boosting algorithms with respect to the predictions generated for both the entire dataset and testing subset. The lithofacies predictions were then compared with poro-perm interpretations from the Nuclear Magnetic Resonance (NMR) log and oil rate from the Production Logging Tool (PLT). Rudist-rich and argillaceous lithofacies display lower porosity and permeability, respectively. The Rudist-rich lithotype is associated with high-production-rate zones, whereas the argillaceous facies is associated with low-production-rate zones. The boosting machine learning workflow developed efficiently provides accurate lithofacies classification with reduced uncertainty in carbonate lithofacies determinations. The entire workflow was fully implemented and visualized using open-source R computer codes. These codes have the potential to be generalized for the application of facies classification to other clastic and carbonate reservoirs in oil and gas fields." @default.
• W4295021519 created "2022-09-09" @default.
• W4295021519 creator A5024490166 @default.
• W4295021519 creator A5027047123 @default.
• W4295021519 creator A5028777364 @default.
• W4295021519 date "2022-11-01" @default.
• W4295021519 modified "2023-10-16" @default.
• W4295021519 title "Performance evaluation of boosting machine learning algorithms for lithofacies classification in heterogeneous carbonate reservoirs" @default.
• W4295021519 cites W1605356892 @default.
• W4295021519 cites W1910501430 @default.
• W4295021519 cites W1998811800 @default.
• W4295021519 cites W2024046085 @default.
• W4295021519 cites W2060901857 @default.
• W4295021519 cites W2070493638 @default.
• W4295021519 cites W2097155671 @default.
• W4295021519 cites W2115034894 @default.
• W4295021519 cites W2125751590 @default.
• W4295021519 cites W2132806135 @default.
• W4295021519 cites W2190069420 @default.
• W4295021519 cites W2574388714 @default.
• W4295021519 cites W2575211338 @default.
• W4295021519 cites W2584285694 @default.
• W4295021519 cites W2626176756 @default.
• W4295021519 cites W2762445688 @default.
• W4295021519 cites W2903674682 @default.
• W4295021519 cites W2931285398 @default.
• W4295021519 cites W2963819471 @default.
• W4295021519 cites W2985504740 @default.
• W4295021519 cites W3004732066 @default.
• W4295021519 cites W3007088664 @default.
• W4295021519 cites W3012833929 @default.
• W4295021519 cites W3013598746 @default.
• W4295021519 cites W3014564255 @default.
• W4295021519 cites W3022076686 @default.
• W4295021519 cites W3028084290 @default.
• W4295021519 cites W3038818616 @default.
• W4295021519 cites W3081524168 @default.
• W4295021519 cites W3088354476 @default.
• W4295021519 cites W3090659357 @default.
• W4295021519 cites W3128697108 @default.
• W4295021519 cites W3135028703 @default.
• W4295021519 cites W3174924387 @default.
• W4295021519 cites W3197231937 @default.
• W4295021519 cites W3210092633 @default.
• W4295021519 cites W4242413772 @default.
• W4295021519 cites W4281848597 @default.
• W4295021519 doi "https://doi.org/10.1016/j.marpetgeo.2022.105886" @default.
• W4295021519 hasPublicationYear "2022" @default.
• W4295021519 type Work @default.
• W4295021519 citedByCount "15" @default.
• W4295021519 countsByYear W42950215192022 @default.
• W4295021519 countsByYear W42950215192023 @default.
• W4295021519 crossrefType "journal-article" @default.
• W4295021519 hasAuthorship W4295021519A5024490166 @default.
• W4295021519 hasAuthorship W4295021519A5027047123 @default.
• W4295021519 hasAuthorship W4295021519A5028777364 @default.
• W4295021519 hasConcept C110083411 @default.
• W4295021519 hasConcept C11413529 @default.
• W4295021519 hasConcept C119857082 @default.
• W4295021519 hasConcept C127313418 @default.
• W4295021519 hasConcept C141404830 @default.
• W4295021519 hasConcept C154945302 @default.
• W4295021519 hasConcept C169258074 @default.
• W4295021519 hasConcept C187320778 @default.
• W4295021519 hasConcept C191897082 @default.
• W4295021519 hasConcept C192562407 @default.
• W4295021519 hasConcept C2780659211 @default.
• W4295021519 hasConcept C41008148 @default.
• W4295021519 hasConcept C45942800 @default.
• W4295021519 hasConcept C46293882 @default.
• W4295021519 hasConcept C46686674 @default.
• W4295021519 hasConcept C6648577 @default.
• W4295021519 hasConcept C70153297 @default.
• W4295021519 hasConcept C95623464 @default.
• W4295021519 hasConceptScore W4295021519C110083411 @default.
• W4295021519 hasConceptScore W4295021519C11413529 @default.
• W4295021519 hasConceptScore W4295021519C119857082 @default.
• W4295021519 hasConceptScore W4295021519C127313418 @default.
• W4295021519 hasConceptScore W4295021519C141404830 @default.
• W4295021519 hasConceptScore W4295021519C154945302 @default.
• W4295021519 hasConceptScore W4295021519C169258074 @default.
• W4295021519 hasConceptScore W4295021519C187320778 @default.
• W4295021519 hasConceptScore W4295021519C191897082 @default.
• W4295021519 hasConceptScore W4295021519C192562407 @default.
• W4295021519 hasConceptScore W4295021519C2780659211 @default.
• W4295021519 hasConceptScore W4295021519C41008148 @default.
• W4295021519 hasConceptScore W4295021519C45942800 @default.
• W4295021519 hasConceptScore W4295021519C46293882 @default.
• W4295021519 hasConceptScore W4295021519C46686674 @default.
• W4295021519 hasConceptScore W4295021519C6648577 @default.
• W4295021519 hasConceptScore W4295021519C70153297 @default.
• W4295021519 hasConceptScore W4295021519C95623464 @default.
• W4295021519 hasLocation W42950215191 @default.
• W4295021519 hasOpenAccess W4295021519 @default.
• W4295021519 hasPrimaryLocation W42950215191 @default.
• W4295021519 hasRelatedWork W4200057378 @default.
• W4295021519 hasRelatedWork W4220785415 @default.
• W4295021519 hasRelatedWork W4293069612 @default.

• next