FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3093991099> ?p ?o ?g. }

• W3093991099 abstract "Abstract A long-term well control strategy is frequently selected using optimization methods applied to reservoir simulations. However, this approach usually requires a large number of simulations that can be computationally demanding. In this paper, we evaluated several machine learning (ML) techniques to reduce the number of simulations for optimizing long-term well control strategy while preserving the quality of the solution. We proposed a methodology, denoted as IDLHC–ML, which combines many ML techniques with iterative discrete Latin hypercube (IDLHC) – a gradient-free optimization algorithm that was successfully applied in previous work – to optimize the coefficients of the logistic equation that guides the well's bottom-hole pressure along the time horizon. In IDLHC-ML, we used a set of simulation runs from the first iteration to train the initial ML models. From the second iteration onwards, we employed the trained ML models to predict the net present value (NPV) and only a percentage of the scenarios, which were expected to have the best NPV, were then simulated. As we simulated new scenarios, we updated our ML models to further improve predictions. For a fair comparison, we set the same values for the optimization parameters of IDLHC to the IDLHC–ML and, then, we compared the NPV and the number of simulation runs considering different configurations of IDLHC parameters. In this paper, we evaluated a total of twelve ML regression techniques, such as Bayesian Ridge, Random Forest, and stacked ensemble learning, which consists in using the predictions from multiple ML algorithms as input to a second-level learning model. To minimize random effects, we repeatedly applied IDLHC and IDLHC–ML five times in a single reservoir model (nominal optimization). The results showed that, depending on the IDLHC optimization parameters, IDLHC-ML reduced at least 27% of simulations while keeping the equivalent NPV statistical metrics calculated in all five repetitions, when compared to IDLHC. Moreover, the best ML technique for IDLHC–ML varied with the IDLHC set of optimization parameters. To conclude, the method proposed here was able to reduce a significant amount of computational time by curtailing the total number of full-physics expensive reservoir simulations, with the help of fast and low-cost ML models. There are many published studies in well control optimization, but these generally involve high computational demand. In this sense, ML methods revealed to be an adequate and inexpensive alternative in reducing the number of simulation runs in well control optimization. The methodology is generic and it can be applied under uncertainties, and for more complex cases." @default.
• W3093991099 created "2020-10-29" @default.
• W3093991099 creator A5018367231 @default.
• W3093991099 creator A5046901637 @default.
• W3093991099 creator A5052275743 @default.
• W3093991099 creator A5087182558 @default.
• W3093991099 date "2020-10-19" @default.
• W3093991099 modified "2023-10-18" @default.
• W3093991099 title "A Machine Learning Approach to Reduce the Number of Simulations for Long-Term Well Control Optimization" @default.
• W3093991099 cites W1538691674 @default.
• W3093991099 cites W1988790447 @default.
• W3093991099 cites W2009930987 @default.
• W3093991099 cites W2023632033 @default.
• W3093991099 cites W2024389841 @default.
• W3093991099 cites W2074780275 @default.
• W3093991099 cites W2293818193 @default.
• W3093991099 cites W2331578319 @default.
• W3093991099 cites W2360351561 @default.
• W3093991099 cites W2415844763 @default.
• W3093991099 cites W2430295593 @default.
• W3093991099 cites W2615765637 @default.
• W3093991099 cites W2753092554 @default.
• W3093991099 cites W2767824321 @default.
• W3093991099 cites W2783875661 @default.
• W3093991099 cites W2787894218 @default.
• W3093991099 cites W28412257 @default.
• W3093991099 cites W2904708820 @default.
• W3093991099 cites W2953465309 @default.
• W3093991099 cites W2971312699 @default.
• W3093991099 cites W2980439226 @default.
• W3093991099 cites W3035002525 @default.
• W3093991099 cites W4212883601 @default.
• W3093991099 cites W4255949318 @default.
• W3093991099 doi "https://doi.org/10.2118/201379-ms" @default.
• W3093991099 hasPublicationYear "2020" @default.
• W3093991099 type Work @default.
• W3093991099 sameAs 3093991099 @default.
• W3093991099 citedByCount "1" @default.
• W3093991099 countsByYear W30939910992023 @default.
• W3093991099 crossrefType "proceedings-article" @default.
• W3093991099 hasAuthorship W3093991099A5018367231 @default.
• W3093991099 hasAuthorship W3093991099A5046901637 @default.
• W3093991099 hasAuthorship W3093991099A5052275743 @default.
• W3093991099 hasAuthorship W3093991099A5087182558 @default.
• W3093991099 hasConcept C105795698 @default.
• W3093991099 hasConcept C11413529 @default.
• W3093991099 hasConcept C121332964 @default.
• W3093991099 hasConcept C126255220 @default.
• W3093991099 hasConcept C154945302 @default.
• W3093991099 hasConcept C173608175 @default.
• W3093991099 hasConcept C177264268 @default.
• W3093991099 hasConcept C19499675 @default.
• W3093991099 hasConcept C199360897 @default.
• W3093991099 hasConcept C20820323 @default.
• W3093991099 hasConcept C2778049539 @default.
• W3093991099 hasConcept C28761237 @default.
• W3093991099 hasConcept C33923547 @default.
• W3093991099 hasConcept C41008148 @default.
• W3093991099 hasConcept C50820777 @default.
• W3093991099 hasConcept C61797465 @default.
• W3093991099 hasConcept C62520636 @default.
• W3093991099 hasConceptScore W3093991099C105795698 @default.
• W3093991099 hasConceptScore W3093991099C11413529 @default.
• W3093991099 hasConceptScore W3093991099C121332964 @default.
• W3093991099 hasConceptScore W3093991099C126255220 @default.
• W3093991099 hasConceptScore W3093991099C154945302 @default.
• W3093991099 hasConceptScore W3093991099C173608175 @default.
• W3093991099 hasConceptScore W3093991099C177264268 @default.
• W3093991099 hasConceptScore W3093991099C19499675 @default.
• W3093991099 hasConceptScore W3093991099C199360897 @default.
• W3093991099 hasConceptScore W3093991099C20820323 @default.
• W3093991099 hasConceptScore W3093991099C2778049539 @default.
• W3093991099 hasConceptScore W3093991099C28761237 @default.
• W3093991099 hasConceptScore W3093991099C33923547 @default.
• W3093991099 hasConceptScore W3093991099C41008148 @default.
• W3093991099 hasConceptScore W3093991099C50820777 @default.
• W3093991099 hasConceptScore W3093991099C61797465 @default.
• W3093991099 hasConceptScore W3093991099C62520636 @default.
• W3093991099 hasLocation W30939910991 @default.
• W3093991099 hasOpenAccess W3093991099 @default.
• W3093991099 hasPrimaryLocation W30939910991 @default.
• W3093991099 hasRelatedWork W2073194613 @default.
• W3093991099 hasRelatedWork W2154735538 @default.
• W3093991099 hasRelatedWork W2218563287 @default.
• W3093991099 hasRelatedWork W2364245233 @default.
• W3093991099 hasRelatedWork W2413588304 @default.
• W3093991099 hasRelatedWork W2578956463 @default.
• W3093991099 hasRelatedWork W2916710807 @default.
• W3093991099 hasRelatedWork W2980066635 @default.
• W3093991099 hasRelatedWork W3205447645 @default.
• W3093991099 hasRelatedWork W4286907761 @default.
• W3093991099 isParatext "false" @default.
• W3093991099 isRetracted "false" @default.
• W3093991099 magId "3093991099" @default.
• W3093991099 workType "article" @default.