FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3097796199> ?p ?o ?g. }

• W3097796199 endingPage "026007" @default.
• W3097796199 startingPage "026007" @default.
• W3097796199 abstract "Abstract In this paper, we present a new deep-learning disruption-prediction algorithm based on important findings from explorative data analysis which effectively allows knowledge transfer from existing devices to new ones, thereby predicting disruptions using very limited disruption data from the new devices. The explorative data analysis, conducted via unsupervised clustering techniques confirms that time-sequence data are much better separators of disruptive and non-disruptive behavior than the instantaneous plasma-state data, with further advantageous implications for a sequence-based predictor. Based on such important findings, we have designed a new algorithm for multi-machine disruption prediction that achieves high predictive accuracy for the C-Mod (AUC = 0.801), DIII-D (AUC = 0.947) and EAST (AUC = 0.973) tokamaks with limited hyperparameter tuning. Through numerical experiments, we show that a boosted accuracy (AUC = 0.959) is achieved for the EAST predictions by including only 20 disruptive discharges with thousands of non-disruptive discharges from EAST in the training, combined with more than a thousand discharges from DIII-D and C-Mod. The improvement in the predictive ability obtained by combining disruption data from other devices is found to be true for all permutations of the three devices. Furthermore, by comparing the predictive performance of each individual numerical experiment, we find that non-disruption data are machine-specific, while disruption data from multiple devices contain device-independent knowledge that can be used to inform predictions for disruptions occurring in a new device." @default.
• W3097796199 created "2020-11-09" @default.
• W3097796199 creator A5032830528 @default.
• W3097796199 creator A5038291431 @default.
• W3097796199 creator A5049937363 @default.
• W3097796199 creator A5059265684 @default.
• W3097796199 creator A5070244572 @default.
• W3097796199 creator A5076307875 @default.
• W3097796199 date "2020-12-22" @default.
• W3097796199 modified "2023-10-05" @default.
• W3097796199 title "Hybrid deep-learning architecture for general disruption prediction across multiple tokamaks" @default.
• W3097796199 cites W1964499601 @default.
• W3097796199 cites W1964616952 @default.
• W3097796199 cites W1987296455 @default.
• W3097796199 cites W1995336912 @default.
• W3097796199 cites W2010066433 @default.
• W3097796199 cites W2014096208 @default.
• W3097796199 cites W2029148907 @default.
• W3097796199 cites W2036137984 @default.
• W3097796199 cites W2049009017 @default.
• W3097796199 cites W2060540104 @default.
• W3097796199 cites W2083902178 @default.
• W3097796199 cites W2130983602 @default.
• W3097796199 cites W2135293965 @default.
• W3097796199 cites W2155653793 @default.
• W3097796199 cites W2241427245 @default.
• W3097796199 cites W2285344451 @default.
• W3097796199 cites W2436467738 @default.
• W3097796199 cites W2531207078 @default.
• W3097796199 cites W2592115149 @default.
• W3097796199 cites W2762618983 @default.
• W3097796199 cites W2789327431 @default.
• W3097796199 cites W2792542213 @default.
• W3097796199 cites W2804565953 @default.
• W3097796199 cites W2890081106 @default.
• W3097796199 cites W2937394206 @default.
• W3097796199 cites W2942639165 @default.
• W3097796199 cites W2952388932 @default.
• W3097796199 cites W2954531949 @default.
• W3097796199 cites W2964199361 @default.
• W3097796199 cites W3006577210 @default.
• W3097796199 cites W4205182184 @default.
• W3097796199 cites W4240203357 @default.
• W3097796199 doi "https://doi.org/10.1088/1741-4326/abc664" @default.
• W3097796199 hasPublicationYear "2020" @default.
• W3097796199 type Work @default.
• W3097796199 sameAs 3097796199 @default.
• W3097796199 citedByCount "23" @default.
• W3097796199 countsByYear W30977961992021 @default.
• W3097796199 countsByYear W30977961992022 @default.
• W3097796199 countsByYear W30977961992023 @default.
• W3097796199 crossrefType "journal-article" @default.
• W3097796199 hasAuthorship W3097796199A5032830528 @default.
• W3097796199 hasAuthorship W3097796199A5038291431 @default.
• W3097796199 hasAuthorship W3097796199A5049937363 @default.
• W3097796199 hasAuthorship W3097796199A5059265684 @default.
• W3097796199 hasAuthorship W3097796199A5070244572 @default.
• W3097796199 hasAuthorship W3097796199A5076307875 @default.
• W3097796199 hasBestOaLocation W30977961992 @default.
• W3097796199 hasConcept C116515362 @default.
• W3097796199 hasConcept C119857082 @default.
• W3097796199 hasConcept C121332964 @default.
• W3097796199 hasConcept C154945302 @default.
• W3097796199 hasConcept C41008148 @default.
• W3097796199 hasConcept C62520636 @default.
• W3097796199 hasConcept C73555534 @default.
• W3097796199 hasConcept C82706917 @default.
• W3097796199 hasConcept C8642999 @default.
• W3097796199 hasConceptScore W3097796199C116515362 @default.
• W3097796199 hasConceptScore W3097796199C119857082 @default.
• W3097796199 hasConceptScore W3097796199C121332964 @default.
• W3097796199 hasConceptScore W3097796199C154945302 @default.
• W3097796199 hasConceptScore W3097796199C41008148 @default.
• W3097796199 hasConceptScore W3097796199C62520636 @default.
• W3097796199 hasConceptScore W3097796199C73555534 @default.
• W3097796199 hasConceptScore W3097796199C82706917 @default.
• W3097796199 hasConceptScore W3097796199C8642999 @default.
• W3097796199 hasIssue "2" @default.
• W3097796199 hasLocation W30977961991 @default.
• W3097796199 hasLocation W30977961992 @default.
• W3097796199 hasLocation W30977961993 @default.
• W3097796199 hasLocation W30977961994 @default.
• W3097796199 hasOpenAccess W3097796199 @default.
• W3097796199 hasPrimaryLocation W30977961991 @default.
• W3097796199 hasRelatedWork W2523770745 @default.
• W3097796199 hasRelatedWork W3014815208 @default.
• W3097796199 hasRelatedWork W3199608561 @default.
• W3097796199 hasRelatedWork W4210794429 @default.
• W3097796199 hasRelatedWork W4223456145 @default.
• W3097796199 hasRelatedWork W4283697347 @default.
• W3097796199 hasRelatedWork W4295309597 @default.
• W3097796199 hasRelatedWork W4295681619 @default.
• W3097796199 hasRelatedWork W4298144215 @default.
• W3097796199 hasRelatedWork W4309113015 @default.
• W3097796199 hasVolume "61" @default.
• W3097796199 isParatext "false" @default.
• W3097796199 isRetracted "false" @default.
• W3097796199 magId "3097796199" @default.

• next