FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387354556> ?p ?o ?g. }

• W4387354556 abstract "Abstract Machine learning (ML) has been increasingly applied to space weather and ionosphere problems in recent years, with the goal of improving modeling and forecasting capabilities through a data‐driven modeling approach of nonlinear relationships. However, little work has been done to quantify the uncertainty of the results, lacking an indication of how confident and reliable the results of an ML system are. In this paper, we implement and analyze several uncertainty quantification approaches for an ML‐based model to forecast Vertical Total Electron Content (VTEC) 1‐day ahead and corresponding uncertainties with 95% confidence intervals (CI): (a) Super‐Ensemble of ML‐based VTEC models (SE), (b) Gradient Tree Boosting with quantile loss function (Quantile Gradient Boosting, QGB), (c) Bayesian neural network (BNN), and (d) BNN including data uncertainty (BNN + D). Techniques that consider only model parameter uncertainties (a and c) predict narrow CI and over‐optimistic results, whereas accounting for both model parameter and data uncertainties with the BNN + D approach leads to a wider CI and the most realistic uncertainties quantification of VTEC forecast. However, the BNN + D approach suffers from a high computational burden, while the QGB approach is the most computationally efficient solution with slightly less realistic uncertainties. The QGB CI are determined to a large extent from space weather indices, as revealed by the feature analysis. They exhibit variations related to daytime/nightime, solar irradiance, geomagnetic activity, and post‐sunset low‐latitude ionosphere enhancement." @default.
• W4387354556 created "2023-10-05" @default.
• W4387354556 creator A5020756386 @default.
• W4387354556 creator A5046082471 @default.
• W4387354556 creator A5073173295 @default.
• W4387354556 date "2023-10-01" @default.
• W4387354556 modified "2023-10-06" @default.
• W4387354556 title "Uncertainty Quantification for Machine Learning‐Based Ionosphere and Space Weather Forecasting: Ensemble, Bayesian Neural Network, and Quantile Gradient Boosting" @default.
• W4387354556 cites W1678356000 @default.
• W4387354556 cites W1955857676 @default.
• W4387354556 cites W1988790447 @default.
• W4387354556 cites W1998820031 @default.
• W4387354556 cites W2011301426 @default.
• W4387354556 cites W2026050950 @default.
• W4387354556 cites W2044963167 @default.
• W4387354556 cites W2104515329 @default.
• W4387354556 cites W2563003513 @default.
• W4387354556 cites W2598637447 @default.
• W4387354556 cites W2624134272 @default.
• W4387354556 cites W2789930424 @default.
• W4387354556 cites W2901229001 @default.
• W4387354556 cites W2911466664 @default.
• W4387354556 cites W2911964244 @default.
• W4387354556 cites W2966873897 @default.
• W4387354556 cites W3008629551 @default.
• W4387354556 cites W3102100346 @default.
• W4387354556 cites W3102476541 @default.
• W4387354556 cites W3104446864 @default.
• W4387354556 cites W3112737963 @default.
• W4387354556 cites W3134774296 @default.
• W4387354556 cites W3150635270 @default.
• W4387354556 cites W3164764104 @default.
• W4387354556 cites W4206084455 @default.
• W4387354556 cites W4206604443 @default.
• W4387354556 cites W4221159243 @default.
• W4387354556 cites W4224228550 @default.
• W4387354556 cites W4225377256 @default.
• W4387354556 cites W4238084594 @default.
• W4387354556 cites W4241996101 @default.
• W4387354556 cites W4281647636 @default.
• W4387354556 cites W4287148124 @default.
• W4387354556 cites W4295780210 @default.
• W4387354556 cites W4296466758 @default.
• W4387354556 cites W4304779548 @default.
• W4387354556 cites W4366960361 @default.
• W4387354556 doi "https://doi.org/10.1029/2023sw003483" @default.
• W4387354556 hasPublicationYear "2023" @default.
• W4387354556 type Work @default.
• W4387354556 citedByCount "0" @default.
• W4387354556 crossrefType "journal-article" @default.
• W4387354556 hasAuthorship W4387354556A5020756386 @default.
• W4387354556 hasAuthorship W4387354556A5046082471 @default.
• W4387354556 hasAuthorship W4387354556A5073173295 @default.
• W4387354556 hasBestOaLocation W43873545561 @default.
• W4387354556 hasConcept C118671147 @default.
• W4387354556 hasConcept C119857082 @default.
• W4387354556 hasConcept C121332964 @default.
• W4387354556 hasConcept C149782125 @default.
• W4387354556 hasConcept C151325931 @default.
• W4387354556 hasConcept C153294291 @default.
• W4387354556 hasConcept C154945302 @default.
• W4387354556 hasConcept C169258074 @default.
• W4387354556 hasConcept C24552861 @default.
• W4387354556 hasConcept C33923547 @default.
• W4387354556 hasConcept C41008148 @default.
• W4387354556 hasConcept C46686674 @default.
• W4387354556 hasConcept C50644808 @default.
• W4387354556 hasConcept C70153297 @default.
• W4387354556 hasConceptScore W4387354556C118671147 @default.
• W4387354556 hasConceptScore W4387354556C119857082 @default.
• W4387354556 hasConceptScore W4387354556C121332964 @default.
• W4387354556 hasConceptScore W4387354556C149782125 @default.
• W4387354556 hasConceptScore W4387354556C151325931 @default.
• W4387354556 hasConceptScore W4387354556C153294291 @default.
• W4387354556 hasConceptScore W4387354556C154945302 @default.
• W4387354556 hasConceptScore W4387354556C169258074 @default.
• W4387354556 hasConceptScore W4387354556C24552861 @default.
• W4387354556 hasConceptScore W4387354556C33923547 @default.
• W4387354556 hasConceptScore W4387354556C41008148 @default.
• W4387354556 hasConceptScore W4387354556C46686674 @default.
• W4387354556 hasConceptScore W4387354556C50644808 @default.
• W4387354556 hasConceptScore W4387354556C70153297 @default.
• W4387354556 hasFunder F4320320875 @default.
• W4387354556 hasIssue "10" @default.
• W4387354556 hasLocation W43873545561 @default.
• W4387354556 hasOpenAccess W4387354556 @default.
• W4387354556 hasPrimaryLocation W43873545561 @default.
• W4387354556 hasRelatedWork W1968832299 @default.
• W4387354556 hasRelatedWork W1979006554 @default.
• W4387354556 hasRelatedWork W2766514146 @default.
• W4387354556 hasRelatedWork W4283312409 @default.
• W4387354556 hasRelatedWork W4296079469 @default.
• W4387354556 hasRelatedWork W4312821854 @default.
• W4387354556 hasRelatedWork W4313488044 @default.
• W4387354556 hasRelatedWork W4379536929 @default.
• W4387354556 hasRelatedWork W4385447970 @default.
• W4387354556 hasRelatedWork W1994492082 @default.
• W4387354556 hasVolume "21" @default.
• W4387354556 isParatext "false" @default.
• W4387354556 isRetracted "false" @default.

• next