FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2902809560> ?p ?o ?g. }

• W2902809560 abstract "Most of the methods that produce space weather forecasts are based on deterministic models. In order to generate a probabilistic forecast, a model needs to be run several times sampling the input parameter space, in order to generate an ensemble from which the distribution of outputs can be inferred. However, ensemble simulations are costly and often preclude the possibility of real-time forecasting. We introduce a simple and robust method to generate uncertainties from deterministic models, that does not require ensemble simulations. The method is based on the simple consideration that a probabilistic forecast needs to be both accurate and well-calibrated (reliable). We argue that these two requirements are equally important, and we introduce the Accuracy-Reliability cost function that quantitatively measures the trade-off between accuracy and reliability. We then define the optimal uncertainties as the standard deviation of the Gaussian distribution that minimizes the cost function. We demonstrate that this simple strategy, implemented here by means of a regularized deep neural network, produces accurate and well-calibrated forecasts, showing examples both on synthetic and real-world space weather data." @default.
• W2902809560 created "2018-12-11" @default.
• W2902809560 creator A5007996680 @default.
• W2902809560 creator A5026729445 @default.
• W2902809560 creator A5034817843 @default.
• W2902809560 creator A5054362485 @default.
• W2902809560 date "2019-03-01" @default.
• W2902809560 modified "2023-10-12" @default.
• W2902809560 title "On the Generation of Probabilistic Forecasts From Deterministic Models" @default.
• W2902809560 cites W1494192115 @default.
• W2902809560 cites W1567962968 @default.
• W2902809560 cites W1619432394 @default.
• W2902809560 cites W1629285470 @default.
• W2902809560 cites W1663132993 @default.
• W2902809560 cites W1781081742 @default.
• W2902809560 cites W1793241826 @default.
• W2902809560 cites W1878132393 @default.
• W2902809560 cites W1956749843 @default.
• W2902809560 cites W1968889950 @default.
• W2902809560 cites W1969404663 @default.
• W2902809560 cites W1973333099 @default.
• W2902809560 cites W1974385572 @default.
• W2902809560 cites W1976255336 @default.
• W2902809560 cites W1983156129 @default.
• W2902809560 cites W1984113680 @default.
• W2902809560 cites W1984350169 @default.
• W2902809560 cites W2018159038 @default.
• W2902809560 cites W2024228246 @default.
• W2902809560 cites W2031123958 @default.
• W2902809560 cites W2068747474 @default.
• W2902809560 cites W2069821006 @default.
• W2902809560 cites W2070164032 @default.
• W2902809560 cites W2073241381 @default.
• W2902809560 cites W2076635813 @default.
• W2902809560 cites W2082066983 @default.
• W2902809560 cites W2130715829 @default.
• W2902809560 cites W2149764047 @default.
• W2902809560 cites W2151084831 @default.
• W2902809560 cites W2153811526 @default.
• W2902809560 cites W2178242555 @default.
• W2902809560 cites W2261214516 @default.
• W2902809560 cites W2509145218 @default.
• W2902809560 cites W2523658438 @default.
• W2902809560 cites W2545487696 @default.
• W2902809560 cites W2562647817 @default.
• W2902809560 cites W2562779509 @default.
• W2902809560 cites W2597979373 @default.
• W2902809560 cites W2606395562 @default.
• W2902809560 cites W2671185684 @default.
• W2902809560 cites W2672198984 @default.
• W2902809560 cites W2735338621 @default.
• W2902809560 cites W2747780508 @default.
• W2902809560 cites W2761381454 @default.
• W2902809560 cites W2762377469 @default.
• W2902809560 cites W2765737553 @default.
• W2902809560 cites W2783585003 @default.
• W2902809560 cites W2808432498 @default.
• W2902809560 cites W2811318726 @default.
• W2902809560 cites W2963321480 @default.
• W2902809560 cites W3007874947 @default.
• W2902809560 cites W3102688741 @default.
• W2902809560 cites W4230382409 @default.
• W2902809560 cites W4241640881 @default.
• W2902809560 cites W4300600608 @default.
• W2902809560 doi "https://doi.org/10.1029/2018sw002026" @default.
• W2902809560 hasPublicationYear "2019" @default.
• W2902809560 type Work @default.
• W2902809560 sameAs 2902809560 @default.
• W2902809560 citedByCount "17" @default.
• W2902809560 countsByYear W29028095602019 @default.
• W2902809560 countsByYear W29028095602020 @default.
• W2902809560 countsByYear W29028095602021 @default.
• W2902809560 countsByYear W29028095602022 @default.
• W2902809560 countsByYear W29028095602023 @default.
• W2902809560 crossrefType "journal-article" @default.
• W2902809560 hasAuthorship W2902809560A5007996680 @default.
• W2902809560 hasAuthorship W2902809560A5026729445 @default.
• W2902809560 hasAuthorship W2902809560A5034817843 @default.
• W2902809560 hasAuthorship W2902809560A5054362485 @default.
• W2902809560 hasBestOaLocation W29028095601 @default.
• W2902809560 hasConcept C105795698 @default.
• W2902809560 hasConcept C111472728 @default.
• W2902809560 hasConcept C119857082 @default.
• W2902809560 hasConcept C119898033 @default.
• W2902809560 hasConcept C121332964 @default.
• W2902809560 hasConcept C122282355 @default.
• W2902809560 hasConcept C126255220 @default.
• W2902809560 hasConcept C138885662 @default.
• W2902809560 hasConcept C14036430 @default.
• W2902809560 hasConcept C149441793 @default.
• W2902809560 hasConcept C154945302 @default.
• W2902809560 hasConcept C163258240 @default.
• W2902809560 hasConcept C163716315 @default.
• W2902809560 hasConcept C2780586882 @default.
• W2902809560 hasConcept C33923547 @default.
• W2902809560 hasConcept C41008148 @default.
• W2902809560 hasConcept C43214815 @default.
• W2902809560 hasConcept C49937458 @default.
• W2902809560 hasConcept C62520636 @default.
• W2902809560 hasConcept C78458016 @default.

• next