FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4293731781> ?p ?o ?g. }

• W4293731781 abstract "Abstract Satellite low-Earth-orbiting (LEO) and geostationary (GEO) imager estimates of cloud-top pressure (CTP) have many applications in both operations and in studying long-term variations in cloud properties. Recently, machine learning (ML) approaches have shown improvement upon physically based algorithms. However, ML approaches, and especially neural networks, can suffer from a lack of interpretability, making it difficult to understand what information is most useful for accurate predictions of cloud properties. We trained several neural networks to estimate CTP from the infrared channels of the Visible Infrared Imaging Radiometer Suite (VIIRS) and the Advanced Baseline Imager (ABI). The main focus of this work is assessing the relative importance of each instrument’s infrared channels in neural networks trained to estimate CTP. We use several ML explainability methods to offer different perspectives on feature importance. These methods show many differences in the relative feature importance depending on the exact method used, but most agree on a few points. Overall, the 8.4- and 8.6- μ m channels appear to be the most useful for CTP estimation on ABI and VIIRS, respectively, with other native infrared window channels and the 13.3- μ m channel playing a moderate role. Furthermore, we find that the neural networks learn relationships that may account for properties of clouds such as opacity and cloud-top phase that otherwise complicate the estimation of CTP. Significance Statement Model interpretability is an important consideration for transitioning machine learning models to operations. This work applies several explainability methods in an attempt to understand what information is most important for estimating the pressure level at the top of a cloud from satellite imagers in a neural network model. We observe much disagreement between approaches, which motivates further work in this area but find agreement on the importance of channels in the infrared window region around 8.6 and 10–12 μ m, informing future cloud property algorithm development. We also find some evidence suggesting that these neural networks are able to learn physically relevant variability in radiation measurements related to key cloud properties." @default.
• W4293731781 created "2022-08-31" @default.
• W4293731781 creator A5007322799 @default.
• W4293731781 creator A5018502490 @default.
• W4293731781 creator A5085447919 @default.
• W4293731781 date "2022-10-01" @default.
• W4293731781 modified "2023-10-16" @default.
• W4293731781 title "Probing the Explainability of Neural Network Cloud-Top Pressure Models for LEO and GEO Imagers" @default.
• W4293731781 cites W1787224781 @default.
• W4293731781 cites W1964107755 @default.
• W4293731781 cites W1968151054 @default.
• W4293731781 cites W1998025025 @default.
• W4293731781 cites W2002869399 @default.
• W4293731781 cites W2011301426 @default.
• W4293731781 cites W2016304835 @default.
• W4293731781 cites W2027210298 @default.
• W4293731781 cites W2035939669 @default.
• W4293731781 cites W2038518524 @default.
• W4293731781 cites W2057657175 @default.
• W4293731781 cites W2060172488 @default.
• W4293731781 cites W2066124661 @default.
• W4293731781 cites W2080278412 @default.
• W4293731781 cites W2084032127 @default.
• W4293731781 cites W2089178461 @default.
• W4293731781 cites W2127332422 @default.
• W4293731781 cites W2144991971 @default.
• W4293731781 cites W2153120705 @default.
• W4293731781 cites W2397796799 @default.
• W4293731781 cites W2417026208 @default.
• W4293731781 cites W2494302106 @default.
• W4293731781 cites W2564620832 @default.
• W4293731781 cites W2570994043 @default.
• W4293731781 cites W2787809105 @default.
• W4293731781 cites W2795114264 @default.
• W4293731781 cites W2796293253 @default.
• W4293731781 cites W2799985555 @default.
• W4293731781 cites W2810041204 @default.
• W4293731781 cites W2949330945 @default.
• W4293731781 cites W2950210192 @default.
• W4293731781 cites W2956076828 @default.
• W4293731781 cites W2969309273 @default.
• W4293731781 cites W2973136764 @default.
• W4293731781 cites W3006566055 @default.
• W4293731781 cites W3093480534 @default.
• W4293731781 cites W3097483010 @default.
• W4293731781 cites W3099878876 @default.
• W4293731781 cites W3103145119 @default.
• W4293731781 cites W3104675167 @default.
• W4293731781 cites W3118495285 @default.
• W4293731781 cites W3157220546 @default.
• W4293731781 cites W4234314512 @default.
• W4293731781 doi "https://doi.org/10.1175/aies-d-21-0001.1" @default.
• W4293731781 hasPublicationYear "2022" @default.
• W4293731781 type Work @default.
• W4293731781 citedByCount "0" @default.
• W4293731781 crossrefType "journal-article" @default.
• W4293731781 hasAuthorship W4293731781A5007322799 @default.
• W4293731781 hasAuthorship W4293731781A5018502490 @default.
• W4293731781 hasAuthorship W4293731781A5085447919 @default.
• W4293731781 hasBestOaLocation W42937317811 @default.
• W4293731781 hasConcept C108583219 @default.
• W4293731781 hasConcept C111919701 @default.
• W4293731781 hasConcept C119857082 @default.
• W4293731781 hasConcept C127313418 @default.
• W4293731781 hasConcept C127413603 @default.
• W4293731781 hasConcept C138885662 @default.
• W4293731781 hasConcept C146978453 @default.
• W4293731781 hasConcept C154945302 @default.
• W4293731781 hasConcept C16405173 @default.
• W4293731781 hasConcept C19269812 @default.
• W4293731781 hasConcept C2776401178 @default.
• W4293731781 hasConcept C2777701342 @default.
• W4293731781 hasConcept C2781067378 @default.
• W4293731781 hasConcept C41008148 @default.
• W4293731781 hasConcept C41895202 @default.
• W4293731781 hasConcept C50644808 @default.
• W4293731781 hasConcept C62649853 @default.
• W4293731781 hasConcept C79974875 @default.
• W4293731781 hasConcept C81363708 @default.
• W4293731781 hasConceptScore W4293731781C108583219 @default.
• W4293731781 hasConceptScore W4293731781C111919701 @default.
• W4293731781 hasConceptScore W4293731781C119857082 @default.
• W4293731781 hasConceptScore W4293731781C127313418 @default.
• W4293731781 hasConceptScore W4293731781C127413603 @default.
• W4293731781 hasConceptScore W4293731781C138885662 @default.
• W4293731781 hasConceptScore W4293731781C146978453 @default.
• W4293731781 hasConceptScore W4293731781C154945302 @default.
• W4293731781 hasConceptScore W4293731781C16405173 @default.
• W4293731781 hasConceptScore W4293731781C19269812 @default.
• W4293731781 hasConceptScore W4293731781C2776401178 @default.
• W4293731781 hasConceptScore W4293731781C2777701342 @default.
• W4293731781 hasConceptScore W4293731781C2781067378 @default.
• W4293731781 hasConceptScore W4293731781C41008148 @default.
• W4293731781 hasConceptScore W4293731781C41895202 @default.
• W4293731781 hasConceptScore W4293731781C50644808 @default.
• W4293731781 hasConceptScore W4293731781C62649853 @default.
• W4293731781 hasConceptScore W4293731781C79974875 @default.
• W4293731781 hasConceptScore W4293731781C81363708 @default.
• W4293731781 hasFunder F4320332181 @default.
• W4293731781 hasIssue "4" @default.

• next