Matches in SemOpenAlex for { <https://semopenalex.org/work/W4309591054> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W4309591054 abstract "Environmental sensors are crucial for monitoring weather conditions and the impacts of climate change. However, it is challenging to place sensors in a way that maximises the informativeness of their measurements, particularly in remote regions like Antarctica. Probabilistic machine learning models can suggest informative sensor placements by finding sites that maximally reduce prediction uncertainty. Gaussian process (GP) models are widely used for this purpose, but they struggle with capturing complex non-stationary behaviour and scaling to large datasets. This paper proposes using a convolutional Gaussian neural process (ConvGNP) to address these issues. A ConvGNP uses neural networks to parameterise a joint Gaussian distribution at arbitrary target locations, enabling flexibility and scalability. Using simulated surface air temperature anomaly over Antarctica as training data, the ConvGNP learns spatial and seasonal non-stationarities, outperforming a non-stationary GP baseline. In a simulated sensor placement experiment, the ConvGNP better predicts the performance boost obtained from new observations than GP baselines, leading to more informative sensor placements. We contrast our approach with physics-based sensor placement methods and propose future steps towards an operational sensor placement recommendation system. Our work could help to realise environmental digital twins that actively direct measurement sampling to improve the digital representation of reality." @default.
- W4309591054 created "2022-11-28" @default.
- W4309591054 creator A5016592089 @default.
- W4309591054 creator A5022158131 @default.
- W4309591054 creator A5027874429 @default.
- W4309591054 creator A5030713819 @default.
- W4309591054 creator A5034631090 @default.
- W4309591054 creator A5037802903 @default.
- W4309591054 creator A5041436747 @default.
- W4309591054 creator A5048696996 @default.
- W4309591054 creator A5052812417 @default.
- W4309591054 creator A5064975808 @default.
- W4309591054 creator A5072490106 @default.
- W4309591054 date "2022-11-18" @default.
- W4309591054 modified "2023-09-26" @default.
- W4309591054 title "Environmental Sensor Placement with Convolutional Gaussian Neural Processes" @default.
- W4309591054 doi "https://doi.org/10.48550/arxiv.2211.10381" @default.
- W4309591054 hasPublicationYear "2022" @default.
- W4309591054 type Work @default.
- W4309591054 citedByCount "0" @default.
- W4309591054 crossrefType "posted-content" @default.
- W4309591054 hasAuthorship W4309591054A5016592089 @default.
- W4309591054 hasAuthorship W4309591054A5022158131 @default.
- W4309591054 hasAuthorship W4309591054A5027874429 @default.
- W4309591054 hasAuthorship W4309591054A5030713819 @default.
- W4309591054 hasAuthorship W4309591054A5034631090 @default.
- W4309591054 hasAuthorship W4309591054A5037802903 @default.
- W4309591054 hasAuthorship W4309591054A5041436747 @default.
- W4309591054 hasAuthorship W4309591054A5048696996 @default.
- W4309591054 hasAuthorship W4309591054A5052812417 @default.
- W4309591054 hasAuthorship W4309591054A5064975808 @default.
- W4309591054 hasAuthorship W4309591054A5072490106 @default.
- W4309591054 hasBestOaLocation W43095910541 @default.
- W4309591054 hasConcept C105795698 @default.
- W4309591054 hasConcept C106131492 @default.
- W4309591054 hasConcept C111919701 @default.
- W4309591054 hasConcept C119857082 @default.
- W4309591054 hasConcept C121332964 @default.
- W4309591054 hasConcept C124101348 @default.
- W4309591054 hasConcept C140779682 @default.
- W4309591054 hasConcept C154945302 @default.
- W4309591054 hasConcept C163716315 @default.
- W4309591054 hasConcept C205649164 @default.
- W4309591054 hasConcept C2780598303 @default.
- W4309591054 hasConcept C31972630 @default.
- W4309591054 hasConcept C33923547 @default.
- W4309591054 hasConcept C41008148 @default.
- W4309591054 hasConcept C48044578 @default.
- W4309591054 hasConcept C49937458 @default.
- W4309591054 hasConcept C61326573 @default.
- W4309591054 hasConcept C62520636 @default.
- W4309591054 hasConcept C62649853 @default.
- W4309591054 hasConcept C739882 @default.
- W4309591054 hasConcept C77088390 @default.
- W4309591054 hasConcept C81363708 @default.
- W4309591054 hasConcept C81692654 @default.
- W4309591054 hasConcept C98045186 @default.
- W4309591054 hasConceptScore W4309591054C105795698 @default.
- W4309591054 hasConceptScore W4309591054C106131492 @default.
- W4309591054 hasConceptScore W4309591054C111919701 @default.
- W4309591054 hasConceptScore W4309591054C119857082 @default.
- W4309591054 hasConceptScore W4309591054C121332964 @default.
- W4309591054 hasConceptScore W4309591054C124101348 @default.
- W4309591054 hasConceptScore W4309591054C140779682 @default.
- W4309591054 hasConceptScore W4309591054C154945302 @default.
- W4309591054 hasConceptScore W4309591054C163716315 @default.
- W4309591054 hasConceptScore W4309591054C205649164 @default.
- W4309591054 hasConceptScore W4309591054C2780598303 @default.
- W4309591054 hasConceptScore W4309591054C31972630 @default.
- W4309591054 hasConceptScore W4309591054C33923547 @default.
- W4309591054 hasConceptScore W4309591054C41008148 @default.
- W4309591054 hasConceptScore W4309591054C48044578 @default.
- W4309591054 hasConceptScore W4309591054C49937458 @default.
- W4309591054 hasConceptScore W4309591054C61326573 @default.
- W4309591054 hasConceptScore W4309591054C62520636 @default.
- W4309591054 hasConceptScore W4309591054C62649853 @default.
- W4309591054 hasConceptScore W4309591054C739882 @default.
- W4309591054 hasConceptScore W4309591054C77088390 @default.
- W4309591054 hasConceptScore W4309591054C81363708 @default.
- W4309591054 hasConceptScore W4309591054C81692654 @default.
- W4309591054 hasConceptScore W4309591054C98045186 @default.
- W4309591054 hasLocation W43095910541 @default.
- W4309591054 hasOpenAccess W4309591054 @default.
- W4309591054 hasPrimaryLocation W43095910541 @default.
- W4309591054 hasRelatedWork W1606946149 @default.
- W4309591054 hasRelatedWork W2059173847 @default.
- W4309591054 hasRelatedWork W2063381173 @default.
- W4309591054 hasRelatedWork W2337926734 @default.
- W4309591054 hasRelatedWork W3027997911 @default.
- W4309591054 hasRelatedWork W3175643212 @default.
- W4309591054 hasRelatedWork W4285195761 @default.
- W4309591054 hasRelatedWork W4287776258 @default.
- W4309591054 hasRelatedWork W4312501200 @default.
- W4309591054 hasRelatedWork W4366224123 @default.
- W4309591054 isParatext "false" @default.
- W4309591054 isRetracted "false" @default.
- W4309591054 workType "article" @default.