FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313894939> ?p ?o ?g. }

• W4313894939 abstract "<strong class=journal-contentHeaderColor>Abstract.</strong> Under the Copernicus programme, an operational CO₂ monitoring system (CO₂MVS) is being developed and will exploit data from future satellites monitoring the amount of CO₂ within the atmosphere. Methods for estimating CO₂ emissions from significant local emitters (hotspots, i.e. cities or power plants) can greatly benefit from the availability of such satellite images, displaying atmospheric plumes of CO₂. Indeed, local emissions are strongly correlated to the size, shape and concentrations distribution of the corresponding plume, the visible consequence of the emission. The estimation of emissions from a given source can therefore directly benefit from the detection of its associated plumes in the satellite image. In this study, we address the problem of plume segmentation, i.e. the problem of finding all pixels in an image that constitute a city or power plant plume. This represents a significant challenge, as the signal from CO₂ plumes induced by emissions from cities or power plants is inherently difficult to detect since it rarely exceeds values of a few ppm and is perturbed by variable regional CO₂ background signals and observation errors. To address this key issue, we investigate the potential of deep learning methods and in particular convolutional neural networks to learn to distinguish plume-specific spatial features from background or instrument features. Specifically, a U-net algorithm, an image-to-image convolutional neural network, with a state-of-the-art encoder, is used to transform an XCO₂ field into an image representing the positions of the targeted plume. Our models are trained on hourly 1 km simulated XCO₂ fields in the regions of Paris, Berlin and several German power plants. Each field represents the plume of the hotspot, the background consisting of the signal of anthropogenic and biogenic CO₂ surface fluxes near or far from the targeted source and the simulated satellite observation errors. The performance of the deep learning method is thereafter evaluated and compared with a plume segmentation technique based on thresholding in two contexts: the first where the model is trained and tested on data from the same region, and the second where the model is trained and tested in two different regions. In both contexts, our method outperforms the usual segmentation technique based on thresholding and demonstrates its ability to generalise in various cases: city plumes, power plant plumes, and areas with multiple plumes. Although less accurate than in the first context, the ability of the algorithm to extrapolate on new geographical data is conclusive, paving the way to a promising universal segmentation model, trained on a well-chosen sample of power plants and cities, and able to detect the majority of the plumes from all of them. Finally, the highly accurate results for segmentation suggest a significant potential of convolutional neural networks for estimating local emissions from spaceborne imagery." @default.
• W4313894939 created "2023-01-10" @default.
• W4313894939 date "2023-01-09" @default.
• W4313894939 modified "2023-10-17" @default.
• W4313894939 title "Comment on gmd-2022-288" @default.
• W4313894939 doi "https://doi.org/10.5194/gmd-2022-288-rc1" @default.
• W4313894939 hasPublicationYear "2023" @default.
• W4313894939 type Work @default.
• W4313894939 citedByCount "0" @default.
• W4313894939 crossrefType "peer-review" @default.
• W4313894939 hasBestOaLocation W43138949391 @default.
• W4313894939 hasConcept C127413603 @default.
• W4313894939 hasConcept C146978453 @default.
• W4313894939 hasConcept C153294291 @default.
• W4313894939 hasConcept C154945302 @default.
• W4313894939 hasConcept C160633673 @default.
• W4313894939 hasConcept C19269812 @default.
• W4313894939 hasConcept C205649164 @default.
• W4313894939 hasConcept C2775840915 @default.
• W4313894939 hasConcept C39432304 @default.
• W4313894939 hasConcept C41008148 @default.
• W4313894939 hasConcept C62649853 @default.
• W4313894939 hasConcept C65440619 @default.
• W4313894939 hasConcept C81363708 @default.
• W4313894939 hasConceptScore W4313894939C127413603 @default.
• W4313894939 hasConceptScore W4313894939C146978453 @default.
• W4313894939 hasConceptScore W4313894939C153294291 @default.
• W4313894939 hasConceptScore W4313894939C154945302 @default.
• W4313894939 hasConceptScore W4313894939C160633673 @default.
• W4313894939 hasConceptScore W4313894939C19269812 @default.
• W4313894939 hasConceptScore W4313894939C205649164 @default.
• W4313894939 hasConceptScore W4313894939C2775840915 @default.
• W4313894939 hasConceptScore W4313894939C39432304 @default.
• W4313894939 hasConceptScore W4313894939C41008148 @default.
• W4313894939 hasConceptScore W4313894939C62649853 @default.
• W4313894939 hasConceptScore W4313894939C65440619 @default.
• W4313894939 hasConceptScore W4313894939C81363708 @default.
• W4313894939 hasLocation W43138949391 @default.
• W4313894939 hasOpenAccess W4313894939 @default.
• W4313894939 hasPrimaryLocation W43138949391 @default.
• W4313894939 hasRelatedWork W1996736617 @default.
• W4313894939 hasRelatedWork W2018057559 @default.
• W4313894939 hasRelatedWork W2079713286 @default.
• W4313894939 hasRelatedWork W2091632404 @default.
• W4313894939 hasRelatedWork W2116047388 @default.
• W4313894939 hasRelatedWork W2140269005 @default.
• W4313894939 hasRelatedWork W2145240897 @default.
• W4313894939 hasRelatedWork W2172971994 @default.
• W4313894939 hasRelatedWork W2366643224 @default.
• W4313894939 hasRelatedWork W4230119631 @default.
• W4313894939 isParatext "false" @default.
• W4313894939 isRetracted "false" @default.
• W4313894939 workType "peer-review" @default.