Matches in SemOpenAlex for { <https://semopenalex.org/work/W3156930162> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W3156930162 endingPage "104778" @default.
- W3156930162 startingPage "104778" @default.
- W3156930162 abstract "Sedimentary petrology is the basis for most mineral and textural identification in sandstones. Automating mineralogical interpretation of an entire thin section image has many practical applications, including improved geological understanding, input of spatial distribution of mineralogy and grain size for petrophysical evaluations, and integration with 3D imaging modalities (micro-CT, nano-CT). We investigate the application of Convolutional Neural Network (CNN) based supervised semantic segmentation methods for predicting pixel-scale mineralogy using 2D RGB images of sandstones acquired by transmission light microscopy. Models were trained to interpret a simple binary pore-mineral (grain) segmentation and a 10-class segmentation (porosity, quartz, feldspar, rock fragments, carbonate grains, opaque grains, quartz cement, carbonate cement, clay cement, and hydrocarbons filling pores). For the 2-class classification framework to distinguish between pores and minerals, most models lead to satisfactory results with acceptable accuracy. For the 10-class classification framework, models trained with Deeplab V3+ Resnet-18 network yield more continuous results compared to those based on VGG networks. We conclude that the effectiveness of the models, in predicting a petrology class in a thin section, strongly correlates with the amount of labeled data available to train the model to interpret the class in question. Semantic segmentation models, based on CNNs, can produce encouraging results for a 10-class petrological classification framework of an entire thin section image and thus provide a complete scene understanding which is difficult to produce manually." @default.
- W3156930162 created "2021-04-26" @default.
- W3156930162 creator A5009926788 @default.
- W3156930162 creator A5014119350 @default.
- W3156930162 creator A5055768448 @default.
- W3156930162 creator A5075447757 @default.
- W3156930162 date "2021-07-01" @default.
- W3156930162 modified "2023-10-13" @default.
- W3156930162 title "Application of deep learning for semantic segmentation of sandstone thin sections" @default.
- W3156930162 cites W1498436455 @default.
- W3156930162 cites W2031012492 @default.
- W3156930162 cites W2038899946 @default.
- W3156930162 cites W2062467613 @default.
- W3156930162 cites W2068671195 @default.
- W3156930162 cites W2069414620 @default.
- W3156930162 cites W2093565662 @default.
- W3156930162 cites W2143266529 @default.
- W3156930162 cites W2158698691 @default.
- W3156930162 cites W2199370672 @default.
- W3156930162 cites W2469938794 @default.
- W3156930162 cites W2590155560 @default.
- W3156930162 cites W2596255478 @default.
- W3156930162 cites W2725756231 @default.
- W3156930162 cites W2804860796 @default.
- W3156930162 cites W2945210856 @default.
- W3156930162 cites W2954996726 @default.
- W3156930162 cites W2963881378 @default.
- W3156930162 cites W2996476327 @default.
- W3156930162 cites W3035477383 @default.
- W3156930162 doi "https://doi.org/10.1016/j.cageo.2021.104778" @default.
- W3156930162 hasPublicationYear "2021" @default.
- W3156930162 type Work @default.
- W3156930162 sameAs 3156930162 @default.
- W3156930162 citedByCount "18" @default.
- W3156930162 countsByYear W31569301622022 @default.
- W3156930162 countsByYear W31569301622023 @default.
- W3156930162 crossrefType "journal-article" @default.
- W3156930162 hasAuthorship W3156930162A5009926788 @default.
- W3156930162 hasAuthorship W3156930162A5014119350 @default.
- W3156930162 hasAuthorship W3156930162A5055768448 @default.
- W3156930162 hasAuthorship W3156930162A5075447757 @default.
- W3156930162 hasConcept C123677613 @default.
- W3156930162 hasConcept C127313418 @default.
- W3156930162 hasConcept C151730666 @default.
- W3156930162 hasConcept C153180895 @default.
- W3156930162 hasConcept C154945302 @default.
- W3156930162 hasConcept C187320778 @default.
- W3156930162 hasConcept C199289684 @default.
- W3156930162 hasConcept C2778520076 @default.
- W3156930162 hasConcept C2779870107 @default.
- W3156930162 hasConcept C41008148 @default.
- W3156930162 hasConcept C46293882 @default.
- W3156930162 hasConcept C6648577 @default.
- W3156930162 hasConcept C81363708 @default.
- W3156930162 hasConcept C82990744 @default.
- W3156930162 hasConcept C89600930 @default.
- W3156930162 hasConceptScore W3156930162C123677613 @default.
- W3156930162 hasConceptScore W3156930162C127313418 @default.
- W3156930162 hasConceptScore W3156930162C151730666 @default.
- W3156930162 hasConceptScore W3156930162C153180895 @default.
- W3156930162 hasConceptScore W3156930162C154945302 @default.
- W3156930162 hasConceptScore W3156930162C187320778 @default.
- W3156930162 hasConceptScore W3156930162C199289684 @default.
- W3156930162 hasConceptScore W3156930162C2778520076 @default.
- W3156930162 hasConceptScore W3156930162C2779870107 @default.
- W3156930162 hasConceptScore W3156930162C41008148 @default.
- W3156930162 hasConceptScore W3156930162C46293882 @default.
- W3156930162 hasConceptScore W3156930162C6648577 @default.
- W3156930162 hasConceptScore W3156930162C81363708 @default.
- W3156930162 hasConceptScore W3156930162C82990744 @default.
- W3156930162 hasConceptScore W3156930162C89600930 @default.
- W3156930162 hasLocation W31569301621 @default.
- W3156930162 hasOpenAccess W3156930162 @default.
- W3156930162 hasPrimaryLocation W31569301621 @default.
- W3156930162 hasRelatedWork W2045681504 @default.
- W3156930162 hasRelatedWork W2330713756 @default.
- W3156930162 hasRelatedWork W2331105282 @default.
- W3156930162 hasRelatedWork W2774550181 @default.
- W3156930162 hasRelatedWork W2949228272 @default.
- W3156930162 hasRelatedWork W2954208830 @default.
- W3156930162 hasRelatedWork W3011861320 @default.
- W3156930162 hasRelatedWork W4200528772 @default.
- W3156930162 hasRelatedWork W4297680363 @default.
- W3156930162 hasRelatedWork W4386031966 @default.
- W3156930162 hasVolume "152" @default.
- W3156930162 isParatext "false" @default.
- W3156930162 isRetracted "false" @default.
- W3156930162 magId "3156930162" @default.
- W3156930162 workType "article" @default.