Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384616622> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W4384616622 endingPage "105412" @default.
- W4384616622 startingPage "105412" @default.
- W4384616622 abstract "Spatial nonstationarity, the location variance of features' statistical distributions, is ubiquitous in many natural settings. For example, in geological reservoirs rock matrix porosity varies vertically due to geomechanical compaction trends, in mineral deposits grades vary due to sedimentation and concentration processes, in hydrology rainfall varies due to the atmosphere and topography interactions, and in metallurgy crystalline structures vary due to differential cooling. Conventional geostatistical modeling workflows rely on the assumption of stationarity to be able to model spatial features for the geostatistical inference. Nevertheless, this is often not a realistic assumption when dealing with nonstationary spatial data and this has motivated a variety of nonstationary spatial modeling workflows such as trend and residual decomposition, cosimulation with secondary features, and spatial segmentation and independent modeling over stationary subdomains. The advent of deep learning technologies has enabled new workflows for modeling spatial relationships. However, there is a paucity of demonstrated best practice and general guidance on mitigation of spatial nonstationarity with deep learning in the geospatial context. We demonstrate the impact of two common types of geostatistical spatial nonstationarity on deep learning model prediction performance and propose the mitigation of such impacts using self-attention (vision transformer) models. We demonstrate the utility of vision transformers for the mitigation of nonstationarity with relative errors as low as 10%, exceeding the performance of alternative deep learning methods such as convolutional neural networks. We establish best practice by demonstrating the ability of self-attention networks for modeling large-scale spatial relationships in the presence of commonly observed geospatial nonstationarity." @default.
- W4384616622 created "2023-07-18" @default.
- W4384616622 creator A5018870906 @default.
- W4384616622 creator A5023112770 @default.
- W4384616622 creator A5061964004 @default.
- W4384616622 creator A5078622567 @default.
- W4384616622 date "2023-09-01" @default.
- W4384616622 modified "2023-09-27" @default.
- W4384616622 title "Mitigation of spatial nonstationarity with vision transformers" @default.
- W4384616622 cites W1989752917 @default.
- W4384616622 cites W1994020749 @default.
- W4384616622 cites W1994422549 @default.
- W4384616622 cites W2001211772 @default.
- W4384616622 cites W2015883816 @default.
- W4384616622 cites W2018509690 @default.
- W4384616622 cites W2114193021 @default.
- W4384616622 cites W2154788232 @default.
- W4384616622 cites W2165698076 @default.
- W4384616622 cites W2606759614 @default.
- W4384616622 cites W2799858096 @default.
- W4384616622 cites W2923222994 @default.
- W4384616622 cites W2948893225 @default.
- W4384616622 cites W2954996726 @default.
- W4384616622 cites W3043128058 @default.
- W4384616622 cites W3147262955 @default.
- W4384616622 cites W4224033008 @default.
- W4384616622 cites W1986054014 @default.
- W4384616622 doi "https://doi.org/10.1016/j.cageo.2023.105412" @default.
- W4384616622 hasPublicationYear "2023" @default.
- W4384616622 type Work @default.
- W4384616622 citedByCount "0" @default.
- W4384616622 crossrefType "journal-article" @default.
- W4384616622 hasAuthorship W4384616622A5018870906 @default.
- W4384616622 hasAuthorship W4384616622A5023112770 @default.
- W4384616622 hasAuthorship W4384616622A5061964004 @default.
- W4384616622 hasAuthorship W4384616622A5078622567 @default.
- W4384616622 hasBestOaLocation W43846166222 @default.
- W4384616622 hasConcept C105795698 @default.
- W4384616622 hasConcept C108583219 @default.
- W4384616622 hasConcept C119857082 @default.
- W4384616622 hasConcept C124101348 @default.
- W4384616622 hasConcept C125572338 @default.
- W4384616622 hasConcept C127313418 @default.
- W4384616622 hasConcept C154881674 @default.
- W4384616622 hasConcept C154945302 @default.
- W4384616622 hasConcept C158709400 @default.
- W4384616622 hasConcept C159620131 @default.
- W4384616622 hasConcept C177212765 @default.
- W4384616622 hasConcept C18903297 @default.
- W4384616622 hasConcept C2776214188 @default.
- W4384616622 hasConcept C33923547 @default.
- W4384616622 hasConcept C41008148 @default.
- W4384616622 hasConcept C62649853 @default.
- W4384616622 hasConcept C77088390 @default.
- W4384616622 hasConcept C81692654 @default.
- W4384616622 hasConcept C86803240 @default.
- W4384616622 hasConcept C94747663 @default.
- W4384616622 hasConcept C9770341 @default.
- W4384616622 hasConceptScore W4384616622C105795698 @default.
- W4384616622 hasConceptScore W4384616622C108583219 @default.
- W4384616622 hasConceptScore W4384616622C119857082 @default.
- W4384616622 hasConceptScore W4384616622C124101348 @default.
- W4384616622 hasConceptScore W4384616622C125572338 @default.
- W4384616622 hasConceptScore W4384616622C127313418 @default.
- W4384616622 hasConceptScore W4384616622C154881674 @default.
- W4384616622 hasConceptScore W4384616622C154945302 @default.
- W4384616622 hasConceptScore W4384616622C158709400 @default.
- W4384616622 hasConceptScore W4384616622C159620131 @default.
- W4384616622 hasConceptScore W4384616622C177212765 @default.
- W4384616622 hasConceptScore W4384616622C18903297 @default.
- W4384616622 hasConceptScore W4384616622C2776214188 @default.
- W4384616622 hasConceptScore W4384616622C33923547 @default.
- W4384616622 hasConceptScore W4384616622C41008148 @default.
- W4384616622 hasConceptScore W4384616622C62649853 @default.
- W4384616622 hasConceptScore W4384616622C77088390 @default.
- W4384616622 hasConceptScore W4384616622C81692654 @default.
- W4384616622 hasConceptScore W4384616622C86803240 @default.
- W4384616622 hasConceptScore W4384616622C94747663 @default.
- W4384616622 hasConceptScore W4384616622C9770341 @default.
- W4384616622 hasFunder F4320310620 @default.
- W4384616622 hasLocation W43846166221 @default.
- W4384616622 hasLocation W43846166222 @default.
- W4384616622 hasOpenAccess W4384616622 @default.
- W4384616622 hasPrimaryLocation W43846166221 @default.
- W4384616622 hasRelatedWork W1968850938 @default.
- W4384616622 hasRelatedWork W1979286891 @default.
- W4384616622 hasRelatedWork W2125271424 @default.
- W4384616622 hasRelatedWork W2373611444 @default.
- W4384616622 hasRelatedWork W2773198424 @default.
- W4384616622 hasRelatedWork W2912352680 @default.
- W4384616622 hasRelatedWork W2941745888 @default.
- W4384616622 hasRelatedWork W2978933927 @default.
- W4384616622 hasRelatedWork W3133739838 @default.
- W4384616622 hasRelatedWork W3149487280 @default.
- W4384616622 hasVolume "178" @default.
- W4384616622 isParatext "false" @default.
- W4384616622 isRetracted "false" @default.
- W4384616622 workType "article" @default.