Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288952136> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W4288952136 abstract "This study develops a neural network-based approach for emulating high-resolution modeled precipitation data with comparable statistical properties but at greatly reduced computational cost. The key idea is to use combination of low- and high- resolution simulations to train a neural network to map from the former to the latter. Specifically, we define two types of CNNs, one that stacks variables directly and one that encodes each variable before stacking, and we train each CNN type both with a conventional loss function, such as mean square error (MSE), and with a conditional generative adversarial network (CGAN), for a total of four CNN variants. We compare the four new CNN-derived high-resolution precipitation results with precipitation generated from original high resolution simulations, a bilinear interpolater and the state-of-the-art CNN-based super-resolution (SR) technique. Results show that the SR technique produces results similar to those of the bilinear interpolator with smoother spatial and temporal distributions and smaller data variabilities and extremes than the original high resolution simulations. While the new CNNs trained by MSE generate better results over some regions than the interpolator and SR technique do, their predictions are still not as close as the original high resolution simulations. The CNNs trained by CGAN generate more realistic and physically reasonable results, better capturing not only data variability in time and space but also extremes such as intense and long-lasting storms. The new proposed CNN-based downscaling approach can downscale precipitation from 50~km to 12~km in 14~min for 30~years once the network is trained (training takes 4~hours using 1~GPU), while the conventional dynamical downscaling would take 1~month using 600 CPU cores to generate simulations at the resolution of 12~km over contiguous United States." @default.
- W4288952136 created "2022-07-31" @default.
- W4288952136 creator A5001186999 @default.
- W4288952136 creator A5032231503 @default.
- W4288952136 creator A5036839849 @default.
- W4288952136 creator A5062572385 @default.
- W4288952136 creator A5068373159 @default.
- W4288952136 creator A5089924647 @default.
- W4288952136 date "2021-01-17" @default.
- W4288952136 modified "2023-09-23" @default.
- W4288952136 title "Fast and accurate learned multiresolution dynamical downscaling for precipitation" @default.
- W4288952136 doi "https://doi.org/10.48550/arxiv.2101.06813" @default.
- W4288952136 hasPublicationYear "2021" @default.
- W4288952136 type Work @default.
- W4288952136 citedByCount "0" @default.
- W4288952136 crossrefType "posted-content" @default.
- W4288952136 hasAuthorship W4288952136A5001186999 @default.
- W4288952136 hasAuthorship W4288952136A5032231503 @default.
- W4288952136 hasAuthorship W4288952136A5036839849 @default.
- W4288952136 hasAuthorship W4288952136A5062572385 @default.
- W4288952136 hasAuthorship W4288952136A5068373159 @default.
- W4288952136 hasAuthorship W4288952136A5089924647 @default.
- W4288952136 hasBestOaLocation W42889521361 @default.
- W4288952136 hasConcept C105795698 @default.
- W4288952136 hasConcept C107054158 @default.
- W4288952136 hasConcept C11413529 @default.
- W4288952136 hasConcept C121332964 @default.
- W4288952136 hasConcept C138268822 @default.
- W4288952136 hasConcept C139945424 @default.
- W4288952136 hasConcept C153180895 @default.
- W4288952136 hasConcept C153294291 @default.
- W4288952136 hasConcept C154945302 @default.
- W4288952136 hasConcept C205203396 @default.
- W4288952136 hasConcept C205372480 @default.
- W4288952136 hasConcept C31972630 @default.
- W4288952136 hasConcept C33923547 @default.
- W4288952136 hasConcept C41008148 @default.
- W4288952136 hasConcept C41156917 @default.
- W4288952136 hasConcept C50644808 @default.
- W4288952136 hasConcept C81363708 @default.
- W4288952136 hasConceptScore W4288952136C105795698 @default.
- W4288952136 hasConceptScore W4288952136C107054158 @default.
- W4288952136 hasConceptScore W4288952136C11413529 @default.
- W4288952136 hasConceptScore W4288952136C121332964 @default.
- W4288952136 hasConceptScore W4288952136C138268822 @default.
- W4288952136 hasConceptScore W4288952136C139945424 @default.
- W4288952136 hasConceptScore W4288952136C153180895 @default.
- W4288952136 hasConceptScore W4288952136C153294291 @default.
- W4288952136 hasConceptScore W4288952136C154945302 @default.
- W4288952136 hasConceptScore W4288952136C205203396 @default.
- W4288952136 hasConceptScore W4288952136C205372480 @default.
- W4288952136 hasConceptScore W4288952136C31972630 @default.
- W4288952136 hasConceptScore W4288952136C33923547 @default.
- W4288952136 hasConceptScore W4288952136C41008148 @default.
- W4288952136 hasConceptScore W4288952136C41156917 @default.
- W4288952136 hasConceptScore W4288952136C50644808 @default.
- W4288952136 hasConceptScore W4288952136C81363708 @default.
- W4288952136 hasLocation W42889521361 @default.
- W4288952136 hasLocation W42889521362 @default.
- W4288952136 hasOpenAccess W4288952136 @default.
- W4288952136 hasPrimaryLocation W42889521361 @default.
- W4288952136 hasRelatedWork W10710906 @default.
- W4288952136 hasRelatedWork W12336802 @default.
- W4288952136 hasRelatedWork W13540765 @default.
- W4288952136 hasRelatedWork W2433769 @default.
- W4288952136 hasRelatedWork W4136762 @default.
- W4288952136 hasRelatedWork W7682646 @default.
- W4288952136 hasRelatedWork W819137 @default.
- W4288952136 hasRelatedWork W8208422 @default.
- W4288952136 hasRelatedWork W9190101 @default.
- W4288952136 hasRelatedWork W9465030 @default.
- W4288952136 isParatext "false" @default.
- W4288952136 isRetracted "false" @default.
- W4288952136 workType "article" @default.