Matches in SemOpenAlex for { <https://semopenalex.org/work/W3090474448> ?p ?o ?g. }
- W3090474448 abstract "Atmospheric chemistry models—components in models that simulate air pollution and climate change—are computationally expensive. Previous studies have shown that machine-learned atmospheric chemical solvers can be orders of magnitude faster than traditional integration methods but tend to suffer from numerical instability. Here, we present a modeling framework that reduces error accumulation compared to previous work while maintaining computational efficiency. Our approach is novel in that it (1) uses a recurrent training regime that results in extended (>1 week) simulations without exponential error accumulation and (2) can reversibly compress the number of modeled chemical species by >80% without further decreasing accuracy. We observe an ~260× speedup (~1,900× with specialized hardware) compared to the traditional solver. We use random initial conditions in training to promote general applicability across a wide range of atmospheric conditions. For ozone (concentrations ranging from 0–70 ppb), our model predictions over a 24-hr simulation period match those of the reference solver with median error of 2.7 and <19 ppb error across 99% of simulations initialized with random noise. Error can be significantly higher in the remaining 1% of simulations, which include extreme concentration fluctuations simulated by the reference model. Results are similar for total particulate matter (median error of 16 and <32 μg/m3 across 99% of simulations with concentrations ranging from 0–150 μg/m3). Finally, we discuss practical implications of our modeling framework and next steps for improvements. The machine learning models described here are not yet replacements for traditional chemistry solvers but represent a step toward that goal." @default.
- W3090474448 created "2020-10-08" @default.
- W3090474448 creator A5001173179 @default.
- W3090474448 creator A5011740304 @default.
- W3090474448 creator A5037036749 @default.
- W3090474448 creator A5050225100 @default.
- W3090474448 creator A5083450863 @default.
- W3090474448 date "2020-12-02" @default.
- W3090474448 modified "2023-10-04" @default.
- W3090474448 title "Toward Stable, General Machine‐Learned Models of the Atmospheric Chemical System" @default.
- W3090474448 cites W1965756721 @default.
- W3090474448 cites W1988326277 @default.
- W3090474448 cites W1995341919 @default.
- W3090474448 cites W2004667916 @default.
- W3090474448 cites W2008016796 @default.
- W3090474448 cites W2012965359 @default.
- W3090474448 cites W2019817940 @default.
- W3090474448 cites W2044661755 @default.
- W3090474448 cites W2064675550 @default.
- W3090474448 cites W2067318157 @default.
- W3090474448 cites W2068241213 @default.
- W3090474448 cites W2072692927 @default.
- W3090474448 cites W2076063813 @default.
- W3090474448 cites W2081968951 @default.
- W3090474448 cites W2095132769 @default.
- W3090474448 cites W2100262118 @default.
- W3090474448 cites W2111907830 @default.
- W3090474448 cites W2122538988 @default.
- W3090474448 cites W2151997316 @default.
- W3090474448 cites W2153056810 @default.
- W3090474448 cites W2157952317 @default.
- W3090474448 cites W2166266517 @default.
- W3090474448 cites W2167820090 @default.
- W3090474448 cites W2169979652 @default.
- W3090474448 cites W2337507902 @default.
- W3090474448 cites W2471774534 @default.
- W3090474448 cites W2513751996 @default.
- W3090474448 cites W2537339873 @default.
- W3090474448 cites W2595507424 @default.
- W3090474448 cites W2605896263 @default.
- W3090474448 cites W2617759587 @default.
- W3090474448 cites W2777417212 @default.
- W3090474448 cites W2801851968 @default.
- W3090474448 cites W2808400960 @default.
- W3090474448 cites W2891039272 @default.
- W3090474448 cites W2895144725 @default.
- W3090474448 cites W2910249264 @default.
- W3090474448 cites W2913323966 @default.
- W3090474448 cites W2948567396 @default.
- W3090474448 cites W2964128214 @default.
- W3090474448 cites W2965752768 @default.
- W3090474448 cites W2966419255 @default.
- W3090474448 cites W2974527409 @default.
- W3090474448 cites W2981906852 @default.
- W3090474448 doi "https://doi.org/10.1029/2020jd032759" @default.
- W3090474448 hasPublicationYear "2020" @default.
- W3090474448 type Work @default.
- W3090474448 sameAs 3090474448 @default.
- W3090474448 citedByCount "22" @default.
- W3090474448 countsByYear W30904744482021 @default.
- W3090474448 countsByYear W30904744482022 @default.
- W3090474448 countsByYear W30904744482023 @default.
- W3090474448 crossrefType "journal-article" @default.
- W3090474448 hasAuthorship W3090474448A5001173179 @default.
- W3090474448 hasAuthorship W3090474448A5011740304 @default.
- W3090474448 hasAuthorship W3090474448A5037036749 @default.
- W3090474448 hasAuthorship W3090474448A5050225100 @default.
- W3090474448 hasAuthorship W3090474448A5083450863 @default.
- W3090474448 hasBestOaLocation W30904744482 @default.
- W3090474448 hasConcept C11413529 @default.
- W3090474448 hasConcept C115051666 @default.
- W3090474448 hasConcept C115961682 @default.
- W3090474448 hasConcept C121332964 @default.
- W3090474448 hasConcept C123614077 @default.
- W3090474448 hasConcept C127413603 @default.
- W3090474448 hasConcept C134306372 @default.
- W3090474448 hasConcept C146978453 @default.
- W3090474448 hasConcept C151376022 @default.
- W3090474448 hasConcept C153294291 @default.
- W3090474448 hasConcept C154945302 @default.
- W3090474448 hasConcept C173608175 @default.
- W3090474448 hasConcept C199360897 @default.
- W3090474448 hasConcept C204323151 @default.
- W3090474448 hasConcept C2778770139 @default.
- W3090474448 hasConcept C33923547 @default.
- W3090474448 hasConcept C41008148 @default.
- W3090474448 hasConcept C49999975 @default.
- W3090474448 hasConcept C508106653 @default.
- W3090474448 hasConcept C68339613 @default.
- W3090474448 hasConcept C76155785 @default.
- W3090474448 hasConcept C99498987 @default.
- W3090474448 hasConceptScore W3090474448C11413529 @default.
- W3090474448 hasConceptScore W3090474448C115051666 @default.
- W3090474448 hasConceptScore W3090474448C115961682 @default.
- W3090474448 hasConceptScore W3090474448C121332964 @default.
- W3090474448 hasConceptScore W3090474448C123614077 @default.
- W3090474448 hasConceptScore W3090474448C127413603 @default.
- W3090474448 hasConceptScore W3090474448C134306372 @default.
- W3090474448 hasConceptScore W3090474448C146978453 @default.
- W3090474448 hasConceptScore W3090474448C151376022 @default.