English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

We developed and applied a machine-learned discretization for one-dimensional(1-D) horizontal passive scalar advection, which is an operator componentcommon to all chemical transport models (CTMs). Our learned advection schemeresembles a second-order accuracy, three-stencil numerical solver, but differsfrom a traditional solver in that coefficients for each equation term areoutput by a neural network rather than being theoretically-derived constants.We downsampled higher-resolution simulation results -- resulting in up to16$\times$ larger grid size and 64$\times$ larger timestep -- and trained ourneural network-based scheme to match the downsampled integration data. In thisway, we created an operator that is low-resolution (in time or space) but canreproduce the behavior of a high-resolution traditional solver. Our model showshigh fidelity in reproducing its training dataset (a single 10-day 1-Dsimulation) and is similarly accurate in simulations with unseen initialconditions, wind fields, and grid spacing. In many cases, our learned solver ismore accurate than a low-resolution version of the reference solver, but thelow-resolution reference solver achieves greater computational speedup(500$\times$ acceleration) over the high-resolution simulation than the learnedsolver is able to (18$\times$ acceleration). Surprisingly, our learned 1-Dscheme -- when combined with a splitting technique -- can be used to predict2-D advection, and is in some cases more stable and accurate than thelow-resolution reference solver in 2-D. Overall, our results suggest thatlearned advection operators may offer a higher-accuracy method for acceleratingCTM simulations as compared to simply running a traditional integrator at lowresolution.

Learned 1-D passive scalar advection to accelerate chemical transport modeling: a case study with GEOS-FP horizontal wind fields