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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We propose GNN-Surrogate, a graph neural network-based surrogate model toexplore the parameter space of ocean climate simulations. Parameter spaceexploration is important for domain scientists to understand the influence ofinput parameters (e.g., wind stress) on the simulation output (e.g.,temperature). The exploration requires scientists to exhaust the complicatedparameter space by running a batch of computationally expensive simulations.Our approach improves the efficiency of parameter space exploration with asurrogate model that predicts the simulation outputs accurately andefficiently. Specifically, GNN-Surrogate predicts the output field with givensimulation parameters so scientists can explore the simulation parameter spacewith visualizations from user-specified visual mappings. Moreover, ourgraph-based techniques are designed for unstructured meshes, making theexploration of simulation outputs on irregular grids efficient. For efficienttraining, we generate hierarchical graphs and use adaptive resolutions. We givequantitative and qualitative evaluations on the MPAS-Ocean simulation todemonstrate the effectiveness and efficiency of GNN-Surrogate. Source code ispublicly available at https://github.com/trainsn/GNN-Surrogate.

GNN-Surrogate: A Hierarchical and Adaptive Graph Neural Network for Parameter Space Exploration of Unstructured-Mesh Ocean Simulations