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

Analysis of compressible turbulent flows is essential for applicationsrelated to propulsion, energy generation, and the environment. Here, we presentBLASTNet 2.0, a 2.2 TB network-of-datasets containing 744 full-domain samplesfrom 34 high-fidelity direct numerical simulations, which addresses the currentlimited availability of 3D high-fidelity reacting and non-reacting compressibleturbulent flow simulation data. With this data, we benchmark a total of 49variations of five deep learning approaches for 3D super-resolution - which canbe applied for improving scientific imaging, simulations, turbulence models, aswell as in computer vision applications. We perform neural scaling analysis onthese models to examine the performance of different machine learning (ML)approaches, including two scientific ML techniques. We demonstrate that (i)predictive performance can scale with model size and cost, (ii) architecturematters significantly, especially for smaller models, and (iii) the benefits ofphysics-based losses can persist with increasing model size. The outcomes ofthis benchmark study are anticipated to offer insights that can aid the designof 3D super-resolution models, especially for turbulence models, while thisdata is expected to foster ML methods for a broad range of flow physicsapplications. This data is publicly available with download links and browsingtools consolidated at https://blastnet.github.io.

Turbulence in Focus: Benchmarking Scaling Behavior of 3D Volumetric Super-Resolution with BLASTNet 2.0 Data