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

Simulating physical systems is a core component of scientific computing,encompassing a wide range of physical domains and applications. Recently, therehas been a surge in data-driven methods to complement traditional numericalsimulations methods, motivated by the opportunity to reduce computational costsand/or learn new physical models leveraging access to large collections ofdata. However, the diversity of problem settings and applications has led to aplethora of approaches, each one evaluated on a different setup and withdifferent evaluation metrics. We introduce a set of benchmark problems to takea step towards unified benchmarks and evaluation protocols. We propose fourrepresentative physical systems, as well as a collection of both widely usedclassical time integrators and representative data-driven methods(kernel-based, MLP, CNN, nearest neighbors). Our framework allows evaluatingobjectively and systematically the stability, accuracy, and computationalefficiency of data-driven methods. Additionally, it is configurable to permitadjustments for accommodating other learning tasks and for establishing afoundation for future developments in machine learning for scientificcomputing.

An Extensible Benchmark Suite for Learning to Simulate Physical Systems