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

Ocean current, fluid mechanics, and many other spatio-temporal physicaldynamical systems are essential components of the universe. One keycharacteristic of such systems is that certain physics laws -- represented asordinary/partial differential equations (ODEs/PDEs) -- largely dominate thewhole process, irrespective of time or location. Physics-informed learning hasrecently emerged to learn physics for accurate prediction, but they often lacka mechanism to leverage localized spatial and temporal correlation or rely onhard-coded physics parameters. In this paper, we advocate a physics-coupledneural network model to learn parameters governing the physics of the system,and further couple the learned physics to assist the learning of recurringdynamics. A spatio-temporal physics-coupled neural network (ST-PCNN) model isproposed to achieve three goals: (1) learning the underlying physicsparameters, (2) transition of local information between spatio-temporalregions, and (3) forecasting future values for the dynamical system. Thephysics-coupled learning ensures that the proposed model can be tremendouslyimproved by using learned physics parameters, and can achieve good long-rangeforecasting (e.g., more than 30-steps). Experiments, using simulated andfield-collected ocean current data, validate that ST-PCNN outperforms existingphysics-informed models.

ST-PCNN: Spatio-Temporal Physics-Coupled Neural Networks for Dynamics Forecasting