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 present an open-source Physics Informed Neural Network environment forsimulations of transient phenomena on two-dimensional rectangular domains, withthe following features: (1) it is compatible with Google Colab which allowsautomatic execution on cloud environment; (2) it supports two dimensionaltime-dependent PDEs; (3) it provides simple interface for definition of theresidual loss, boundary condition and initial loss, together with theirweights; (4) it support Neumann and Dirichlet boundary conditions; (5) itallows for customizing the number of layers and neurons per layer, as well asfor arbitrary activation function; (6) the learning rate and number of epochsare available as parameters; (7) it automatically differentiates PINN withrespect to spatial and temporal variables; (8) it provides routines forplotting the convergence (with running average), initial conditions learnt, 2Dand 3D snapshots from the simulation and movies (9) it includes a library ofproblems: (a) non-stationary heat transfer; (b) wave equation modeling atsunami; (c) atmospheric simulations including thermal inversion; (d) tumorgrowth simulations.

Physics Informed Neural Network Code for 2D Transient Problems (PINN-2DT) Compatible with Google Colab