Code accompanying "Augmented Physics-Informed Neural Networks (APINNs): A gating network-based soft domain decomposition methodology" https://arxiv.org/abs/2211.08939.
The paper has been accepted for publication in Engineering Applications of Artificial Intelligence (EAAI).
The file "main.py" provides the code for the Burgers' equation, Helmholtz equation, Wave equation, and Klein-Gordon equation.
You can control the PDE, the models, and the hyperparameters by setting up args in the file.
BB.py and BB4.py provide the codes for the Burgers-Boussinesq equation with two and four subdomains, respectively. The usage is the same as main.py.