Hello everyone,
I would like to test my model on a large spatial domain. From what I read so far [1][2], it looks like a domain decomposition can enhance the prediction results. What is the best way to implement this in Modulus? Is it best to modify the conf files or create a new network model? Is it possible to modify any of the current network models to perform domain decomposition?
[1] Kharazmi, Ehsan, Zhongqiang Zhang, and George Em Karniadakis. “hp-VPINNs: Variational physics-informed neural networks with domain decomposition.” Computer Methods in Applied Mechanics and Engineering 374 (2021): 113547.
[2] N. Borrel-Jensen, S. Goswami, A. P. Engsig-Karup, G. E. Karniadakis, and C.-H. Jeong, “Sound propagation in realistic interactive 3D scenes with parameterized sources using deep neural operators,” pp. 1–25, 2023.
Thank you for your support!