Reproduce “Neural Surrogate Modeling of Ultrasonic Wave Propagation in Heterogeneous Media” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Burla Nur Korkmaz, Petro Moilanen, Ari Salmi, Harsha Vardhan Tetali, Arto Klami
LU-NO combines Fourier layers in a U-shaped multiscale network with learned local-integral resampling to predict ultrasound wavefields across spatial resolutions. The authors evaluate models trained at 121×121 on 16 simulated test instances, including a 301×301 grid. At high resolution, LU-NO reaches relative squared L2 error 0.305 ± 0.083 versus U-NO’s 0.453 ± 0.047, and alone reproduces the main reflection; results are limited to this simulated setting.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.