cs.LGNov 10, 2026

JAX-WAVE: A Differentiable Physics-Supervised Framework for Inverse Wave Design in Heterogeneous Media

Authors: Honghui Du, Binyao Guo, Yushu Pan

Organizations: Department of Civil, Environmental, and Geo- Engineering, University of Minnesota, Minneapolis, MN, USA. · Department of Computer Science, Columbia University, New York, NY, USA.

Abstract

Designing a prescribed wave field in a heterogeneous medium requires an initial pressure distribution that compensates for the medium's propagation response. Repeated numerical inversion solves this task afresh for each target and environment. We introduce JAX-WAVE for amortized inverse wave design: a shared neural network maps desired terminal fields and known wave-speed maps directly to bounded initial pressures. Training through a differentiable finite-difference time-domain solver uses the physical design objective without requiring optimized control labels. Linear propagation and symmetric pressure bounds imply an exact sign-reversal relation for the regularized optimum. A shared-weight projection enforces this relation, preserves feasibility, and satisfies an exact identity for the paired-sign objective. We characterize the discrete propagator and its weighted adjoint to connect learning, numerical inversion, and optimality assessment. On an independent confirmation set, three trained models achieve unseen-material errors of 25.24% for geometric targets and 4.77% for reachable targets. Matched-capacity comparisons show improved reconstruction with the sign parameterization. Within a 5 ms median online budget, the learned map reduces mean error by 45% relative to accelerated numerical inversion on the heterogeneous benchmark; longer numerical solves recover greater accuracy. The results establish a reusable inverse-design procedure and show how its accuracy and computational value depend on target structure and query workload.

Figures & tables

Appendix figures & tables13 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. A solver-in-the-loop framework for end-to-end differentiable coastal hydrodynamics

    Apr 8, 2026Elsa Cardoso-Bihlo, Alex BihloDifferentiable PhysicsComputational Fluid Dynamics

  2. NAP-Wave: A Neural Adaptive Plane-Wave Architecture for High-Frequency Helmholtz Problems

    Nov 14, 2026Hamza Kamil, Mohammad Mahdi Abedi, David PardoNeural PDE SolversPDE Solving

  3. Inductively Scalable, Single-Step Neural Surrogates for Wave-Scattering Inverse Problems

    Aug 18, 2026Charles Dove, Laura WallerNeural Surrogate ModelingPDE Surrogate Modeling