Accelerating physics-informed neural networks for full waveform inversion using a hybrid quantum-classical finite-basis architecture
arXiv:2606.01110v1 Announce Type: cross Abstract: Full waveform inversion (FWI) reconstructs heterogeneous material properties from receiver data but remains computationally demanding. Physics-informed neural networks (PINNs) and their domain-decomposed variants (FBPINNs) offer a mesh-free alternative but face convergence challenges when representing complex velocity fields. We present a hybrid quantum-classical FBPINN for acoustic FWI, bringing together quantum computing and classical machine learning, in which the decomposed wavefield network and the global velocity network are implemented a
This development emerges as the computational demands of advanced scientific simulations like full waveform inversion increasingly push the limits of classical machine learning and prompt exploration into quantum computing's potential.
A strategic reader should care because this represents a tangible step towards integrating quantum computing into scientific workflows, potentially accelerating complex computational problems previously intractable for classical systems.
The computational approach to complex geological modeling is changing, moving from purely classical methods to a hybrid quantum-classical paradigm, which could significantly enhance simulation speed and accuracy.
- · Quantum computing developers
- · Geophysics and energy exploration
- · AI/ML research labs
- · Academic research institutions
Improved accuracy and speed in subsurface imaging for resource discovery and seismic hazard assessment.
Increased investment and talent flow into hybrid quantum-classical algorithm development across various scientific fields.
The establishment of quantum supremacy in specific computational science niches, leading to broader adoption and integration of quantum accelerators.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG