Hybrid quantum-classical FBPINN for acoustic FWI achieves lower L1 velocity error than classical baselines in ~8x fewer iterations with ~33% fewer parameters on anomaly and checkerboard benchmarks.
Solving the frequency-domain acoustic vti wave equation using physics-informed neural networks.Geophysical Journal International, 225(2):846–859, 01 2021
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
physics.geo-ph 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Accelerating physics-informed neural networks for full waveform inversion using a hybrid quantum-classical finite-basis architecture
Hybrid quantum-classical FBPINN for acoustic FWI achieves lower L1 velocity error than classical baselines in ~8x fewer iterations with ~33% fewer parameters on anomaly and checkerboard benchmarks.