cd /news/machine-learning/romnet-a-hybrid-reduced-order-modeli… · home topics machine-learning article
[ARTICLE · art-112784] src=machinebrief.com ↗ pub= topic=machine-learning verified=true sentiment=· neutral

ROMNet: a hybrid reduced order modeling and machine learning approach to waveform inversion

Researchers introduced ROMNet, a hybrid reduced order modeling and machine learning approach that uses a neural network to map a reduced order model (ROM) matrix to a nearby one with simpler dependence on wave speed, reducing computational cost in waveform inversion. In numerical tests with random media and the GeoFWI dataset, ROMNet outperformed direct ROM-based inversion and two deep learning baselines, Fourier-DeepONet and InversionNet.

read1 min views1 publishedAug 27, 2026

arXiv:2608.25160v1 Announce Type: cross Abstract: Waveform inversion seeks to estimate the wave speed of a heterogeneous, inaccessible medium, from time-resolved measurements of the waves at user controlled sensors. We consider this inverse problem for acoustic waves and an active array of source/receiver sensors that emit probing signals and measure the generated pressure waves. The forward map, from the wave speed to the measurements, is nonlinear and oscillatory. The oscillations cause cycle skipping, the main impediment to using the standard, nonlinear least-squares data fitting formulation, known as full waveform inversion (FWI). A recently introduced alternative waveform inversion approach computes from the measurements an algebraic surrogate of the wave operator, a reduced order model (ROM) matrix, which is then used to estimate the wave speed. The mapping from the measurements to the ROM is nonlinear, but well understood. It is computed efficiently, in a non-iterative manner. The nonlinear mapping from the ROM to the wave speed is less understood, and its approximation involves time-consuming optimization. Our goal in this paper is to use a neural network to map the ROM matrix to a nearby one, that has a simpler and explicit dependence on the wave speed. This simplifies and reduces the computational cost of the ROM-based waveform inversion. We introduce the methodology, called ROMNet, and test it with numerical simulations, using two training data sets: The first set consists of random media with variations of the wave speed modeled by a superposition of Gaussians with random amplitudes and standard deviations. The second is the publicly available GeoFWI dataset introduced for benchmarking FWI using deep learning. We compare the performance of ROMNet with the direct ROM-based inversion and with two representative deep learning approaches to FWI: Fourier-DeepONet" and InversionNet".

── more in #machine-learning 4 stories · sorted by recency
── more on @romnet 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/romnet-a-hybrid-redu…] indexed:0 read:1min 2026-08-27 ·