Home /Learned Multiphysics Inversion with Differentiable Programming & Machine Learning: An open-source path from wave physics to CO₂ digital twins
Learned Multiphysics Inversion with Differentiable Programming & Machine Learning: An open-source path from wave physics to CO₂ digital twins
| Title | Learned Multiphysics Inversion with Differentiable Programming & Machine Learning: An open-source path from wave physics to CO₂ digital twins |
| Publication Type | Conference |
| Year of Publication | 2026 |
| Authors | Mathias Louboutin, Bhar, I, Huseyin Tuna Erdinc, Felix J. Herrmann |
| Conference Name | EAGE Workshop: Open for Energy: Open Source, Open Data, Open Models, EAGE, Aberdeen |
| Month | 6 |
| Keywords | Bayesian inference, deep learning, EAGE, foundation models, full waveform inference, generative model, Imaging, Inverse problems, multiphysics, RTM, score, Summary Statistics, UK-NDR, Uncertainty quantification |
| URL | https://slim.gatech.edu/Publications/Public/Conferences/EAGE/2026/herrmann2026EAGEWSlmi |
| Citation Key | herrmann2026EAGEWSlmi |
