公开(公告)号：US20210164944A1

公开(公告)日：2021-06-03

申请号：US16956605

申请日：2019-07-23

Applicant: Landmark Graphics Corporation

Inventor： Srinivasan JAGNNATHAN ,  Oluwatosin OGUNDARE ,  Srinath MADASU ,  Keshava RANGARAJAN

IPC: G01N29/44 ,  G06N3/04

Abstract: Methods and systems for solving inverse problems arising in systems described by a physics-based forward propagation model use a Bayesian approach to model the uncertainty in the realization of model parameters. A Generative Adversarial Network (“GAN”) architecture along with heuristics and statistical learning is used. This results in a more reliable point estimate of the desired model parameters. In some embodiments, the disclosed methodology may be applied to automatic inversion of physics-based modeling of pipelines.