Physic Based Inverse Problem

Physics-based inverse problems aim to infer unknown parameters or states of a system from observed data, leveraging underlying physical principles modeled in a forward problem. Current research heavily utilizes deep learning approaches, including generative adversarial networks (GANs), diffusion models, and autoencoders, to solve these often ill-posed problems, particularly in high-dimensional spaces. These methods are applied across diverse fields, such as materials science, biomechanics, and seismic imaging, improving the accuracy and efficiency of parameter estimation and uncertainty quantification. The resulting advancements offer significant potential for accelerating scientific discovery and enhancing the reliability of predictions in various applications.

Papers

June 30, 2023

MeLM, a generative pretrained language modeling framework that solves forward and inverse mechanics problems
Markus J. Buehler
Material Discovery Multi Modal Language Model Inspired Design Emergent Structure Physic Based Inverse Problem Carbon Nanotube

June 8, 2023

Solution of physics-based inverse problems using conditional generative adversarial networks with full gradient penalty
Deep Ray, Javier Murgoitio-Esandi, Agnimitra Dasgupta, Assad A. Oberai
Generative Adversarial Network Inverse Problem Solution Path Conditional Generative Adversarial Network Gradient Penalty Physic Based Inverse Problem

January 24, 2023

Solving Inverse Physics Problems with Score Matching
Benjamin J. Holzschuh, Simona Vegetti, Nils Thuerey
Inverse Problem Score Matching Physic Based Inverse Problem

July 20, 2022

Deep Preconditioners and their application to seismic wavefield processing
Matteo Ravasi
Application Proficiency Inverse Problem Seismic Data Neural Preconditioners Seismic Wavefield Sparsifying Transform Physic Based Inverse Problem

February 15, 2022

The efficacy and generalizability of conditional GANs for posterior inference in physics-based inverse problems
Deep Ray, Harisankar Ramaswamy, Dhruv V. Patel, Assad A. Oberai
Generative Adversarial Network Multi Scale Stronger Generalizability Posterior Inference Physic Informed Conditional GANs Physic Based Inverse Problem

Physic Based Inverse Problem

Papers

MeLM, a generative pretrained language modeling framework that solves forward and inverse mechanics problems

Solution of physics-based inverse problems using conditional generative adversarial networks with full gradient penalty

Solving Inverse Physics Problems with Score Matching

Deep Preconditioners and their application to seismic wavefield processing

The efficacy and generalizability of conditional GANs for posterior inference in physics-based inverse problems