JutulDarcyRules: auto-differentiable multiphase flow solvers based on JutulDarcy with ChainRules integration
Interoperate Jutul.jl and JutulDarcy.jl to other Julia packages via ChainRules.jl. We welcome you to read the open-access article, "Learned multiphysics inversion with differentiable programming and machine learning", for the design principle of this software package.
The software used in this repository can be modified and redistributed according to MIT license.
The following publications use JutulDarcyRules.jl:
-
"Time-lapse full-waveform permeability inversion: A feasibility study", doi: 10.1190/tle43080544.1
-
"A Digital Twin for Geological Carbon Storage with Controlled Injectivity", doi: 10.48550/arXiv.2403.19819
-
BEACON: Bayesian Experimental design Acceleration with Conditional Normalizing flows – a case study in optimal monitor well placement for CO2 sequestration, doi: 10.48550/arXiv.2404.00075
-
"Inference of CO2 flow patterns -- a feasibility study", doi: 10.48550/arXiv.2311.00290
-
"Solving multiphysics-based inverse problems with learned surrogates and constraints", doi: 10.1186/s40323-023-00252-0
-
"Learned multiphysics inversion with differentiable programming and machine learning", doi: 10.1190/tle42070474.1
If you use our software for your research, we appreciate it if you cite us following the bibtex in CITATION.bib.
This package is developed by the researchers at the Seismic Laboratory for Imaging and Modeling (SLIM) at the Georgia Institute of Technology.
If you have any question, we welcome your contributions to our software by opening issue or pull request.
SLIM Group @ Georgia Institute of Technology, https://slim.gatech.edu.
SLIM public GitHub account, https://github.com/slimgroup.