equinor / flownet

FlowNet - Data-Driven Reservoir Predictions

FlowNet: Data-Driven Reservoir Predictions

FlowNet aims at solving the following problems:

• Create data-driven reduced physics models - directly from the data
• Train the model
• Assure model predictiveness
• Use the models to efficiently optimize and make decisions

For documentation, see the GitHub pages for this repository.

Contributing

Please check out our contribution guidelines if you want to contribute to FlowNet.

Installation

FlowNet is a Python package. All required dependencies are automatically installed together with FlowNet, except for the OPM-Flow reservoir simulator binaries which you will need to install separately.

If your Flow installation is not located at /usr/bin/flow you should set an environment variable FLOW_PATH with path to your Flow executable prior to running FlowNet.

Install FlowNet

The easiest and recommended approach is to install FlowNet from PyPI by running

pip install flownet

If you want to install and try out the latest unreleased code you can do

git clone [email protected]:equinor/flownet.git
cd flownet
pip install -e .

Omit the -e flag if you want a standard installation.

⚠️ Do you want to run FlowNet through the LSF queue? To be able to have the ERT process, that will be called by FlowNet, run jobs via LSF correctly you will need to update your default shell's configuration file (.cshrc or .bashrc) to automatically source your virtual environment.

Running FlowNet

You can run FlowNet as a single command line:

flownet ahm ./some_config.yaml ./some_output_folder

Run flownet --help to see all possible command line argument options.

Running webviz to check results

Before running webviz for the first time on your machine, you will need to to create a localhost https certificate by doing:

webviz certificate --auto-install --force

License

FlowNet is, with a few exceptions listed below, GPLv3.

• The Norne test data is available under the Open Database License
• The FlowNet logo is CC BY-NC-ND 4.0