Wouter J. de Bruin
Wouter J. de Bruin
This PR implements scaling of correlated observations using the ERT build-in PCA scaling method. --- ### Contributor checklist - [x] :tada: This PR closes #206. - [x] :scroll: I have...
When running hyperparameter tuning, MLflow expects an mlruns folder - which we don't create. If we stick with the standard we can ommit having to run `mlflow ui` with the...
Since the 2021.04 OPM Flow release numerical aquifers are supported. By supporting this, we potentially can simplify aquifers in FlowNets. See: https://opm-project.org/?p=1388
Currently we are loading data only from one source (the original reservoir simulation model). However, it will be benefitial to be able to load data that does not exist in...
After #356 is merged, a possible follow-up could be to distribute the volume from the original model per cell instead of per tube. This would lead to smaller volumes close...
The simple plotting tool added in #351 should also be exposed as a forward model option in FlowNet. If used in MLFlow runs, the output should then be stored as...
The relative permeability modelling has in the meanwhile become quite extensive. We should write documentation on it.
Using `time_ag_open_location` 
When wells have multiple perforations, many "overlapping" triangles are potentially created as a result of Delaunay triagulation. This leads to many tubes that need to be history matched which all...