Miguel de la Varga & Jan Niederau

Things you'll need:
Slack channel: #t22-mon-mcmc (visit softwareunderground.org/slack to join)
Repo: github.com/cgre-aachen/gempy_workshops/tree/master…

Starting from a simple inference problem, we show PyMC3s capabilities in pythonic Bayesian Inference, step-by-step extending the (spatial) dimensions, till working with a simple geological model.

Timestamps:
0:00:00 Start of live stream
3:30 Repository
4:30 Virtual Machine Azure cloud option to run the tutorial
labs.azure.com/register/cqgky5n4
9:50 Intro
16:30 Importing libraries
17:25 Model definition
17:58 Simplest probabilistic modeling
23:35 Sampling the model
39:26 Increasing number of observations
1:01:39 Extending the Dimensions
1:14:57 Applying this to geological modeling
1:23:26 Bayesian Inference with GemPy and Pymc3