Skip to content

Modeling Uncertainty seeks to identify and explore interesting approaches to understanding the world without disregarding the critical aspects of uncertainty within any given problem set.

License

mwmckenzie/modeling-uncertainty

 
 

Repository files navigation

if Modeling: return Uncertainty

A Project Hub for Experiments with Probabilistic and Ensemble Modeling

https://mwmckenzie.github.io/modeling-uncertainty/

Unique and Interesting Approaches towards a Better Understanding of Real-World Problem Sets

Example 1000 member ensemble model for infectious persons per 10,000A beautiful, and somewhat mesmerizing, example of a "Spaghetti Plot" displaying the results from a 1,000 model ensemble. The results depict the outcome of randomly sampled initial conditions run through the SEIR model created for this site's first project. See the sidebar for links to the details and code.

Latest Projects and Updates

See the Sidebar [Top Menu on mobile] for Links to the Full Projects Listed Below

COVID-19 Graph Network Simulation SEIR Model

The first annotated Python Jupyter notebook has been posted!

Annotated Simulation Notebook

COVID-19 Probabilistic Ensemble Model

Multiple annotated Python Jupyter notebooks for the first COVID-19 Probabilistic Ensemble Model created and posted:

  • A probility distribution discovery and creation application.
  • The main ensemble model and data organization and export application.
  • A data visualization and exploration application.

Testing Online Notebook Hosting Services

Exploring MyBinder.org as a host for interactive and shareable Jupyter notebooks and applications - seeking a means for exploring model results online:

Interactive Ensemble Results via MyBinder

About

Modeling Uncertainty seeks to identify and explore interesting approaches to understanding the world without disregarding the critical aspects of uncertainty within any given problem set.

Resources

License

Code of conduct

Stars

Watchers

Forks

Packages

No packages published

Languages

  • SCSS 64.9%
  • JavaScript 16.5%
  • HTML 14.4%
  • Ruby 4.0%
  • Shell 0.2%