Skip to content

What is DDR?

Distributed Differentiable Routing (DDR) is a end-to-end differentiable Muskingum Cunge flow router (src/ddr) + geospatial scaffolding/wrapper (/engine) for building graphs from geospatial fabrics. This work is brought to you by contributers/developers of the \(\delta\)MC, \(\delta\)MC-Juniata-hydroDL2, and T-Route. The goal of this project is to provide an open-sourced, easy to follow, routing module that can be applied to a wide variety of geospatial flow networks and input lateral flow datasets.

Get started or learn more about DDR:

  • Model Training for how to create your own weights/states
  • Model Testing for evaluating your trained weights
  • Routing for how to route flow anywhere with trained weights
  • Summed Q_Prime for determining how well your unit catchment predictions are (pre-routing)