search

USGS-R / regional-hydrologic-forcings-ml

Repo for machine learning models for regional prediction of hydrologic forcing functions. Includes probabilistic seasonal high flow regions for CONUS, and prediction of high flow metrics for selected regions.
Creative Commons Zero v1.0 Universal
0 stars 4 forks source link

Add function and target to create map of transition regions. #195

Closed cstillwellusgs closed 1 year ago

cstillwellusgs commented 1 year ago

Closes #194

All reaches that have 2nd most likely probability greater than 0.1 Transitions_High_NoPhysio_NHD_fine_k5_threshold_0 1

All reaches that have 2nd most likely probability greater than 0.2 Transitions_High_NoPhysio_NHD_fine_k5_threshold_0 2

cstillwellusgs commented 1 year ago

Try adding color to reaches that have > 5% for 3-5 most likely (maybe in gray). Could use all(probs > 0.05) to do this filter.

Would this be a separate panel? Or overlaid? I started to think that through but it doesn't really go with the current format.

jds485 commented 1 year ago

Would this be a separate panel? Or overlaid

I was thinking overlaid on each panel for only the reaches in that panel

cstillwellusgs commented 1 year ago

Would this be a separate panel? Or overlaid

I was thinking overlaid on each panel for only the reaches in that panel

Okay, so if any reach has 3 regions with 3+ probabilities of 5% or greater... that reach would be classified completely separate from the transition regions. For example, if a reach is 55% region 1, 30% region 2, and 15% region 3, that would be classified exclusively ("confused" - I'll think of a better label) from the transition regions 1-2, 2-3, and 1-3. Do I understand correctly?

(in my current code that example reach would appear in each of the panels for region transtions 1-2, 1-3, and 2-3)

cstillwellusgs commented 1 year ago

Transitions_High_NoPhysio_NHD_fine_k5_threshold_0 05

cstillwellusgs commented 1 year ago

Region_Count_High_NoPhysio_NHD_fine_k5_threshold_0 05