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.
Originally posted by **jds485** January 26, 2022
There are 28 GAGES sites without flood thresholds (NaN value).
So that I can run the code, I'll assign a quantile threshold for these sites based on the daily flow values. But I'm interested in your thoughts on why these wouldn't have values. Maybe not enough peak flow data?
> if(is.na(floodThreshold)){
> floodThreshold <- quantile(x = df_dv$discharge, probs = 0.66)
> }
Discussed in https://github.com/USGS-R/regional-hydrologic-forcings-ml/discussions/43