USGS-R / river-dl

Deep learning model for predicting environmental variables on river systems
Creative Commons Zero v1.0 Universal
21 stars 15 forks source link

make code agnostic to input/output data sources #103

Closed jsadler2 closed 3 years ago

jsadler2 commented 3 years ago

I need to make the code agnostic to input/output data sources. This is necessary since I'm moving away from using the prms/sntemp io as input and pretraining data. I will need to support input data from NLDAS. I think this will mainly mean that I will need to make the prep code and other code able to accept variable names as arguments. Currently they are hard-coded (e.g., seg_id_nat).