USGS-R / river-dl

Deep learning model for predicting environmental variables on river systems
Creative Commons Zero v1.0 Universal
22 stars 14 forks source link

differences in input between xiaowei and my code #7

Closed jsadler2 closed 3 years ago

jsadler2 commented 4 years ago

Xiaowei's processed feature data file (processed_features.npy) has 20 input variables. But in sntemp_input_output_subset.feather there are 24 features. Three of those are not meaningful as model input (IMO): 'seg_id_nat', 'model_idx', 'date' which leaves 21 total variables. So my question is, which one of these did Xiaowei not include? Or are we working from a different dataset?