Closed jsadler2 closed 3 years ago
try using normalized nash-sutcliffe in loss function. I think this is a good idea to try b/c it is what I'm usually reporting for flow performance and it is the standard in the hydrology community (much more than rmse).
I will use normalized Nash-sutcliffe since it bounded: https://en.wikipedia.org/wiki/Nash–Sutcliffe_model_efficiency_coefficient
try using normalized nash-sutcliffe in loss function. I think this is a good idea to try b/c it is what I'm usually reporting for flow performance and it is the standard in the hydrology community (much more than rmse).