Repository navigation
Explicitly include GPP, ER, Gas exchange in model outputs #46
Description
Activity
A couple more ideas for this version of the model:
- We could add process guidance based on physical relationships between stream slope, width and depth with gas exchange (K)
- Both GPP and ER could be constrained to have a degree of autocorrelation (unless there is high precipitation possibly)
Reacted by Jeff SadlerAlso, an option for farther down the road would be to take this approach but then add on a second layer of neural network after the GPP, ER and K are predicted that included a subset of the original predictors. This would allow for non-deterministic relationships between metabolism and oxygen concentrations that arise because of variation in stream temperatures, differences in groundwater inputs, or other types of process error.
Reacted by Jeff SadlerOne more thought - could we also estimate water temperature? Meaning that the estimated variables would be:
If so, then we could calculate DO saturation, and then have equations like the ones above to calculate DO max/mean/min:
I'm still don't fully understand the h, W, and b terms - so I apologize if these equations don't make sense!
Reacted by Jeff Sadler- locked and limited conversation to collaborators
on Jan 31, 2022
One possible approach to adding process guidance to the vanilla deep learning model is to explicitly represent the DO mass balance by outputting GPP, ER, and Gas exchange:
Baseline LSTM (#40):
Proposed:
