DassHydro / smash

An open source, Python library interfacing the Fortran Spatially distributed Modelling and ASsimilation for Hydrology platform.
https://smash.recover.inrae.fr/
GNU General Public License v3.0
12 stars 6 forks source link

ENH: Low memory adjoint #145

Closed inoelloc closed 8 months ago

inoelloc commented 8 months ago

This commit is an upgrade of the adjoint model allowing time step checkpoints to lower the maximum memory usage. By default, in the forward sweep of the adjoint, at each time, n arrays of shape (nrow, ncol) where pushed. This arrays were poped at the end of the forward sweep which result in some case (large domain and time steps) to a too high memory peak. This commit adds checkpoints in the forward sweep to reduce the memory peak and pass the variables that must be checkpointed at each time (i.e. fluxes and states) to a vector of active cell instead of a grid of number of rows and columns.

This upgrade should be pretty efficient for large domain and time step calibration