Prepare calibration dataset (Delft3D FM)

[xldeltares]

For calibration of the regression module, calibration data set including rainfall timeseries at each rain gauges and maximum flood at manholes need to be prepared.

• [ ] #10
• [ ] #16
• [ ] For Delft3d fm, the maximum flood depth at mesh1d nodes should be obtained from the map file (output to regression model)

[xldeltares]

Also related to the last item in https://github.com/xldeltares/hybridurb/issues/10

[xldeltares]

Inject delft3dfm model following the example below (ref: neural hydrology)

# --- Data configurations --------------------------------------------------------------------------

# which data set to use [camels_us, camels_gb, global, hourly_camels_us]
dataset: camels_us --> delft3dfm

# Path to data set root
data_dir: ../../data/CAMELS_US   --> eindhoven

# Forcing product [daymet, maurer, maurer_extended, nldas, nldas_extended, nldas_hourly]
# can be either a list of forcings or a single forcing product
forcings: --> rainfall and runoff series
  - maurer
  - daymet
  - nldas

dynamic_inputs: --> maybe not needed?
  - PRCP(mm/day)_nldas
  - PRCP(mm/day)_maurer
  - prcp(mm/day)_daymet
  - srad(W/m2)_daymet
  - tmax(C)_daymet
  - tmin(C)_daymet
  - vp(Pa)_daymet

# which columns to use as target
target_variables:
  - QObs(mm/d) --> mesh1d_water_depth_on_ground?

# clip negative predictions to zero for all variables listed below. Should be a list, even for single variables.
clip_targets_to_zero:
  - QObs(mm/d)