def get_precipitation_fields(
num_prev_files=0,
num_next_files=0,
return_raw=False,
metadata=False,
upscale=None,
source="mch",
log_transform=True,
clip=None,
**importer_kwargs,
):
"""
Get a precipitation field from the archive to be used as reference.
Source: bom
Reference time: 2018/06/16 10000 UTC
Source: fmi
Reference time: 2016/09/28 1600 UTC
Source: knmi
Reference time: 2010/08/26 0000 UTC
Source: mch
Reference time: 2015/05/15 1630 UTC
Source: opera
Reference time: 2018/08/24 1800 UTC
Source: saf
Reference time: 2018/06/01 0700 UTC
Source: mrms
Reference time: 2019/06/10 0000 UTC
Parameters
----------
num_prev_files: int, optional
Number of previous times (files) to return with respect to the
reference time.
num_next_files: int, optional
Number of future times (files) to return with respect to the
reference time.
return_raw: bool, optional
Do not preprocess the precipitation fields. False by default.
The pre-processing steps are: 1) Convert to mm/h,
2) Mask invalid values, 3) Log-transform the data [dBR].
metadata: bool, optional
If True, also return file metadata.
clip: scalars (left, right, bottom, top), optional
The extent of the bounding box in data coordinates to be used to clip
the data.
upscale: float or None, optional
Upscale fields in space during the pre-processing steps.
If it is None, the precipitation field is not modified.
If it is a float, represents the length of the space window that is
used to upscale the fields.
source: {"bom", "fmi" , "knmi", "mch", "opera", "saf", "mrms"}, optional
Name of the data source to be used.
log_transform: bool
Whether to transform the output to dB.
Other Parameters
----------------
importer_kwargs : dict
Additional keyword arguments passed to the importer.
Returns
-------
reference_field : array
metadata : dict
"""
if source == "bom":
pytest.importorskip("netCDF4")
if source == "fmi":
pytest.importorskip("pyproj")
if source == "knmi":
pytest.importorskip("h5py")
if source == "mch":
pytest.importorskip("PIL")
if source == "opera":
pytest.importorskip("h5py")
if source == "saf":
pytest.importorskip("netCDF4")
if source == "mrms":
pytest.importorskip("pygrib")
try:
date = _reference_dates[source]
except KeyError:
raise ValueError(f"Unknown source name '{source}'\n"
"The available data sources are: "
f"{str(list(_reference_dates.keys()))}")
data_source = rcparams.data_sources[source]
root_path = data_source["root_path"]
path_fmt = data_source["path_fmt"]
fn_pattern = data_source["fn_pattern"]
fn_ext = data_source["fn_ext"]
importer_name = data_source["importer"]
_importer_kwargs = data_source["importer_kwargs"].copy()
_importer_kwargs.update(**importer_kwargs)
timestep = data_source["timestep"]
# Find the input files from the archive
fns = io.archive.find_by_date(
date,
root_path,
path_fmt,
fn_pattern,
fn_ext,
timestep=timestep,
num_prev_files=num_prev_files,
num_next_files=num_next_files,
)
# Read the radar composites
importer = io.get_method(importer_name, "importer")
reference_field, __, ref_metadata = io.read_timeseries(
fns, importer, **_importer_kwargs)
if not return_raw:
if (num_prev_files == 0) and (num_next_files == 0):
# Remove time dimension
reference_field = np.squeeze(reference_field)
# Convert to mm/h
reference_field, ref_metadata = stp.utils.to_rainrate(
reference_field, ref_metadata)
# Clip domain
reference_field, ref_metadata = stp.utils.clip_domain(
reference_field, ref_metadata, clip)
# Upscale data
reference_field, ref_metadata = aggregate_fields_space(
reference_field, ref_metadata, upscale)
# Mask invalid values
reference_field = np.ma.masked_invalid(reference_field)
if log_transform:
# Log-transform the data [dBR]
reference_field, ref_metadata = stp.utils.dB_transform(
reference_field, ref_metadata, threshold=0.1, zerovalue=-15.0)
# Set missing values with the fill value
np.ma.set_fill_value(reference_field, -15.0)
reference_field.data[reference_field.mask] = -15.0
if metadata:
return reference_field, ref_metadata
return reference_field
importer_kwargs = data_source["importer_kwargs"]
timestep = data_source["timestep"]
# Find the input files from the archive
fns = io.archive.find_by_date(
date,
root_path,
path_fmt,
fn_pattern,
fn_ext,
timestep=5,
num_next_files=35,
)
# Read the radar composites
importer = io.get_method(importer_name, "importer")
R, __, metadata = io.read_timeseries(fns, importer, **importer_kwargs)
# Convert to mm/h
R, metadata = conversion.to_rainrate(R, metadata)
# Upscale to 2 km (simply to reduce the memory demand)
R, metadata = dimension.aggregate_fields_space(R, metadata, 2000)
# Keep only one frame every 10 minutes (i.e., every 2 timesteps)
# (to highlight the need for advection correction)
R = R[::2]
################################################################################
# Advection correction
# --------------------
source = "".join([i for i in case if not i.isdigit()])
data_source = pysteps.rcparams.data_sources[source]
# Find the input files from the archive
file_names = io.archive.find_by_date(
case_date,
data_source["root_path"],
data_source["path_fmt"],
data_source["fn_pattern"],
data_source["fn_ext"],
data_source["timestep"],
num_prev_files=0,
num_next_files=frames - 1,
)
if None in file_names[0]:
raise FileNotFoundError(f"Error loading {case} case. Some files are missing.")
# Read the radar composites
importer = io.get_method(data_source["importer"], "importer")
importer_kwargs = data_source["importer_kwargs"]
reflectivity, _, metadata = io.read_timeseries(
file_names, importer, **importer_kwargs
)
# Convert to rain rate
precip, metadata = conversion.to_rainrate(reflectivity, metadata)
return precip, metadata, data_source["timestep"]
fn_ext = radar_data_source["fn_ext"]
importer_name = radar_data_source["importer"]
importer_kwargs = radar_data_source["importer_kwargs"]
timestep = 10.0
# Find the radar files in the archive
fns = io.find_by_date(date_radar,
root_path,
path_fmt,
fn_pattern,
fn_ext,
timestep,
num_prev_files=2)
# Read the radar composites
importer = io.get_method(importer_name, "importer")
radar_precip, _, radar_metadata = io.read_timeseries(fns, importer,
**importer_kwargs)
# Import the NWP data
filename = os.path.join(
nwp_data_source["root_path"],
datetime.strftime(date_nwp, nwp_data_source["path_fmt"]),
datetime.strftime(date_nwp, nwp_data_source["fn_pattern"]) + "." +
nwp_data_source["fn_ext"],
)
nwp_importer = io.get_method("bom_nwp", "importer")
nwp_precip, _, nwp_metadata = nwp_importer(filename)
# Only keep the NWP forecasts from the last radar observation time (2020-10-31 04:00)
def get_precipitation_fields(num_prev_files=0,
num_next_files=0,
return_raw=False,
metadata=False,
upscale=None):
"""
Get a precipitation field from the archive to be used as reference.
Source: mch
Reference time: 2015/05/15 1630 UTC
Parameters
----------
num_prev_files: int
Number of previous times (files) to return with respect to the
reference time.
num_next_files: int
Number of future times (files) to return with respect to the
reference time.
return_raw: bool
Do not preprocess the precipitation fields. False by default.
The pre-processing steps are: 1) Convert to mm/h,
2) Mask invalid values, 3) Log-transform the data [dBR].
metadata : bool
If True, also return file metadata.
upscale: float or None
Upscale fields in space during the pre-processing steps.
If it is None, the precipitation field is not
modified.
If it is a float, represents the length of the space window that is
used to upscale the fields.
Returns
-------
reference_field : array
metadata : dict
"""
pytest.importorskip('PIL')
# Selected case
date = datetime.strptime("201505151630", "%Y%m%d%H%M")
data_source = rcparams.data_sources["mch"]
root_path = data_source["root_path"]
path_fmt = data_source["path_fmt"]
fn_pattern = data_source["fn_pattern"]
fn_ext = data_source["fn_ext"]
importer_name = data_source["importer"]
importer_kwargs = data_source["importer_kwargs"]
timestep = data_source["timestep"]
# Find the input files from the archive
fns = io.archive.find_by_date(date,
root_path,
path_fmt,
fn_pattern,
fn_ext,
timestep=timestep,
num_prev_files=num_prev_files,
num_next_files=num_next_files)
# Read the radar composites
importer = io.get_method(importer_name, "importer")
reference_field, __, ref_metadata = io.read_timeseries(fns, importer,
**importer_kwargs)
if not return_raw:
if (num_prev_files == 0) and (num_next_files == 0):
# Remove time dimension
reference_field = np.squeeze(reference_field)
# Convert to mm/h
reference_field, ref_metadata = stp.utils.to_rainrate(reference_field,
ref_metadata)
# Upscale data to 2 km
reference_field, ref_metadata = aggregate_fields_space(reference_field,
ref_metadata,
upscale)
# Mask invalid values
reference_field = np.ma.masked_invalid(reference_field)
# Log-transform the data [dBR]
reference_field, ref_metadata = stp.utils.dB_transform(reference_field,
ref_metadata,
threshold=0.1,
zerovalue=-15.0)
# Set missing values with the fill value
reference_field.data[reference_field.mask] = -15.0
if metadata:
return reference_field, ref_metadata
return reference_field
