def _sal_detect_objects(precip, thr_factor, thr_quantile, tstorm_kwargs):
"""
Detect coherent precipitation objects using a multi-threshold approach from
:cite:`Feldmann2021`.
Parameters
----------
precip: array-like
Array of shape (m,n) containing input data. Nan values are ignored.
thr_factor: float
Factor used to compute the detection threshold as in eq. 1 of :cite:`WHZ2009`.
If not None, this is used to identify coherent objects enclosed by the
threshold contour `thr_factor * thr_quantile(precip)`.
thr_quantile: float
The wet quantile between 0 and 1 used to define the detection threshold.
Required if `thr_factor` is not None.
tstorm_kwargs: dict
Optional dictionary containing keyword arguments for the tstorm feature
detection algorithm. If None, default values are used.
See the documentation of :py:func:`pysteps.feature.tstorm.detection`.
Returns
-------
precip_objects: pd.DataFrame
Dataframe containing all detected cells and their respective properties.
"""
if not PANDAS_IMPORTED:
raise MissingOptionalDependency(
"The pandas package is required for the SAL "
"verification method but it is not installed"
)
if not SKIMAGE_IMPORTED:
raise MissingOptionalDependency(
"The scikit-image package is required for the SAL "
"verification method but it is not installed"
)
if thr_factor is not None and thr_quantile is None:
raise ValueError("You must pass thr_quantile, too")
if tstorm_kwargs is None:
tstorm_kwargs = dict()
if thr_factor is not None:
zero_value = np.nanmin(precip)
threshold = thr_factor * np.nanquantile(
precip[precip > zero_value], thr_quantile
)
tstorm_kwargs = {
"minmax": tstorm_kwargs.get("minmax", threshold),
"maxref": tstorm_kwargs.get("maxref", threshold + 1e-5),
"mindiff": tstorm_kwargs.get("mindiff", 1e-5),
"minref": tstorm_kwargs.get("minref", threshold),
}
_, labels = tstorm_detect.detection(precip, **tstorm_kwargs)
labels = labels.astype(int)
precip_objects = regionprops_table(
labels, intensity_image=precip, properties=REGIONPROPS
)
return pd.DataFrame(precip_objects)
def test_feature_tstorm_detection(source, output_feat, dry_input,
max_num_features):
pytest.importorskip("skimage")
pytest.importorskip("pandas")
if not dry_input:
input, metadata = get_precipitation_fields(0, 0, True, True, None,
source)
input = input.squeeze()
input, __ = to_reflectivity(input, metadata)
else:
input = np.zeros((50, 50))
time = "000"
output = detection(input,
time=time,
output_feat=output_feat,
max_num_features=max_num_features)
if output_feat:
assert isinstance(output, np.ndarray)
assert output.ndim == 2
assert output.shape[1] == 2
if max_num_features is not None:
assert output.shape[0] <= max_num_features
else:
assert isinstance(output, tuple)
assert len(output) == 2
assert isinstance(output[0], DataFrame)
assert isinstance(output[1], np.ndarray)
if max_num_features is not None:
assert output[0].shape[0] <= max_num_features
assert output[0].shape[1] == 9
assert list(output[0].columns) == [
"ID",
"time",
"x",
"y",
"cen_x",
"cen_y",
"max_ref",
"cont",
"area",
]
assert (output[0].time == time).all()
assert output[1].ndim == 2
assert output[1].shape == input.shape
if not dry_input:
assert output[0].shape[0] > 0
assert sorted(list(output[0].ID)) == sorted(
list(np.unique(output[1]))[1:])
else:
assert output[0].shape[0] == 0
assert output[1].sum() == 0
# Extract the list of timestamps
timelist = metadata["timestamps"]
pprint(metadata)
###############################################################################
# Example of thunderstorm identification in a single timestep.
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# The function tstorm_detect.detection requires a 2-D input image, all further inputs are
# optional.
input_image = Z[2, :, :].copy()
time = timelist[2]
cells_id, labels = tstorm_detect.detection(
input_image,
time=time,
)
###############################################################################
# Properties of one of the identified cells:
print(cells_id.iloc[0])
###############################################################################
# Example of thunderstorm tracking over a timeseries
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# The tstorm-dating function requires the entire pre-loaded time series.
# The first two timesteps are required to initialize the
# flow prediction and are not used to compute tracks.
track_list, cell_list, label_list = tstorm_dating.dating(
input_video=Z,
def dating(
input_video,
timelist,
mintrack=3,
cell_list=None,
label_list=None,
start=0,
minref=35,
maxref=48,
mindiff=6,
minsize=50,
minmax=41,
mindis=10,
dyn_thresh=False,
):
"""
This function performs the thunderstorm detection and tracking DATing.
It requires a 3-D input array that contains the temporal succession of the 2-D data
array of each timestep. On each timestep the detection is performed, the identified
objects are advected with a flow prediction and the advected objects are matched to
the newly identified objects of the next timestep.
The last portion re-arranges the data into tracks sorted by ID-number.
Parameters
----------
input_video : array-like
Array of shape (t,m,n) containing input image, with t being the temporal
dimension and m,n the spatial dimensions. Thresholds are tuned to maximum
reflectivity in dBZ with a spatial resolution of 1 km and a temporal resolution
of 5 min. Nan values are ignored.
timelist : list
List of length t containing string of time and date of each (m,n) field.
mintrack : int, optional
minimum duration of cell-track to be counted. The default is 3 time steps.
cell_list : list or None, optional
If you wish to expand an existing list of cells, insert previous cell-list here.
The default is None.
If not None, requires that label_list has the same length.
label_list : list or None, optional
If you wish to expand an existing list of cells, insert previous label-list here.
The default is None.
If not None, requires that cell_list has the same length.
start : int, optional
If you wish to expand an existing list of cells, the input video must contain 2
timesteps prior to the merging. The start can then be set to 2, allowing the
motion vectors to be formed from the first three grids and continuing the cell
tracking from there. The default is 0, which initiates a new tracking sequence.
minref : float, optional
Lower threshold for object detection. Lower values will be set to NaN.
The default is 35 dBZ.
maxref : float, optional
Upper threshold for object detection. Higher values will be set to this value.
The default is 48 dBZ.
mindiff : float, optional
Minimal difference between two identified maxima within same area to split area
into two objects. The default is 6 dBZ.
minsize : float, optional
Minimal area for possible detected object. The default is 50 pixels.
minmax : float, optional
Minimum value of maximum in identified objects. Objects with a maximum lower
than this will be discarded. The default is 41 dBZ.
mindis : float, optional
Minimum distance between two maxima of identified objects. Objects with a
smaller distance will be merged. The default is 10 km.
Returns
-------
track_list : list of dataframes
Each dataframe contains the track and properties belonging to one cell ID.
Columns of dataframes: ID - cell ID, time - time stamp, x - array of all
x-coordinates of cell, y - array of all y-coordinates of cell, cen_x -
x-coordinate of cell centroid, cen_y - y-coordinate of cell centroid, max_ref -
maximum (reflectivity) value of cell, cont - cell contours
cell_list : list of dataframes
Each dataframe contains the detected cells and properties belonging to one
timestep. The IDs are already matched to provide a track.
Columns of dataframes: ID - cell ID, time - time stamp, x - array of all
x-coordinates of cell, y - array of all y-coordinates of cell, cen_x -
x-coordinate of cell centroid, cen_y - y-coordinate of cell centroid, max_ref -
maximum (reflectivity) value of cell, cont - cell contours
label_list : list of arrays
Each (n,m) array contains the gridded IDs of the cells identified in the
corresponding timestep. The IDs are already matched to provide a track.
"""
if not SKIMAGE_IMPORTED:
raise MissingOptionalDependency(
"skimage is required for thunderstorm DATing "
"but it is not installed")
if not PANDAS_IMPORTED:
raise MissingOptionalDependency(
"pandas is required for thunderstorm DATing "
"but it is not installed")
# Check arguments
if cell_list is None or label_list is None:
cell_list = []
label_list = []
else:
if not len(cell_list) == len(label_list):
raise ValueError("len(cell_list) != len(label_list)")
if start > len(timelist):
raise ValueError("start > len(timelist)")
oflow_method = motion.get_method("LK")
max_ID = 0
for t in range(start, len(timelist)):
cells_id, labels = tstorm_detect.detection(
input_video[t, :, :],
minref=minref,
maxref=maxref,
mindiff=mindiff,
minsize=minsize,
minmax=minmax,
mindis=mindis,
time=timelist[t],
)
if len(cell_list) < 2:
cell_list.append(cells_id)
label_list.append(labels)
cid = np.unique(labels)
max_ID = np.nanmax([np.nanmax(cid), max_ID]) + 1
continue
if t >= 2:
flowfield = oflow_method(input_video[t - 2:t + 1, :, :])
cells_id, max_ID, newlabels = tracking(cells_id, cell_list[-1],
labels, flowfield, max_ID)
cid = np.unique(newlabels)
# max_ID = np.nanmax([np.nanmax(cid), max_ID])
cell_list.append(cells_id)
label_list.append(newlabels)
track_list = couple_track(cell_list[2:], int(max_ID), mintrack)
return track_list, cell_list, label_list