def high_q_dur(da: DataArray, threshold: float = 9.) -> float:
"""Calculate high-flow duration.
Average duration of high-flow events (number of consecutive steps >`threshold` times the median flow) [#]_,
[#]_ (Table 2).
Parameters
----------
da : DataArray
Array of flow values.
threshold : float, optional
High-flow threshold. Values larger than ``threshold * median`` are considered high flows.
Returns
-------
float
High-flow duration
References
----------
.. [#] Clausen, B. and Biggs, B. J. F.: Flow variables for ecological studies in temperate streams: groupings based
on covariance. Journal of Hydrology, 2000, 237, 184--197, doi:10.1016/S0022-1694(00)00306-1
.. [#] Westerberg, I. K. and McMillan, H. K.: Uncertainty in hydrological signatures.
Hydrology and Earth System Sciences, 2015, 19, 3951--3968, doi:10.5194/hess-19-3951-2015
"""
median_flow = float(da.median())
idx = np.where(da.values > threshold * median_flow)[0]
if len(idx) > 0:
periods = _split_list(idx)
hqd = np.mean([len(p) for p in periods])
else:
hqd = np.nan
return hqd
def high_q_freq(da: DataArray, coord: str = "date", threshold: float = 9.0) -> float:
# determine the date of the first January 1st in the data period
first_date = da.coords[coord][0].values.astype("datetime64[s]").astype(datetime)
last_date = da.coords[coord][-1].values.astype("datetime64[s]").astype(datetime)
if first_date == datetime.strptime(f"{first_date.year}-01-01", "%Y-%m-%d"):
start_date = first_date
else:
start_date = datetime.strptime(f"{first_date.year + 1}-01-01", "%Y-%m-%d")
# end date of the first full year period
end_date = start_date + relativedelta(years=1) - relativedelta(days=1)
# determine the median flow over the entire period
median_flow = da.median(skipna=True)
hqfs = []
while end_date < last_date:
data = da.sel({coord: slice(start_date, end_date)})
# number of days with discharge higher than threshold * median in a one year period
n_days = (data > (threshold * median_flow)).sum()
hqfs.append(float(n_days))
start_date += relativedelta(years=1)
end_date += relativedelta(years=1)
return np.mean(hqfs)
def high_q_dur(da: DataArray, threshold: float = 9.) -> float:
median_flow = float(da.median())
idx = np.where(da.values > threshold * median_flow)[0]
if len(idx) > 0:
periods = _split_list(idx)
hqd = np.mean([len(p) for p in periods])
else:
hqd = np.nan
return hqd
def high_q_freq(da: DataArray,
datetime_coord: str = None,
threshold: float = 9.) -> float:
"""Calculate high-flow frequency.
Frequency of high-flow events (>`threshold` times the median flow) [#]_, [#]_ (Table 2).
Parameters
----------
da : DataArray
Array of flow values.
datetime_coord : str, optional
Datetime coordinate in the passed DataArray. Tried to infer automatically if not specified.
threshold : float, optional
High-flow threshold. Values larger than ``threshold * median`` are considered high flows.
Returns
-------
float
High-flow frequency
References
----------
.. [#] Clausen, B. and Biggs, B. J. F.: Flow variables for ecological studies in temperate streams: groupings based
on covariance. Journal of Hydrology, 2000, 237, 184--197, doi:10.1016/S0022-1694(00)00306-1
.. [#] Westerberg, I. K. and McMillan, H. K.: Uncertainty in hydrological signatures.
Hydrology and Earth System Sciences, 2015, 19, 3951--3968, doi:10.5194/hess-19-3951-2015
"""
if datetime_coord is None:
datetime_coord = utils.infer_datetime_coord(da)
# determine the date of the first January 1st in the data period
first_date = da.coords[datetime_coord][0].values.astype(
'datetime64[s]').astype(datetime)
last_date = da.coords[datetime_coord][-1].values.astype(
'datetime64[s]').astype(datetime)
if first_date == datetime.strptime(f'{first_date.year}-01-01', '%Y-%m-%d'):
start_date = first_date
else:
start_date = datetime.strptime(f'{first_date.year + 1}-01-01',
'%Y-%m-%d')
# end date of the first full year period
end_date = start_date + relativedelta(years=1) - relativedelta(seconds=1)
# determine the median flow over the entire period
median_flow = da.median(skipna=True)
hqfs = []
while end_date < last_date:
data = da.sel({datetime_coord: slice(start_date, end_date)})
# number of steps with discharge higher than threshold * median in a one year period
n_steps = (data > (threshold * median_flow)).sum()
hqfs.append(float(n_steps))
start_date += relativedelta(years=1)
end_date += relativedelta(years=1)
return np.mean(hqfs)
