You are viewing an old version of this page. View the current version.

Compare with Current View Page History

« Previous Version 14 Next »

page under construction ------------------------------

There are many situations where a user is only interested in a subset of the dataset spatial domain.

For example, when comparing modelled river flow against observations, it is reasonable to being able to extract the timeseries at those point coordinates rather than dealing with many GB of data.

Similarly, when the focus is on a specific catchment it is likely that you want only that part of the spatial domain.

In summary, there two operations that are very popular on CEMS-Flood datasets: 

  • Area cropping
  • Time series extraction 

There are different ways to perform those operations:

  • From the CDS API (less data is downloaded)
  • Locally (full control on the process)


GloFAS

Example script to crop and extract time series from different GloFAS products:

Area cropping: GloFAS Medium-range reforecast  
## === retrieve GloFAS Medium-Range Reforecast ===

## === subset India, Pakistan, Nepal and Bangladesh region === 


import cdsapi
from datetime import datetime, timedelta


def get_monthsdays():

    start, end = datetime(2019, 1, 1), datetime(2019, 12, 31)
    days = [start + timedelta(days=i) for i in range((end - start).days + 1)]
    monthday = [d.strftime("%B-%d").split("-")  for d in days if d.weekday() in [0,3] ]   

    return monthday

MONTHSDAYS = get_monthsdays()

if __name__ == '__main__':
    c = cdsapi.Client()
    
    # user inputs
	BBOX = [40.05 ,59.95, 4.95, 95.05] # North West South East
    YEARS  = ['%d'%(y) for y in range(1999,2019)]
    LEADTIMES = ['%d'%(l) for l in range(24,1128,24)]
    
    # submit request
    for md in MONTHSDAYS:

        month = md[0].lower()
        day = md[1]

        c.retrieve(
            'cems-glofas-reforecast',
            {
                'system_version': 'version_2_2',
                'variable': 'river_discharge_in_the_last_24_hours',
                'format': 'grib',
                'hydrological_model': 'htessel_lisflood',
                'product_type': 'control_reforecast',
				'area': BBOX,# < - subset
                'hyear': YEARS,
                'hmonth': month ,
                'hday': day ,
                'leadtime_hour': LEADTIMES,
            },
            f'glofas_reforecast_{month}_{day}.grib')
Area cropping: GloFAS Seasonal Forecast 
## === retrieve GloFAS Seasonal Forecast ===

## === subset South America/Amazon region === 

import cdsapi


if __name__ == '__main__':
    c = cdsapi.Client()

    YEARS  = ['%d'%(y) for y in range(2020,2022)]


    MONTHS = ['%02d'%(m) for m in range(1,13)]

    LEADTIMES = ['%d'%(l) for l in range(24,2976,24)]
    
    for year in YEARS:

        for month in MONTHS:
            
            c.retrieve(
                'cems-glofas-seasonal',
                {   
                'variable': 'river_discharge_in_the_last_24_hours',
                'format': 'grib',
                'year': year,
                'month': '12' if year == '2020' else month,
                'leadtime_hour': LEADTIMES,
				'area': [ 10.95, -90.95, -30.95, -29.95 ]

                },
                f'glofas_seasonal_{year}_{month}.grib')
Area cropping: GloFAS Seasonal Reforecast 
## === retrieve GloFAS Seasonal Reforecast ===

## === subset South America/Amazon region === 

import cdsapi

if __name__ == '__main__':


    c = cdsapi.Client()

    YEARS  = ['%d'%(y) for y in range(1981,2021)]

    MONTHS = ['january', 'february', 'march', 'april', 'may', 'june', 'july', 'august', 'september', 'october', 'november', 'december']

    LEADTIMES = ['%d'%(l) for l in range(24,2976,24)]
    
    for year in YEARS:
        for month in MONTHS:

            c.retrieve(
                'cems-glofas-seasonal-reforecast',
                {
                    'system_version': 'version_2_2',
                    'variable':'river_discharge_in_the_last_24_hours',
                    'format':'grib',
                    'hydrological_model':'htessel_lisflood',
                    'hyear': year,
                    'hmonth': month,
                    'leadtime_hour': LEADTIMES,
                    'area': [ 10.95, -90.95, -30.95, -29.95 ]
                }, 
                f'glofas_seasonal_reforecast_{year}_{month}.grib')
Extract timeseries: GloFAS Medium-range Reforecast 
import cdsapi
from datetime import datetime, timedelta



def get_monthsdays(start =[2019,1,1],end=[2019,12,31]):
# reforecast time index
start, end = datetime(*start),datetime(*end)
days = [start + timedelta(days=i) for i in range((end - start).days + 1)]
monthday = [d.strftime("%B-%d").split("-") for d in days if d.weekday() in [0,3] ] 

return monthday



if __name__ == '__main__':
c = cdsapi.Client()


# station coordinates (lat,lon)
COORDS = {
"Thames":[51.35,-0.45]
}

# select date index corresponding to the event 
MONTHSDAYS = get_monthsdays(start =[2019,7,11],end=[2019,7,11])

YEAR = '2007' 

LEADTIMES = ['%d'%(l) for l in range(24,1128,24)]

# loop over date index (just 1 in this case)
for md in MONTHSDAYS:

month = md[0].lower()
day = md[1]

# loop over station coordinates
for station in COORDS:

station_point_coord = COORDS[station]*2 # coordinates input for the area keyword

c.retrieve(
'cems-glofas-reforecast',
{
'system_version': 'version_2_2',
'variable': 'river_discharge_in_the_last_24_hours',
'format': 'grib',
'hydrological_model': 'htessel_lisflood',
'product_type': ['control_reforecast','ensemble_perturbed_reforecasts'],
'area':station_point_coord, 
'hyear': YEAR,
'hmonth': month ,
'hday': day ,
'leadtime_hour': LEADTIMES,
},
f'glofas_reforecast_{station}_{month}_{day}.grib')


EFAS

to update once cropping works....

  • No labels