NECCTONsimulations/copernicusmarine_download.py at main · Parcels-code/NECCTONsimulations · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
# Script to download necessary Copernicus Marine data for Arctic NECCTON simulations
import copernicusmarine as cm
from argparse import ArgumentParser
import os
import os.path
import pandas as pd


longitude_range = [-180., 180.]
latitude_range = [50., 90.]
depth_range = [0., 70.]

p = ArgumentParser(description="Download Copernicus Marine data for Arctic NECCTON simulations")
p.add_argument('-startdate', '--startdate', default='2020-01-01', help='Start date for data download (YYYY-MM-DD)')
p.add_argument('-enddate', '--enddate', default='2021-01-01', help='End date for data download (YYYY-MM-DD)')
parsed_args = p.parse_args()


start_day = pd.Timestamp(parsed_args.startdate)
end_day = pd.Timestamp(parsed_args.enddate)
output_directory = "/storage/shared/oceanparcels/output_data/data_Michael/NECCTONsimulations/data/copernicus_data/"

total_days = (end_day - start_day).days + 1 #+1 to include end day

for i in range(total_days):
    current_day = start_day + pd.Timedelta(days=i)

    # Download hydrodynamics
    output_filename = f"cmems_mod_glo_phy_my_{current_day.strftime('%Y-%m-%d')}.nc"

    if not os.path.isfile(output_directory + output_filename):
        cm.subset(
            dataset_id="cmems_mod_glo_phy_my_0.083deg_P1D-m",
            variables=["uo", "vo", "so", "thetao"],
            minimum_longitude=longitude_range[0],
            maximum_longitude=longitude_range[1],
            minimum_latitude=latitude_range[0],
            maximum_latitude=latitude_range[1],
            minimum_depth=depth_range[0],
            maximum_depth=depth_range[1],
            start_datetime=current_day.isoformat(),
            end_datetime=(current_day).isoformat(),
            coordinates_selection_method='outside',
            file_format="netcdf",
            output_filename = output_filename,
            output_directory = output_directory
        )

    # Download biogeochemistry
    output_filename = f"cmems_mod_glo_bgc_my_nppv_{current_day.strftime('%Y-%m-%d')}.nc"
    if not os.path.isfile(output_directory + output_filename):
        # Download the phyc data seprately because it is monthly!
        cm.subset(
            dataset_id="cmems_mod_glo_bgc_my_0.25deg_P1D-m",
            variables=["nppv"],
            minimum_longitude=longitude_range[0],
            maximum_longitude=longitude_range[1],
            minimum_latitude=latitude_range[0],
            maximum_latitude=latitude_range[1],
            minimum_depth=depth_range[0],
            maximum_depth=depth_range[1],
            start_datetime=current_day.isoformat(),
            end_datetime=(current_day).isoformat(),
            coordinates_selection_method='outside',
            file_format="netcdf",
            output_filename = output_filename,
            output_directory = output_directory
        )

    # Download the wave data
    output_filename = f"cmems_mod_glo_wav_my_{current_day.strftime('%Y-%m-%d')}.nc"
    if not os.path.isfile(output_directory + output_filename):
        cm.subset(
            dataset_id="cmems_mod_glo_wav_my_0.2deg_PT3H-i",
            variables=["VSDX", "VSDY", "VTPK"],
            minimum_longitude=longitude_range[0],
            maximum_longitude=longitude_range[1],
            minimum_latitude=latitude_range[0],
            maximum_latitude=latitude_range[1],
            minimum_depth=depth_range[0],
            maximum_depth=depth_range[1],
            start_datetime=current_day.isoformat(),
            end_datetime=(current_day+pd.Timedelta(hours=21)).isoformat(),
            coordinates_selection_method='outside',
            file_format="netcdf",
            output_filename = output_filename,
            output_directory = output_directory
        )

# Ensure all of phyc is downloaded (although, this has already been done!)
# for i in range(12*16):
#     start_day = pd.Timestamp('2008-01-01') + pd.DateOffset(months=i)
#     output_filename = f"cmems_mod_glo_bgc_my_phyc_{start_day.strftime('%Y-%m-%d')}.nc"

#     # Download the phyc data seprately because it is monthly!
#     if not os.path.isfile(output_directory + output_filename):
#         cm.subset(
#             dataset_id="cmems_mod_glo_bgc_my_0.25deg_P1M-m",
#             variables=["phyc"],
#             minimum_longitude=longitude_range[0],
#             maximum_longitude=longitude_range[1],
#             minimum_latitude=latitude_range[0],
#             maximum_latitude=latitude_range[1],
#             minimum_depth=depth_range[0],
#             maximum_depth=depth_range[1],
#             start_datetime=start_day.isoformat(),
#             end_datetime=(start_day).isoformat(),
#             coordinates_selection_method='outside',
#             file_format="netcdf",
#             output_filename = output_filename,
#             output_directory = output_directory
#         )
#     print(start_day)