\n $\"No$ \n

Search and access with ACTRIS Data Portal and json\u00b6

In\u00a0[1]:

# Libraries for working with multidimensional arrays\nimport numpy as np\nimport xarray as xr\nimport pandas as pd\n\n# Libraries for plotting and visualising data\nimport matplotlib.path as mpath\nimport matplotlib.pyplot as plt\n\n# Libraries for working with json files\nimport json\nimport requests\nimport os\n

Access data from example on Search with ACTRIS Data Portal\u00b6

The previous example includes two methods of accessing the data:

THREDDS Data Catalog - Opendap protocol (Streaming of data)
THREDDS Data Catalog - HTTPS protocol (Download of data)

You only need to run one of the protocols to get the dataset in question for the analysis.

In\u00a0[2]:

protocol = 'opendap' # choose 'http' or 'opendap'\n

In\u00a0[3]:

# Check filepath \nfolder = os.getcwd().replace(\"  Analyse ACTRIS data\", \"   Search and access\") ## Change the folder name to the folder where the data is stored\nprint(folder)\n

/home/lemu/repos/actris/actris-jupyter-hub/   Search and access\n

In\u00a0[4]:

os.chdir(folder)\n\nf = open('static/basket.json') # open the file \"basket.json\"\nmd = json.load(f) # load the json file\n\nif protocol == 'http': \n    if os.path.exists(\"static/data_oc_ec\"): \n        print(\"The data folder exists\")\n    else:\n        print(\"The data folder does not exist, here is the short version. To get more information about this protocol see the first example.\")\n        \n        f = open('static/basket.json') # open the file \"basket.json\"\n        md = json.load(f) # load the json file\n        os.makedirs(\"static/data_oc_ec\")\n        for i in md: \n            r = requests.get(md[i]['downloadUrl'])\n            filename = r.url[-12:]\n            filepath = os.path.join(\"static/data_oc_ec\", filename)  # Specify the folder path\n            with open(filepath, mode=\"wb\") as file:\n                file.write(r.content)\n

Data processing\u00b6

Depending on the type of data, the documentation for each file can be found here: https://data.actris.eu/docs

Documentation on the In-Situ file formats (NetCDF) is available here: https://ebas.pages.nilu.no/ebas-io/fileformat_netcdf/index.html

In\u00a0[5]:

ds_elemental_carbon = []  # Create an empty list to store elemental carbon data\nds_organic_carbon = []  # Create an empty list to store organic carbon data\nds_total_carbon = []  # Create an empty list to store total carbon data\n\nfor i in md:  # Iterate over the keys in the 'md' dictionary\n\n    if protocol == 'opendap':\n        ds = xr.open_dataset(md[i]['opendapUrl'])\n    elif protocol == 'http':\n        filename = md[i]['downloadUrl'][-12:]\n        ds = xr.open_dataset('data_oc_ec/{}'.format(filename))  \n    \n    for j in list(ds.data_vars.keys()):  # Iterate over the variables in the dataset\n        attrs = ds[j].attrs  # Get the attributes of the variable\n        \n        # Check if the variable is elemental carbon with specific attributes\n        if attrs.get('standard_name') == 'mass_concentration_of_elemental_carbon_in_pm10_in_air' and \\\n           attrs.get('ebas_statistics') == 'arithmetic mean' and \\\n           attrs.get('units') == 'ug C/m3':\n            ds_elemental_carbon.append(ds[j])  # Add the variable to the elemental carbon list\n        \n        # Check if the variable is organic carbon with specific attributes\n        elif attrs.get('standard_name') == 'mass_concentration_of_organic_carbon_in_pm10_in_air' and \\\n             attrs.get('ebas_statistics') == 'arithmetic mean' and \\\n             attrs.get('units') == 'ug C/m3':\n            if 'Fraction' not in ds[j].dims and 'Fractionx' not in ds[j].dims and 'Fractionxx' not in ds[j].dims:\n                ds_organic_carbon.append(ds[j])  # Add the variable to the organic carbon list\n        \n        # Check if the variable is total carbon with specific attributes\n        elif attrs.get('standard_name') == 'mass_concentration_of_total_carbon_in_pm10_in_air' and \\\n             attrs.get('ebas_statistics') == 'arithmetic mean' and \\\n             attrs.get('units') == 'ug C/m3':\n            ds_total_carbon.append(ds[j])  # Add the variable to the total carbon list\n

In\u00a0[6]:

# Sort the ds_elemental_carbon list based on the first time value in each DataArray\nds_elemental_carbon.sort(key=lambda x: x.time.values[0] if len(x.time) > 0 else np.datetime64('NaT'))\n\n# Sort the ds_organic_carbon list based on the first time value in each DataArray\nds_organic_carbon.sort(key=lambda x: x.time.values[0] if len(x.time) > 0 else np.datetime64('NaT'))\n\n# Sort the ds_total_carbon list based on the first time value in each DataArray\nds_total_carbon.sort(key=lambda x: x.time.values[0] if len(x.time) > 0 else np.datetime64('NaT'))\n

In\u00a0[7]:

# Concatenate the list of DataArrays in ds_elemental_carbon along the 'time' dimension\nec_ds = xr.concat([ds for ds in ds_elemental_carbon], dim='time')\n\n# Concatenate the list of DataArrays in ds_organic_carbon along the 'time' dimension\noc_ds = xr.concat([ds for ds in ds_organic_carbon], dim='time')\n\n# Concatenate the list of DataArrays in ds_total_carbon along the 'time' dimension\ntc_ds = xr.concat([ds for ds in ds_total_carbon], dim='time')\n

Data visualisation\u00b6

Using matplotlib to create a timeseries plot of elemental carbon and organic carbon at Birkenes

In\u00a0[8]:

plt.figure(figsize=(15, 5))\nplt.plot(ec_ds.time, ec_ds, label='Elemental Carbon')\nplt.plot(oc_ds.time, oc_ds, label='Organic Carbon')\n#plt.plot(tc_ds.time, tc_ds, label='Total Carbon')\nplt.legend()\nplt.ylabel('ug C/m3')\nplt.xlabel('Time')\nplt.title('Elemental Carbon and Organic Carbon pm10 at Birkenes in Norway')\nplt.show()\n

\n $\"No$ \n