#W2D1 Tutorial 2: Time series, global averages, and scenario comparison

Indented block

Week 2, Day 1, Future Climate: The Physical Basis

Content creators: Brodie Pearson (Day Lead), Julius Busecke (Tutorial co-lead), Tom Nicholas (Tutorial co-lead)

Content reviewers: Jenna Pearson, Ohad Zivan

Content editors: TBD

Production editors: TBD

Our 2023 Sponsors: TBD

#Tutorial Objectives

Today’s tutorials demonstrate how to work with data from Earth System Models (ESMs) simulations conducted for the recent Climate Model Intercomparison Project (CMIP6)

By the end of today’s tutorials you will be able to:

Manipulate raw data from multiple CMIP6 models
Evaluate the spread of future projections from several CMIP6 models
Synthesize climate data from observations and models

#Setup

# #Imports

# !pip install condacolab &> /dev/null
# import condacolab
# condacolab.install()

# # Install all packages in one call (+ use mamba instead of conda)
# # hopefully this improves speed
# !mamba install xarray-datatree intake-esm gcsfs xmip aiohttp nc-time-axis cf_xarray xarrayutils &> /dev/null

import time

tic = time.time()

import intake
import numpy as np
import matplotlib.pyplot as plt
import xarray as xr

from xmip.preprocessing import combined_preprocessing
from xarrayutils.plotting import shaded_line_plot

from datatree import DataTree
from xmip.postprocessing import _parse_metric

Figure settings#

# @title Figure settings
import ipywidgets as widgets  # interactive display

%config InlineBackend.figure_format = 'retina'
plt.style.use(
    "https://raw.githubusercontent.com/ClimateMatchAcademy/course-content/main/cma.mplstyle"
)
# model_colors = {k:f"C{ki}" for ki, k in enumerate(source_ids)}

Plotting functions#

# @title Plotting functions

# You may have functions that plot results that aren't
# particularly interesting. You can add these here to hide them.


def plotting_z(z):
    """This function multiplies every element in an array by a provided value

    Args:
      z (ndarray): neural activity over time, shape (T, ) where T is number of timesteps

    """

    fig, ax = plt.subplots()

    ax.plot(z)
    ax.set(xlabel="Time (s)", ylabel="Z", title="Neural activity over time")

Helper functions#

# @title Helper functions

# If any helper functions you want to hide for clarity (that has been seen before
# or is simple/uniformative), add here
# If helper code depends on libraries that aren't used elsewhere,
# import those libaries here, rather than in the main import cell


def global_mean(ds: xr.Dataset) -> xr.Dataset:
    """Global average, weighted by the cell area"""
    return ds.weighted(ds.areacello.fillna(0)).mean(["x", "y"], keep_attrs=True)


# Calculate anomaly to reference period
def datatree_anomaly(dt):
    dt_out = DataTree()
    for model, subtree in dt.items():
        # for the coding exercise, ellipses will go after sel on the following line
        ref = dt[model]["historical"].ds.sel(time=slice("1950", "1980")).mean()
        dt_out[model] = subtree - ref
    return dt_out


def plot_historical_ssp126_combined(dt):
    for model in dt.keys():
        datasets = []
        for experiment in ["historical", "ssp126"]:
            datasets.append(dt[model][experiment].ds.tos)

        da_combined = xr.concat(datasets, dim="time")

Tutorial 2: Time series, global averages, and scenario comparison#

Video 1: Video 1 Name#

# @title Video 1: Video 1 Name
# Tech team will add code to format and display the video

##Section 1.1: Load CMIP6 SST data from several models using xarray

Let’s expand on Tutorial 1 by loading five different CMIP6 models on last week’s Climate Modelling day.

col = intake.open_esm_datastore(
    "https://storage.googleapis.com/cmip6/pangeo-cmip6.json"
)  # open an intake catalog containing the Pangeo CMIP cloud data

# pick our five example models
# There are many more to test out! Try executing `col.df['source_id'].unique()` to get a list of all available models
source_ids = ["IPSL-CM6A-LR", "GFDL-ESM4", "ACCESS-CM2", "MPI-ESM1-2-LR", "TaiESM1"]

---------------------------------------------------------------------------
KeyboardInterrupt                         Traceback (most recent call last)
Cell In[7], line 1
----> 1 col = intake.open_esm_datastore(
   "https://storage.googleapis.com/cmip6/pangeo-cmip6.json"
)  # open an intake catalog containing the Pangeo CMIP cloud data
# pick our five example models
# There are many more to test out! Try executing `col.df['source_id'].unique()` to get a list of all available models
source_ids = ["IPSL-CM6A-LR", "GFDL-ESM4", "ACCESS-CM2", "MPI-ESM1-2-LR", "TaiESM1"]

File ~/miniconda3/envs/climatematch/lib/python3.10/site-packages/intake_esm/core.py:107, in esm_datastore.__init__(self, obj, progressbar, sep, registry, read_csv_kwargs, columns_with_iterables, storage_options, **intake_kwargs)
   self.esmcat = ESMCatalogModel.from_dict(obj)
else:
--> 107     self.esmcat = ESMCatalogModel.load(
       obj, storage_options=self.storage_options, read_csv_kwargs=read_csv_kwargs
   )
self.derivedcat = registry or default_registry
self._entries = {}

File ~/miniconda3/envs/climatematch/lib/python3.10/site-packages/intake_esm/cat.py:264, in ESMCatalogModel.load(cls, json_file, storage_options, read_csv_kwargs)
       csv_path = f'{os.path.dirname(_mapper.root)}/{cat.catalog_file}'
   cat.catalog_file = csv_path
--> 264     df = pd.read_csv(
       cat.catalog_file,
       storage_options=storage_options,
       **read_csv_kwargs,
   )
else:
   df = pd.DataFrame(cat.catalog_dict)

File ~/miniconda3/envs/climatematch/lib/python3.10/site-packages/pandas/io/parsers/readers.py:912, in read_csv(filepath_or_buffer, sep, delimiter, header, names, index_col, usecols, dtype, engine, converters, true_values, false_values, skipinitialspace, skiprows, skipfooter, nrows, na_values, keep_default_na, na_filter, verbose, skip_blank_lines, parse_dates, infer_datetime_format, keep_date_col, date_parser, date_format, dayfirst, cache_dates, iterator, chunksize, compression, thousands, decimal, lineterminator, quotechar, quoting, doublequote, escapechar, comment, encoding, encoding_errors, dialect, on_bad_lines, delim_whitespace, low_memory, memory_map, float_precision, storage_options, dtype_backend)
kwds_defaults = _refine_defaults_read(
   dialect,
   delimiter,
   (...)
   dtype_backend=dtype_backend,
)
kwds.update(kwds_defaults)
--> 912 return _read(filepath_or_buffer, kwds)

File ~/miniconda3/envs/climatematch/lib/python3.10/site-packages/pandas/io/parsers/readers.py:577, in _read(filepath_or_buffer, kwds)
_validate_names(kwds.get("names", None))
# Create the parser.
--> 577 parser = TextFileReader(filepath_or_buffer, **kwds)
if chunksize or iterator:
   return parser

File ~/miniconda3/envs/climatematch/lib/python3.10/site-packages/pandas/io/parsers/readers.py:1407, in TextFileReader.__init__(self, f, engine, **kwds)
   self.options["has_index_names"] = kwds["has_index_names"]
self.handles: IOHandles | None = None
-> 1407 self._engine = self._make_engine(f, self.engine)

File ~/miniconda3/envs/climatematch/lib/python3.10/site-packages/pandas/io/parsers/readers.py:1661, in TextFileReader._make_engine(self, f, engine)
   if "b" not in mode:
       mode += "b"
-> 1661 self.handles = get_handle(
   f,
   mode,
   encoding=self.options.get("encoding", None),
   compression=self.options.get("compression", None),
   memory_map=self.options.get("memory_map", False),
   is_text=is_text,
   errors=self.options.get("encoding_errors", "strict"),
   storage_options=self.options.get("storage_options", None),
)
assert self.handles is not None
f = self.handles.handle

File ~/miniconda3/envs/climatematch/lib/python3.10/site-packages/pandas/io/common.py:716, in get_handle(path_or_buf, mode, encoding, compression, memory_map, is_text, errors, storage_options)
   codecs.lookup_error(errors)
# open URLs
--> 716 ioargs = _get_filepath_or_buffer(
   path_or_buf,
   encoding=encoding,
   compression=compression,
   mode=mode,
   storage_options=storage_options,
)
handle = ioargs.filepath_or_buffer
handles: list[BaseBuffer]

File ~/miniconda3/envs/climatematch/lib/python3.10/site-packages/pandas/io/common.py:373, in _get_filepath_or_buffer(filepath_or_buffer, encoding, compression, mode, storage_options)
       if content_encoding == "gzip":
           # Override compression based on Content-Encoding header
           compression = {"method": "gzip"}
--> 373         reader = BytesIO(req.read())
   return IOArgs(
       filepath_or_buffer=reader,
       encoding=encoding,
   (...)
       mode=fsspec_mode,
   )
if is_fsspec_url(filepath_or_buffer):

File ~/miniconda3/envs/climatematch/lib/python3.10/http/client.py:482, in HTTPResponse.read(self, amt)
else:
   try:
--> 482         s = self._safe_read(self.length)
   except IncompleteRead:
       self._close_conn()

File ~/miniconda3/envs/climatematch/lib/python3.10/http/client.py:631, in HTTPResponse._safe_read(self, amt)
def _safe_read(self, amt):
   """Read the number of bytes requested.

   This function should be used when <amt> bytes "should" be present for
   reading. If the bytes are truly not available (due to EOF), then the
   IncompleteRead exception can be used to detect the problem.
   """
--> 631     data = self.fp.read(amt)
   if len(data) < amt:
       raise IncompleteRead(data, amt-len(data))

File ~/miniconda3/envs/climatematch/lib/python3.10/socket.py:705, in SocketIO.readinto(self, b)
while True:
   try:
--> 705         return self._sock.recv_into(b)
   except timeout:
       self._timeout_occurred = True

File ~/miniconda3/envs/climatematch/lib/python3.10/ssl.py:1274, in SSLSocket.recv_into(self, buffer, nbytes, flags)
   if flags != 0:
       raise ValueError(
         "non-zero flags not allowed in calls to recv_into() on %s" %
         self.__class__)
-> 1274     return self.read(nbytes, buffer)
else:
   return super().recv_into(buffer, nbytes, flags)

File ~/miniconda3/envs/climatematch/lib/python3.10/ssl.py:1130, in SSLSocket.read(self, len, buffer)
try:
   if buffer is not None:
-> 1130         return self._sslobj.read(len, buffer)
   else:
       return self._sslobj.read(len)

KeyboardInterrupt: 

If the following cell crashes, run the cell a second time#

# from the full `col` object, create a subset using facet search
cat = col.search(
    source_id=source_ids,
    variable_id='tos',
    member_id='r1i1p1f1',
    table_id='Omon',
    grid_label='gn',
    experiment_id = ['historical', 'ssp126', 'ssp585'],
    require_all_on = ['source_id'] #make sure that we only get models which have all of the above experiments
)

# convert the sub-catalog into a datatree object, by opening each dataset into an xarray.Dataset (without loading the data)
kwargs = dict(
    preprocess=combined_preprocessing, #apply xMIP fixes to each dataset
    xarray_open_kwargs=dict(use_cftime=True), #ensure all datasets use the same time index
    storage_options={'token':'anon'} #anonymous/public authentication to google cloud storage
)
# hopefully we can implement https://github.com/intake/intake-esm/issues/562 before the
# actual tutorial, so this would be a lot cleaner
cat.esmcat.aggregation_control.groupby_attrs = ['source_id', 'experiment_id']
dt = cat.to_datatree(**kwargs)

cat_area = col.search(
    source_id=source_ids,
    variable_id='areacello', # for the coding exercise, ellipses will go after the equals on this line
    member_id='r1i1p1f1',
    table_id='Ofx', # for the coding exercise, ellipses will go after the equals on this line
    grid_label='gn',
    experiment_id = ['historical'], # for the coding exercise, ellipses will go after the equals on this line
    require_all_on = ['source_id']
)
# hopefully we can implement https://github.com/intake/intake-esm/issues/562 before the
# actual tutorial, so this would be a lot cleaner
cat_area.esmcat.aggregation_control.groupby_attrs = ['source_id', 'experiment_id']
dt_area = cat_area.to_datatree(**kwargs)

dt_with_area = DataTree()

for model,subtree in dt.items():
    metric = dt_area[model]['historical'].ds['areacello']
    dt_with_area[model] = subtree.map_over_subtree(_parse_metric,metric)

    %matplotlib inline

# average every dataset in the tree globally
dt_gm = dt_with_area.map_over_subtree(global_mean)

for experiment in ['historical', 'ssp126', 'ssp585']:
    da = dt_gm['TaiESM1'][experiment].ds.tos
    da.plot(label=experiment)
plt.title('Global Mean SST from TaiESM1')
plt.ylabel('Global Mean SST [$^\circ$C]')
plt.xlabel('Year')
plt.legend()

plot_historical_ssp126_combined(dt_gm)

dt_gm_anomaly = datatree_anomaly(dt_gm)

plot_historical_ssp126_combined(dt_gm_anomaly)

plt.close()

#Tutorial 4: Quantifying uncertainty in a CMIP6 multi-model ensemble

Let’s create a multi-model ensemble containing data from multiple CMIP6 models, which we can use to quantify our confidence in future projected sea surface temperature change under low- and high-emissions scenarios.

Specifically, you goal is to create a likely range of future projected conditions. The IPCC uncertainty language defines the likely range as the middle 66% of model results (i.e., ignoring the upper and lower 17% of results)

###Coding Exercise 4.1: Display multi-model ensemble data with IPCC uncertainty bands

Complete the following code to plot:

Shading to display the likely range of temperatures for the CMIP6 historical and projected data (include both SSP1-2.6 and SSP5-8.5). da_upper and da_lower are the boundaries of this shaded region
The multi-model mean temperature
(Not sure if we should include this one) The median temperature across the model ensemble

#################################################
## TODO for students: details of what they should do ##
# Fill out function and remove
raise NotImplementedError("Student exercise: Plot the multi-model mean projections, and their likely range under different experiments/scenarios")
#################################################
%matplotlib inline

for experiment, color in zip(['historical', 'ssp126', 'ssp585'], ['C0', 'C1', 'C2']):
    datasets = []
    for model in dt_gm_anomaly.keys():
        annual_sst = dt_gm_anomaly[model][experiment].ds.tos.coarsen(time=12).mean().assign_coords(source_id=model)
        datasets.append(annual_sst.sel(time=slice(None, '2100')).load()) # the french model has a long running member for ssp126
    da = xr.concat(datasets, dim='source_id', join='override').squeeze()
    x = da.time.data
    # Calculate the lower bound of the likely range
    da_lower = da.squeeze().quantile(...)
    # Calculate the upper bound of the likely range
    da_upper = da.squeeze().quantile(...)
    plt.fill_between(x, da_lower, da_upper,  alpha=0.5, color=color)
    # Calculate the multi-model mean at each time within each experiment
    da.mean(...).plot(color=color, label=experiment,)
    # Calculate the multi-model median at each time within each experiment
    da.squeeze().quantile(...).plot(color=color, linestyle='dashed',)
plt.title('Global Mean SST Anomaly from five-member CMIP6 ensemble (base period: 1950 to 1980)')
plt.ylabel('Global Mean SST Anomaly [$^\circ$C]')
plt.xlabel('Year')
plt.legend()

plt.show()

# to_remove solution
%matplotlib inline

with plt.xkcd():
    for experiment, color in zip(
        ["historical", "ssp126", "ssp585"], ["C0", "C1", "C2"]
    ):
        datasets = []
        for model in dt_gm_anomaly.keys():
            annual_sst = (
                dt_gm_anomaly[model][experiment]
                .ds.tos.coarsen(time=12)
                .mean()
                .assign_coords(source_id=model)
            )
            datasets.append(
                annual_sst.sel(time=slice(None, "2100")).load()
            )  # the french model has a long running member for ssp126
        da = xr.concat(datasets, dim="source_id", join="override").squeeze()
        x = da.time.data
        # Calculate the lower bound of the likely range
        da_lower = da.squeeze().quantile(0.17, dim="source_id")
        # Calculate the upper bound of the likely range
        da_upper = da.squeeze().quantile(0.83, dim="source_id")
        plt.fill_between(x, da_lower, da_upper, alpha=0.5, color=color)
        # Calculate the multi-model mean at each time within each experiment
        da.mean("source_id").plot(
            color=color,
            label=experiment,
        )
        # Calculate the multi-model median at each time within each experiment
        da.squeeze().quantile(0.5, dim="source_id").plot(
            color=color,
            linestyle="dashed",
        )
    plt.title(
        "Global Mean SST Anomaly from five-member \n CMIP6 ensemble (base period: 1950 to 1980)"
    )
    plt.ylabel("Global Mean SST Anomaly [$^\circ$C]")
    plt.xlabel("Year")
    plt.legend()

    plt.show()

Post-figure question#

What does this figure tell you about how the multi-model uncertainty compares to projected physical changes in the global mean SST?
Is this the same for both scenarios?
For a 5-model ensemble like this, how do the likely ranges specifically relate to the 5 indivudual model temperatures at a given time?

Climatematch Academy: Computational Tools for Climate Science

Figure settings

Contents