.. DO NOT EDIT. .. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY. .. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE: .. "examples/09_stormcast_example.py" .. LINE NUMBERS ARE GIVEN BELOW. .. only:: html .. note:: :class: sphx-glr-download-link-note :ref:`Go to the end ` to download the full example code. .. rst-class:: sphx-glr-example-title .. _sphx_glr_examples_09_stormcast_example.py: Running StormCast Inference =============================== Basic StormCast inference workflow. This example will demonstrate how to run a simple inference workflow to generate a basic determinstic forecast using StormCast. For details about the stormcast model, see - https://arxiv.org/abs/2408.10958 .. GENERATED FROM PYTHON SOURCE LINES 33-38 Set Up ------ All workflows inside Earth2Studio require constructed components to be handed to them. In this example, let's take a look at the most basic: :py:meth:`earth2studio.run.deterministic`. .. GENERATED FROM PYTHON SOURCE LINES 40-44 .. literalinclude:: ../../earth2studio/run.py :language: python :start-after: # sphinx - deterministic start :end-before: # sphinx - deterministic end .. GENERATED FROM PYTHON SOURCE LINES 46-55 Thus, we need the following: - Prognostic Model: Use the built in StormCast Model :py:class:`earth2studio.models.px.StormCast`. - Datasource: Pull data from the HRRR data api :py:class:`earth2studio.data.HRRR`. - IO Backend: Let's save the outputs into a Zarr store :py:class:`earth2studio.io.ZarrBackend`. StormCast also requires a conditioning data source. We use a forecast data source here, GFS_FX :py:class:`earth2studio.data.GFS_FX`, but a non-forecast data source such as ARCO could also be used with appropriate time stamps. .. GENERATED FROM PYTHON SOURCE LINES 57-90 .. code-block:: Python from datetime import datetime from loguru import logger from tqdm import tqdm logger.remove() logger.add(lambda msg: tqdm.write(msg, end=""), colorize=True) import os os.makedirs("outputs", exist_ok=True) from dotenv import load_dotenv load_dotenv() # TODO: make common example prep function from earth2studio.data import GFS_FX, HRRR from earth2studio.io import ZarrBackend from earth2studio.models.px import StormCast # Load the default model package which downloads the check point from NGC package = StormCast.load_default_package() model = StormCast.load_model(package) # Create the data source data = HRRR() # Create and set the conditioning data source conditioning_data_source = GFS_FX() model.conditioning_data_source = conditioning_data_source # Create the IO handler, store in memory io = ZarrBackend() .. GENERATED FROM PYTHON SOURCE LINES 91-99 Execute the Workflow -------------------- With all components initialized, running the workflow is a single line of Python code. Workflow will return the provided IO object back to the user, which can be used to then post process. Some have additional APIs that can be handy for post-processing or saving to file. Check the API docs for more information. For the forecast we will predict for 4 hours .. GENERATED FROM PYTHON SOURCE LINES 101-110 .. code-block:: Python import earth2studio.run as run nsteps = 4 today = datetime.today() date = today.isoformat().split("T")[0] io = run.deterministic([date], nsteps, model, data, io) print(io.root.tree()) .. GENERATED FROM PYTHON SOURCE LINES 111-118 Post Processing --------------- The last step is to post process our results. Cartopy is a great library for plotting fields on projections of a sphere. Here we will just plot the temperature at 2 meters (t2m) 4 hours into the forecast. Notice that the Zarr IO function has additional APIs to interact with the stored data. .. GENERATED FROM PYTHON SOURCE LINES 120-162 .. code-block:: Python import cartopy import cartopy.crs as ccrs import matplotlib.pyplot as plt forecast = f"{date}" variable = "t2m" step = 4 # lead time = 1 hr plt.close("all") # Create a correct Lambert Conformal projection projection = ccrs.LambertConformal( central_longitude=262.5, central_latitude=38.5, standard_parallels=(38.5, 38.5), globe=ccrs.Globe(semimajor_axis=6371229, semiminor_axis=6371229), ) # Create a figure and axes with the specified projection fig, ax = plt.subplots(subplot_kw={"projection": projection}, figsize=(10, 6)) # Plot the field using pcolormesh im = ax.pcolormesh( io["lon"][:], io["lat"][:], io[variable][0, step], transform=ccrs.PlateCarree(), cmap="Spectral_r", ) # Set state lines ax.add_feature( cartopy.feature.STATES.with_scale("50m"), linewidth=0.5, edgecolor="black", zorder=2 ) # Set title ax.set_title(f"{forecast} - Lead time: {step}hrs") # Add coastlines and gridlines ax.coastlines() ax.gridlines() plt.savefig(f"outputs/09_{date}_t2m_prediction.jpg") **Estimated memory usage:** 0 MB .. _sphx_glr_download_examples_09_stormcast_example.py: .. only:: html .. container:: sphx-glr-footer sphx-glr-footer-example .. container:: sphx-glr-download sphx-glr-download-jupyter :download:`Download Jupyter notebook: 09_stormcast_example.ipynb <09_stormcast_example.ipynb>` .. container:: sphx-glr-download sphx-glr-download-python :download:`Download Python source code: 09_stormcast_example.py <09_stormcast_example.py>` .. container:: sphx-glr-download sphx-glr-download-zip :download:`Download zipped: 09_stormcast_example.zip <09_stormcast_example.zip>` .. only:: html .. rst-class:: sphx-glr-signature `Gallery generated by Sphinx-Gallery `_